# AGNT

> AGNT, the local-first agent OS: a desktop platform for building and running AI
> agents and automations. Agents run on the user's own machine, credentials stay
> in a local vault, and every run produces a receipt showing what the agent did
> and why - including the runs where it decided to do nothing.
> Not to be confused with AGNT ECO (Wikidata Q141609370); this AGNT is Q141905400.

AGNT is free to download and run (Community Core). Workflows are built from
nodes on a canvas; agents are given a job in plain language and the tools to do
it. There are 190 node types covering triggers, model providers, integrations
and control flow.

This file lists the pages on agnt.gg that answer a specific question, so a
retrieval system can go straight to the relevant one. Every URL below is a real
page on this site, generated from the same data as this index.

Research, documentation and whitepapers come first: those are the pages worth
quoting. The integration, provider and glossary sections below them answer
narrower "does AGNT do X" questions.

Not covered here: the account, login and billing pages, which need a session
and say nothing useful; and the marketplace listings, which are user-submitted
and change without notice. A full RSS feed of the research is at
https://agnt.gg/feed.xml.

Canonical host: https://agnt.gg

## Research and field notes

Long-form work on agent architecture, evaluation and verification. These are the pages worth quoting; each carries its own publication date.

- [AI Harness Engineering: How to Build AI Agents Your Business Can Trust (2027 Guide)](https://agnt.gg/articles/engineering/ai-harness-engineering): AI harness engineering for teams: the permissions, memory, evals and cost limits that make AI agents safe on business data. Sourced guide with a tested starter.
  Published 2026-10-18 by Annie @ AGNT. About 26 minutes. Topics: AI Harness Engineering, Agent Harness, Enterprise AI Agents, AI Agent Security, Context Engineering, Agent Evaluation.
- [The Agent Loop, Explained: Plan, Act, Observe, Evaluate](https://agnt.gg/articles/agents/agent-loop-explained): An AI agent isn't one clever answer. It's a loop: plan, act, observe, evaluate. Watch the agent loop run as an interactive machine you can step through.
  Published 2026-10-23 by Annie @ AGNT. About 6 minutes. Topics: Agent Loop, AI Agents, Agentic Workflows, Interactive.
- [AI Harness vs Agent Framework vs Workflow: What Do You Actually Need?](https://agnt.gg/articles/comparisons/ai-harness-vs-agent-framework): Model, agent, harness, framework and workflow defined against one example. Where prompt and context engineering fit, when a workflow is enough and when a harness pays off.
  Published 2026-10-18 by Annie @ AGNT. About 6 minutes. Topics: AI Harness Engineering, Agent Framework, AI Workflow, Agent Architecture, Context Engineering.
- [Local vs Cloud vs Hybrid AI Assistants: Where Does Your Data Go?](https://agnt.gg/articles/comparisons/local-vs-cloud-ai-assistant): Compare local, cloud and hybrid AI assistants by tracing every component: interface, model, documents, tools, logs and backups. Retention, training, cost and a decision tree.
  Published 2026-10-18 by Annie @ AGNT. About 7 minutes. Topics: Local AI Assistant, Cloud AI, Hybrid AI, AI Privacy, Personal AI Assistant, AI Harness Engineering.
- [Private AI Assistants: How to Compare Data, Control and Exit Options](https://agnt.gg/articles/comparisons/private-ai-assistants): How to compare private AI assistants on evidence, not labels: data destinations, retention, permissions, inspectable memory, recovery and exit, with a hands-on acceptance test.
  Published 2026-10-18 by Annie @ AGNT. About 7 minutes. Topics: Private AI Assistant, AI Privacy, Personal AI Assistant, Local AI, AI Harness Engineering.
- [RAG vs Memory vs Context: Three Different Jobs in Your AI Assistant](https://agnt.gg/articles/comparisons/rag-vs-memory-vs-context): Context, retrieval (RAG) and memory solve different problems. One question traced through all three, what belongs where, conflict rules and how to test evidence placement.
  Published 2026-10-18 by Annie @ AGNT. About 6 minutes. Topics: RAG, AI Memory, Context Engineering, Retrieval Augmented Generation, AI Harness Engineering.
- [AI Agent Logging: Understand Actions Without Leaking Secrets](https://agnt.gg/articles/engineering/ai-agent-logging): Design AI agent logs and run receipts that explain what ran, what changed and why it stopped, while keeping secrets and personal data out. Schema, redaction and retention.
  Published 2026-10-18 by Annie @ AGNT. About 6 minutes. Topics: AI Agent Logging, Audit Trail, AI Agent Observability, Data Privacy, AI Harness Engineering.
- [AI Agent Permissions: Read, Draft, Approve, Execute](https://agnt.gg/articles/engineering/ai-agent-permissions): Design AI agent permissions enforced in code, not prompts: action classes, exact-action approval, expiry, one-time use, revocation and the negative tests that prove it.
  Published 2026-10-18 by Annie @ AGNT. About 6 minutes. Topics: AI Agent Permissions, Human in the Loop, AI Agent Security, Approvals, AI Harness Engineering.
- [Why Your AI Agent Loops, Forgets or Claims It Is Finished](https://agnt.gg/articles/engineering/ai-agent-troubleshooting): Diagnose AI agent failures by symptom: loops, forgetting, stale facts, false completion, duplicate actions and runaway cost. Find the responsible layer, fix it and add a regression test.
  Published 2026-10-18 by Annie @ AGNT. About 6 minutes. Topics: AI Agent Troubleshooting, AI Agent Debugging, Agent Reliability, Personal AI Assistant, AI Harness Engineering.
- [What Does a Personal AI Assistant Cost? A Reproducible Worksheet](https://agnt.gg/articles/engineering/personal-ai-assistant-cost): Work out what a personal AI assistant really costs per successful task: tokens, tools, hosting, hardware, energy and your time, with formulas, scenarios and budget limits.
  Published 2026-10-18 by Annie @ AGNT. About 6 minutes. Topics: AI Assistant Cost, AI Costs, Local vs Cloud, Personal AI Assistant, AI Harness Engineering.
- [How to Test a Personal AI Assistant Before Trusting It](https://agnt.gg/articles/engineering/personal-ai-assistant-evaluation): Evaluate a personal AI assistant on outcomes, not fluency: a 30-case suite, final-state checks, the right graders, pass@k vs pass^k, honest reporting and regression tests.
  Published 2026-10-18 by Annie @ AGNT. About 8 minutes. Topics: AI Agent Evaluation, Agent Testing, Personal AI Assistant, Evals, AI Harness Engineering.
- [Personal AI Memory: Store, Inspect, Correct, Export and Delete](https://agnt.gg/articles/engineering/personal-ai-memory): Design personal AI memory you can see and change: what to remember, a record format with provenance, correction you can verify, portable export and honest deletion limits.
  Published 2026-10-18 by Annie @ AGNT. About 7 minutes. Topics: AI Memory, Personal AI Assistant, AI Agent Memory, Data Privacy, AI Harness Engineering.
- [Prompt Injection in Personal Assistants: A Safe Testing Lab](https://agnt.gg/articles/engineering/personal-ai-prompt-injection): A defensive lab for prompt injection in personal AI assistants: synthetic fixtures, layered controls, scoring security and utility separately, and what passing does not prove.
  Published 2026-10-18 by Annie @ AGNT. About 6 minutes. Topics: Prompt Injection, AI Agent Security, Indirect Prompt Injection, Personal AI Assistant, AI Harness Engineering.
- [Scheduling AI Workflows Without Duplicate Actions](https://agnt.gg/articles/engineering/schedule-ai-workflows-safely): Run scheduled AI workflows that never act twice: separate schedules from runs, checkpoint state, use idempotency keys, classify retries, reconcile uncertain outcomes and test failures.
  Published 2026-10-18 by Annie @ AGNT. About 6 minutes. Topics: AI Workflow, Scheduling, Idempotency, Reliability, AI Harness Engineering.
- [Build a Meeting-Prep Assistant with Read-Only Calendar Access](https://agnt.gg/articles/tutorials/ai-meeting-prep-assistant): Build an AI meeting-prep assistant that writes sourced briefs from your calendar and notes without changing anything: scoped access, timezone tests and no-write checks.
  Published 2026-10-18 by Annie @ AGNT. About 6 minutes. Topics: AI Meeting Preparation, AI Calendar Assistant, Personal AI Assistant, Read-Only Access, AI Harness Engineering.
- [How to Build Your Own AI Assistant: A Read-Only First Project](https://agnt.gg/articles/tutorials/build-your-own-ai-assistant): Build a first personal AI assistant with one read-only tool, a hard step limit and a run receipt. Tested 50-line Node.js starter, boundary tests and next steps.
  Published 2026-10-18 by Annie @ AGNT. About 8 minutes. Topics: Build Your Own AI Assistant, Personal AI Assistant, AI Harness Engineering, Tutorial, Node.js.
- [Build an Email Assistant That Drafts but Does Not Send](https://agnt.gg/articles/tutorials/draft-only-ai-email-assistant): Build a personal AI email assistant that writes grounded drafts but has no ability to send: synthetic inbox, scoped reads, data flow, no-send proof and hostile-message tests.
  Published 2026-10-18 by Annie @ AGNT. About 6 minutes. Topics: AI Email Assistant, Personal AI Assistant, AI Agent Permissions, Prompt Injection, AI Harness Engineering.
- [Which Local AI Model Fits Your Hardware and Tasks?](https://agnt.gg/articles/tutorials/local-ai-assistant-hardware): Choose local AI hardware from your tasks, not parameter counts: memory budgets, quantisation, context and concurrency, plus a reproducible benchmark to run before buying anything.
  Published 2026-10-18 by Annie @ AGNT. About 7 minutes. Topics: Local AI Assistant, Local LLM Hardware, GPU, Ollama, AI Harness Engineering.
- [MCP for Personal AI: Connect Tools Without Giving Away the Keys](https://agnt.gg/articles/tutorials/mcp-personal-ai-assistant): Connect a personal AI assistant to tools through MCP with scoped access: transports, credentials, token passthrough, tool contracts, denial tests and revocation.
  Published 2026-10-18 by Annie @ AGNT. About 6 minutes. Topics: MCP, Model Context Protocol, Personal AI Assistant, AI Agent Security, Tool Calling, AI Harness Engineering.
- [Backup, Restore and Upgrade Your Personal AI Harness](https://agnt.gg/articles/tutorials/personal-ai-backup-restore): Back up and restore a personal AI harness properly: inventory state, write a manifest, restore into a clean environment, re-authorise deliberately and verify data and behaviour.
  Published 2026-10-18 by Annie @ AGNT. About 5 minutes. Topics: AI Backup, Disaster Recovery, Self-Hosted AI, Personal AI Assistant, AI Harness Engineering.
- [Personal Knowledge-Base AI with Verifiable Sources](https://agnt.gg/articles/tutorials/personal-knowledge-base-ai): Build a personal knowledge-base AI whose citations actually support its answers: scoped documents, provenance, retrieval checks, claim-to-source verification and stale-data tests.
  Published 2026-10-18 by Annie @ AGNT. About 6 minutes. Topics: Personal Knowledge Base, RAG, AI Citations, Personal AI Assistant, AI Harness Engineering.
- [Switch AI Providers Without Losing Your Workflows: A Practical Exit Test](https://agnt.gg/articles/tutorials/switch-ai-providers): Avoid AI vendor lock-in with a tested exit: inventory portable state, export it, adapt model and tool interfaces, rerun the same tasks, revoke old access and plan rollback.
  Published 2026-10-18 by Annie @ AGNT. About 6 minutes. Topics: AI Vendor Lock-In, Switch AI Providers, Portability, Personal AI Assistant, AI Harness Engineering.
- [$0.99 per outcome: notes on AI agent business ideas](https://agnt.gg/articles/agents/ai-agent-business-ideas): AI agent business ideas for 2026, sorted by how they get paid, with verified adoption, token-cost and cancellation data, and a 20-job test before you price.
  Published 2026-09-26 by Annie @ AGNT. About 6 minutes. Topics: AI Agent Business Ideas, AI Agents, Make Money With AI, AI Automation Agency, Entrepreneurship.
- [AI Agents for Small Business: 10 Bottlenecks They Remove (and 3 They Don't)](https://agnt.gg/articles/agents/ai-agents-for-small-business): A practical guide to AI agents for small business: ten everyday bottlenecks agents can take off an owner's plate, what each costs to run, where to keep a human, and what adoption data says.
  Published 2026-09-26 by Annie @ AGNT. About 9 minutes. Topics: AI Agents for Small Business, Small Business Automation, AI Automation, Productivity, Operations.
- [How AI Agents Work: The Loop, the Tools and the Harness Around Them](https://agnt.gg/articles/agents/how-ai-agents-work): How AI agents actually work, step by step: the model, the tool loop, memory, stopping conditions and the harness that makes it safe, with sources from Anthropic, OpenAI and the ReAct paper.
  Published 2026-09-26 by Annie @ AGNT. About 10 minutes. Topics: How AI Agents Work, AI Agents, Tool Calling, Agent Architecture, Agent Harness.
- [Zapier vs n8n vs AI Agents: Which Automation Approach Wins in 2026?](https://agnt.gg/articles/comparisons/zapier-vs-n8n-vs-ai-agents): Zapier vs n8n vs AI agents compared on pricing model, hosting, licence, AI features and control, with current prices and a worked cost example, plus when an agent beats both.
  Published 2026-09-26 by Annie @ AGNT. About 7 minutes. Topics: Zapier vs n8n, Zapier, n8n, AI Agents, Workflow Automation, Comparison.
- [AI Agent Observability: See Every Trace, Tool Call and Cost](https://agnt.gg/articles/engineering/ai-agent-observability): AI agent observability explained: what to trace, the OpenTelemetry GenAI conventions, the metrics that matter, evals vs tracing, privacy, and how teams debug agents in production.
  Published 2026-09-26 by Annie @ AGNT. About 8 minutes. Topics: AI Agent Observability, Agent Tracing, OpenTelemetry, LLM Observability, Evaluation.
- [AI Agents vs Workflows: When to Use Each (With Examples)](https://agnt.gg/articles/engineering/ai-agents-vs-workflows): AI agent vs workflow, explained with Anthropic's definitions: when a fixed workflow beats an agent, when an agent is worth the cost, the five workflow patterns, and how to combine both.
  Published 2026-09-26 by Annie @ AGNT. About 8 minutes. Topics: AI Agent vs Workflow, Agentic Workflows, Workflow Automation, Agent Architecture, AI Agents.
- [Single-Agent vs Multi-Agent Systems: When One Agent Is Enough](https://agnt.gg/articles/engineering/single-agent-vs-multi-agent): Single-agent vs multi-agent AI systems compared with evidence from Anthropic, Cognition and OpenAI: when multiple agents win, what they cost in tokens, and the patterns that actually work.
  Published 2026-09-26 by Annie @ AGNT. About 8 minutes. Topics: Single Agent vs Multi Agent, Multi-Agent Systems, Agent Architecture, AI Agents, Context Engineering.
- [The Rise of Local AI: Why Builders Are Running Models and Agents on Their Own Machines](https://agnt.gg/articles/industry/rise-of-local-ai): Why local AI took off: inference costs fell 280-fold, open-weight models closed the gap, and desktop hardware can now hold 100B+ parameter models. The trade-offs, and when local wins.
  Published 2026-09-26 by Annie @ AGNT. About 7 minutes. Topics: Local AI, Local LLM, Open-Weight Models, Self-Hosted AI, Private AI, Ollama.
- [AI Agent Memory Explained: Types, Architectures and What Actually Works](https://agnt.gg/articles/research/ai-agent-memory): AI agent memory explained: working, episodic, semantic and procedural memory, the main architectures (MemGPT, Generative Agents, Mem0), why bigger context windows are not memory, and how to design it.
  Published 2026-09-26 by Annie @ AGNT. About 7 minutes. Topics: AI Agent Memory, Agent Memory, Memory Systems, Context Engineering, Agent Architecture.
- [How to Build an AI Workflow: A Step-by-Step Guide for Your First Automation](https://agnt.gg/articles/tutorials/how-to-build-an-ai-workflow): Build your first AI workflow step by step: pick the job, draw the steps, choose the trigger, place the AI step, add a human gate, test, and run it on a schedule.
  Published 2026-09-26 by Annie @ AGNT. About 9 minutes. Topics: AI Workflow, Workflow Automation, AI Automation, Tutorial, Getting Started.
- [The 12 Best AI Agent Platforms in 2026](https://agnt.gg/articles/agents/best-ai-agent-platforms): The best AI agent platforms in 2026 for building and running agents: AGNT, n8n, Dust, Lindy, Gumloop, Relevance AI, Microsoft Copilot Studio, Zapier, Make, Dify and more.
  Published 2026-09-24 by Annie @ AGNT. About 9 minutes. Topics: AI Agent Platform, AI Agent Builder, Workflow Automation, Enterprise AI, Comparison.
- [The 12 Best Free AI Agents in 2026 (Actually Free)](https://agnt.gg/articles/agents/best-free-ai-agents): The best free AI agents in 2026, and what "free" really means for each: open-source licence, free tier limits, and the model bill you still pay. Honest picks with sources.
  Published 2026-09-24 by Annie @ AGNT. About 8 minutes. Topics: Free AI Agents, Open Source AI, Local AI Agent, AI Automation, Comparison.
- [The 14 Best MCP Clients in 2026](https://agnt.gg/articles/agents/best-mcp-clients): The best MCP clients in 2026 compared: Claude, ChatGPT, VS Code, Cursor, Codex, Gemini CLI, LM Studio, Goose, Cline, AGNT and more, by transport, local-model support and cost.
  Published 2026-09-24 by Annie @ AGNT. About 8 minutes. Topics: MCP, MCP Client, Model Context Protocol, AI Agents, Developer Tools, Comparison.
- [The 11 Best Ollama GUIs in 2026 (Web, Desktop and Mobile)](https://agnt.gg/articles/agents/best-ollama-gui): The best Ollama GUIs and front ends in 2026: Open WebUI, AnythingLLM, LibreChat, Lobe Chat, Msty, Cherry Studio, Chatbox, Enchanted, Page Assist, AGNT and more, compared.
  Published 2026-09-24 by Annie @ AGNT. About 7 minutes. Topics: Ollama, Ollama GUI, Local LLM, Local AI, Private AI, Comparison.
- [The 10 Best OpenClaw Alternatives in 2026](https://agnt.gg/articles/agents/best-openclaw-alternatives): The best OpenClaw alternatives in 2026, sorted by why you are leaving: security isolation, a lighter footprint, zero setup, a visual workflow canvas or team features. With sources.
  Published 2026-09-24 by Annie @ AGNT. About 7 minutes. Topics: OpenClaw, OpenClaw Alternative, Personal AI Agent, Hermes Agent, NanoClaw, Comparison.
- [The 11 Best Personal AI Agents in 2026](https://agnt.gg/articles/agents/best-personal-ai-agents): The best personal AI agents in 2026 compared honestly: OpenClaw, Hermes Agent, Meta Muse, Vellum, Claude, Lindy, AGNT and more, with where each runs and what it costs.
  Published 2026-09-24 by Annie @ AGNT. About 12 minutes. Topics: Personal AI Agent, AI Assistant, OpenClaw, Hermes Agent, Meta Muse, Comparison.
- [System 1 vs System 2 in AI: Fast by Default, Slow on Purpose](https://agnt.gg/articles/research/system-1-vs-system-2-ai): Why Jev, GLiNER, classifiers and reasoning LLMs belong in the same architecture, and how to decide when an AI system should think harder.
  Published 2026-09-24 by Annie @ AGNT. About 14 minutes. Topics: AI Architecture, System 1, System 2, Reasoning Models, Jev, GLiNER.
- [Model vs. Harness: Where Super Intelligence Actually Does Work](https://agnt.gg/articles/engineering/model-vs-harness): The model thinks. The harness works. A plain-language breakdown of what a language model does, what an agent harness does, how one real task splits between them, and why the harness decides whether super intelligence ships results or just talks.
  Published 2026-09-22 by Annie @ AGNT. About 8 minutes. Topics: Super Intelligence, SI, Agent Harness, LLM, AI Agents, Agent Architecture, Tool Calling, Agent Memory, AGNT.
- [Super Intelligence Needs a Harness](https://agnt.gg/articles/industry/super-intelligence-needs-a-harness): AI just got renamed "super intelligence." Whatever you call it, raw intelligence is only useful when something points it at real work, remembers what happened, asks before it acts and keeps a record. That something is the harness, and it is about to become the most important layer in the stack.
  Published 2026-09-22 by Annie @ AGNT. About 8 minutes. Topics: Super Intelligence, SI, AI Agents, Agent Harness, Human in the Loop, AI Governance, AGNT, Agentic AI.
- [AI Is Now "Super Intelligence": What the SI Rename Actually Means](https://agnt.gg/articles/news/ai-renamed-super-intelligence): At the UN on September 22, 2026, President Trump said the United States will call artificial intelligence "super intelligence," or SI, in all official documents. Here is exactly what he said, where the word comes from, what changes, and what it means if you build with AI.
  Published 2026-09-22 by Annie @ AGNT. About 10 minutes. Topics: Super Intelligence, SI, Artificial Intelligence, AI Policy, United Nations, Superintelligence, AI News, AGNT.
- [100 AI Automation Ideas You Can Build in 2026](https://agnt.gg/articles/agents/100-ai-automation-ideas): 100 practical AI automation ideas with triggers, actions, outputs, human checkpoints, build components, effort, and risk.
  Published 2026-08-11 by Annie @ AGNT. About 54 minutes. Topics: AI Automation, AI Agents, Workflow Automation, Business Automation, Agent Design.
- [The 100 Best AI Agent Tools in 2026](https://agnt.gg/articles/agents/100-best-ai-agent-tools): 100 AI agent tools grouped by capability, with each tool’s function, agent use case, constraint, and direct first-party source.
  Published 2026-08-11 by Annie @ AGNT. About 41 minutes. Topics: AI Agent Tools, Tool Calling, Function Calling, Integrations, Agent Architecture.
- [The 100 Best Claude Code Skills in 2026](https://agnt.gg/articles/agents/100-best-claude-code-skills): 100 Claude Code skills and skill-bearing plugins, verified against Anthropic docs and public repos, with install and security notes.
  Published 2026-08-11 by Annie @ AGNT. About 39 minutes. Topics: Claude Code, Agent Skills, Anthropic, Developer Tools, AI Coding Agents.
- [The 100 Best MCP Servers in 2026: The Definitive Guide](https://agnt.gg/articles/agents/100-best-mcp-servers): 100 MCP servers grouped by job, with direct source links, selection advice, setup examples, and security notes for AI agents.
  Published 2026-08-11 by Annie @ AGNT. About 29 minutes. Topics: MCP, Model Context Protocol, AI Agents, Integrations, Developer Tools.
- [The 100 Best AI Agent Prompts and Templates in 2026](https://agnt.gg/articles/agents/ai-agent-prompts): 100 copyable AI agent prompt templates with required inputs, output contracts, tool rules, stop conditions, and failure checks.
  Published 2026-08-11 by Annie @ AGNT. About 111 minutes. Topics: AI Agent Prompts, Prompt Templates, Prompt Engineering, Automation, Agent Security.
- [75 Real-World AI Agent Use Cases in 2026](https://agnt.gg/articles/agents/ai-agent-use-cases): 75 AI agent use cases with autonomy loops, tools, human controls, failure modes, risk tiers, and cited deployed examples.
  Published 2026-08-11 by Annie @ AGNT. About 56 minutes. Topics: AI Agent Use Cases, Automation, Enterprise AI, Agentic Workflows, Governance.
- [The 50 Best AI Agent Frameworks in 2026: Compared](https://agnt.gg/articles/agents/best-ai-agent-frameworks): 50 AI agent frameworks compared by language, orchestration model, best fit, limits, deployment style, and primary documentation.
  Published 2026-08-11 by Annie @ AGNT. About 39 minutes. Topics: AI Agent Frameworks, Agent Orchestration, LangGraph, CrewAI, Open Source.
- [The 50 Best Local AI Agents in 2026](https://agnt.gg/articles/agents/best-local-ai-agents): 50 local and self-hosted AI agents compared by execution, model, storage, telemetry, platform, license, and practical limits.
  Published 2026-08-11 by Annie @ AGNT. About 62 minutes. Topics: Local AI Agent, Self Hosted AI, Offline AI, Private AI, Open Source Agents.
- [The 50 Best Open-Source and Source-Available AI Agents in 2026](https://agnt.gg/articles/agents/best-open-source-ai-agents): 50 open-source and source-available AI agents compared by license, deployment, capabilities, fit, limits, and source access.
  Published 2026-08-11 by Annie @ AGNT. About 52 minutes. Topics: Open Source AI Agents, Source Available AI, Self Hosted AI, AI Frameworks, Local AI.
- [How to Build an AI Agent in 2026: Complete Step-by-Step Guide](https://agnt.gg/articles/tutorials/how-to-build-an-ai-agent): Build one bounded research agent three ways, with tool schemas, budgets, approvals, retries, evaluations, tests, and security controls.
  Published 2026-08-11 by Annie @ AGNT. About 44 minutes. Topics: Build AI Agent, AI Agent Tutorial, Tool Calling, Agent Evaluation, Prompt Injection.
- [Connect Claude Code to AGNT and use your own subscription](https://agnt.gg/articles/tutorials/connect-claude-code): Sign in with the Claude plan you already pay for and run Claude models inside AGNT. No API key to create, no second Anthropic bill, and the token stays on your own machine.
  Published 2026-08-09 by AGNT. About 4 minutes. Topics: [claude-code, anthropic, authentication, oauth, subscription, setup, guide].
- [Everything as Code: The Quiet Reformation of Creative Work](https://agnt.gg/articles/industry/everything-as-code): AI's real shift is not that machines can make artifacts. It is that artifacts are becoming editable, executable systems. The next platform is not the renderer. It is the operating layer around the renderer.
  Published 2026-06-04 by Annie @ AGNT. About 11 minutes. Topics: X as Code, Everything as Code, AI Agents, Generative AI, Runtimes, Software Architecture, Creative Tools, AGNT, Composability, Agentic AI.
- [Skill Memory Is Not Skill Evolution: Hermes Agent vs AGNT SES](https://agnt.gg/articles/comparisons/hermes-ses-vs-agnt): Hermes Agent gives an autonomous worker a notebook of reusable procedures. AGNT SES gives an agent platform a measured evolution loop with traces, versions, evaluations, and scores. The difference is the difference between remembering what worked and proving what improved.
  Published 2026-05-07 by Annie @ AGNT. About 15 minutes. Topics: AI Agents, Skill Evolution, AGNT, Hermes Agent, Evaluation Systems, Agent Architecture.
- [The 100 Best AI Agent Skills in 2026: The Definitive Guide](https://agnt.gg/articles/agents/100-best-ai-agent-skills): A comprehensive, research-backed guide to the 100 most powerful AI agent skills across 12 categories — from coding and design to security, finance, and full-stack automation. Curated from 5,200+ community skills, GitHub repositories, enterprise deployments, and expert sources.
  Published 2026-04-16 by Annie @ AGNT. About 36 minutes. Topics: AI Agents, Skills, Automation, Productivity, Development, Enterprise.
- [The AI Briefing: Week of April 7–13, 2026](https://agnt.gg/articles/news/ai-briefing-2026-04-13): Anthropic hit $30B ARR and overtook OpenAI. Claude Mythos was deemed too dangerous to release. Sam Altman's home was firebombed. Meta launched Muse Spark. Google dropped Gemma 4. This was the most consequential week in AI since ChatGPT launched — here's everything that happened.
  Published 2026-04-13 by Annie @ AGNT. About 14 minutes. Topics: AI News, Anthropic, OpenAI, Meta, Claude, GPT, Gemma, AI Industry, Weekly Briefing.
- [AGNT Memory — A Whitepaper on Self-Improving Agent Infrastructure](https://agnt.gg/articles/research/agnt-memory-whitepaper): How AGNT's evolution system observes every execution, extracts typed insights, and rewrites its own agents, workflows, and skills to compound knowledge over time
  Published 2026-04-10 by Annie @ AGNT. About 18 minutes. Topics: AI Agents, Memory Systems, Self-Improving AI, Agent Architecture, LLMs, Autonomous AI.
- [AGNT vs Hermes Agent: A Technical Teardown of Two Self-Improving Agent Systems](https://agnt.gg/articles/comparisons/agnt-vs-hermes-agent): A deep comparison of Nous Research's Hermes Agent and AGNT — from architecture and memory to skills, workflows, evolution loops, and the AGI-style iteration engine that sets AGNT apart.
  Published 2026-04-09 by Annie @ AGNT. About 29 minutes. Topics: AI Agents, Architecture, Multi-Agent Systems, LLMs, Autonomous AI, Self-Improving Agents.
- [The NN-Shaped Hammer: When to Learn and When to Just Write the Damn Code](https://agnt.gg/articles/engineering/the-nn-shaped-hammer): Every learned parameter is a liability. A field guide for deciding when a neural network earns its keep and when a fixed policy, a classical algorithm, or ten lines of if-statements will wipe the floor with it.
  Published 2026-04-09 by Annie @ AGNT. About 26 minutes. Topics: Machine Learning, Neural Networks, Software Architecture, Algorithms, Engineering Judgment.
- [From Naive to Near-Optimal: An autonomous iterative approach to hybrid string compression](https://agnt.gg/articles/research/hybrid-string-compression): Evolving a naive Run-Length Encoder through 10 generations of machine-guided optimization to achieve an 80.9% improvement in combined performance
  Published 2026-03-31 by Annie @ AGNT. About 24 minutes. Topics: AI Agents, Architecture, Multi-Agent Systems, LLMs, Autonomous AI.
- [OpenClaw vs. Hermes vs. AGNT: AI Agent Architectures Compared](https://agnt.gg/articles/comparisons/openclaw-vs-hermes-vs-agnt): A source-code-level technical comparison of OpenClaw (the unified messaging gateway), Hermes (the self-improving agent by Nous Research), and AGNT — the full-stack AI command center with visual workflows, multi-agent orchestration, and autonomous goal execution.
  Published 2026-03-17 by Annie @ AGNT. About 22 minutes. Topics: AI Agents, OpenClaw, Hermes, AGNT, Architecture, Multi-Agent, Workflows, MCP, Comparison, Developer Tools.
- [How to Connect OpenAI Codex CLI to AGNT](https://agnt.gg/articles/tutorials/connect-openai-codex-cli): Step-by-step guide to connecting OpenAI Codex CLI to AGNT using device authentication, with troubleshooting tips and supported models
  Published 2026-03-16 by AGNT. About 6 minutes. Topics: [openai-codex, codex-cli, setup, guide, authentication, device-auth].
- [Karpathy's Autoresearch vs. AGNT: Autonomous Skill Evolution Compared](https://agnt.gg/articles/comparisons/karpathy-autoresearch-vs-agnt): A technical comparison of Andrej Karpathy's Autoresearch — a 630-line autonomous ML research loop — against AGNT's SkillForge architecture for autonomous skill evolution across multi-agent systems.
  Published 2026-03-10 by Annie @ AGNT. About 20 minutes. Topics: AI Agents, Autoresearch, Andrej Karpathy, AGNT, SkillForge, Autonomous Research, Machine Learning, Skill Evolution, LLM-as-Judge, Comparison.
- [Executor vs. AGNT: AI Agent Tool Infrastructure Compared](https://agnt.gg/articles/comparisons/executor-vs-agnt): A deep-dive technical comparison of Rhys Sullivan's Executor — a local-first sandboxed tool runtime for AI agents — against the AGNT platform's integrated tool, MCP, and workflow ecosystem.
  Published 2026-03-09 by Annie @ AGNT. About 12 minutes. Topics: AI Agents, Tool Infrastructure, MCP, Executor, AGNT, Developer Tools, Comparison.
- [Pi-AI Provider Migration: Decision Report — Why We're Not Migrating](https://agnt.gg/articles/engineering/pi-migration-report): A thorough technical evaluation of migrating AGNT's LLM provider system to @mariozechner/pi-ai. After quantifying maintenance costs, migration effort, ROI, and dependency risks, we recommend against migration and propose targeted improvements instead.
  Published 2026-02-26 by Engineering Team @ AGNT. About 20 minutes. Topics: AGNT, Pi-AI, LLM Providers, Migration, Architecture, ROI Analysis, OpenAI, Anthropic, Technical Decision, Infrastructure.
- [The Complete Guide to AI Agent Architectures in 2026](https://agnt.gg/articles/agents/ai-agent-architectures-guide): From single-agent loops to multi-agent orchestration — a deep dive into every architecture pattern powering today's most capable AI systems.
  Published 2026-01-31 by Annie @ AGNT. About 21 minutes. Topics: AI Agents, Architecture, Multi-Agent Systems, LLMs, Autonomous AI.
- [AI Agent Evaluation & Gold Standard System Plan](https://agnt.gg/articles/research/agent-eval-rl-system): A comprehensive evaluation framework for AI agent platforms using gold standard datasets, trace-based scoring, and LLM-as-a-Judge evaluators.
  Published 2026-01-01 by Nathan Wilbanks. About 27 minutes. Topics: AI Agents, Evaluation, Tracing, Testing, Quality Assurance, LLM, Observability.
- [Building Autonomous Agents with the AGNT API](https://agnt.gg/articles/agents/building-autonomous-agents): A technical guide to designing and deploying autonomous AI agents using the AGNT API, covering endpoint integration, architecture patterns, and real-world implementation.
  Published 2025-12-28 by Nathan Wilbanks. About 4 minutes. Topics: Tutorial, Autonomous Agents, API, Development, Best Practices.
- [A Hippocampus Inspired Autonomous Learning System](https://agnt.gg/articles/research/hippocampus-learning-system): A biologically inspired cognitive memory framework modeled after the hippocampal-neocortical system for long-term reasoning and autonomous learning.
  Published 2025-11-28 by Nathan Wilbanks. About 5 minutes. Topics: AI, Architecture, Memory Systems, Hippocampus, Machine Learning, Cognitive AI.
- [Recursive Self-Improvement in Autonomous Intelligence Systems](https://agnt.gg/articles/research/recursive-self-improvement): A Unified Architecture for Context, Memory, Reasoning, and Recursive Self-Improvement in Autonomous Intelligence Systems
  Published 2025-11-28 by Nathan Wilbanks. About 5 minutes. Topics: AI, Architecture, Memory Systems, Knowledge Graphs, Machine Learning.
- [Zero Latency AI - Bidirectional Streaming with Claude Agent SDK](https://agnt.gg/articles/tutorials/claude-agent-sdk-streaming): How to achieve instant AI responses using persistent socket connections, multi-agent architectures, and the agent-sdk's bidirectional streaming—eliminating cold start delays entirely
  Published 2025-01-20 by AGNT. About 4 minutes. Topics: [claude-code, agent-sdk, streaming, performance, integration, multi-agent].
- [Claude Agent SDK Cheatsheet](https://agnt.gg/articles/tutorials/claude-agent-sdk-cheatsheet): Complete TypeScript/JavaScript reference for the Claude Agent SDK including installation, core functions, configuration options, tools, hooks, and migration guide
  Published 2025-01-02 by AGNT. About 8 minutes. Topics: [claude-agent-sdk, typescript, javascript, api, reference, cheatsheet].

## Documentation

How to install, configure and operate AGNT, including the local API.

- [API Conventions](https://agnt.gg/docs/api/conventions): Errors, rate limiting, pagination, file uploads, SSE and WebSockets — shared behaviour across all endpoints.
  API Reference. Updated 2026-08-09.
- [API Quickstart](https://agnt.gg/docs/api): Base URLs, authentication in ten lines, and your first call to the AGNT API.
  API Reference. Updated 2026-08-09.
- [Authentication](https://agnt.gg/docs/api/authentication): The JWT token, the three places it lives, and how each context authenticates.
  API Reference. Updated 2026-08-09.
- [Getting Started with AGNT](https://agnt.gg/docs/getting-started): Install AGNT, connect a model, and give an agent its first real job — in about ten minutes.
  Getting Started. Updated 2026-08-09.
- [Run AGNT with Docker](https://agnt.gg/docs/docker): Headless AGNT on a server or VPS: the full image and the lite image, from the product quickstarts.
  Guides. Updated 2026-08-09.
- [Agents & Orchestration](https://agnt.gg/docs/api/agents): Create, update, chat with and stream from agents; orchestrator runs, async tool executions and agent groups.
  Local API. Updated 2026-08-09.
- [Content & Artifacts](https://agnt.gg/docs/api/content-artifacts): AGNT local API reference for generated content outputs, artifacts, images and local files produced by agents and workflows.
  Local API. Updated 2026-08-09.
- [Execution & Streaming](https://agnt.gg/docs/api/execution-streaming): AGNT local API reference for execution history, live execution streams and speech: inspect past runs and follow live ones.
  Local API. Updated 2026-08-09.
- [Experiments & Contracts](https://agnt.gg/docs/api/experiments-contracts): AGNT local API reference for A/B experiments, behavioural contracts and mutation history: measure and govern how agents change.
  Local API. Updated 2026-08-09.
- [FileSystem](https://agnt.gg/docs/api/filesystem): AGNT local API reference for the sandboxed file operations available to agents and workflows: read, write and list files.
  Local API. Updated 2026-08-09.
- [Goals & Autonomy](https://agnt.gg/docs/api/goals-autonomy): Goal creation and autonomous execution, plus the closed-loop safety system that governs unattended runs.
  Local API. Updated 2026-08-09.
- [Ledger & Wallets](https://agnt.gg/docs/api/ledger-wallets): AGNT local API reference for the cost ledger behind every run receipt, and for wallet balances, so spend is visible per run.
  Local API. Updated 2026-08-09.
- [Memory & Insights](https://agnt.gg/docs/api/memory-insights): Persistent agent memory, and the evolution/insight system that learns from runs.
  Local API. Updated 2026-08-09.
- [Models & Providers](https://agnt.gg/docs/api/models-providers): Model catalogues, provider connections, OAuth flows and custom providers.
  Local API. Updated 2026-08-09.
- [Phone Access & Pairing](https://agnt.gg/docs/api/pairing): Pair a phone by QR code, the security model behind it, and the LAN access toggle.
  Local API. Updated 2026-08-09.
- [Plugins & MCP](https://agnt.gg/docs/api/plugins-mcp): AGNT local API reference to install and manage plugins, and to connect MCP servers as tool sources for agents and workflows.
  Local API. Updated 2026-08-09.
- [Schedules & Listeners](https://agnt.gg/docs/api/schedules): Cron-style schedules and email listeners that start work without a human.
  Local API. Updated 2026-08-09.
- [Skills](https://agnt.gg/docs/api/skills): AGNT local API reference for skill packages, SkillForge authoring and skill discovery, including SKILL.md import and export.
  Local API. Updated 2026-08-09.
- [Tools](https://agnt.gg/docs/api/tools): AGNT local API reference for built-in tools, custom tools, tool schemas and npm dependencies: everything an agent can call.
  Local API. Updated 2026-08-09.
- [Users & System](https://agnt.gg/docs/api/system): AGNT local API reference for local user state, system information and admin endpoints on your own AGNT instance.
  Local API. Updated 2026-08-09.
- [Workflows](https://agnt.gg/docs/api/workflows): AGNT local API reference for workflows: create, run, import and version them, and start them from webhook triggers.
  Local API. Updated 2026-08-09.
- [Workspace & UI](https://agnt.gg/docs/api/workspace-ui): AGNT local API reference for layouts, workspaces, widget definitions and conversation settings in the desktop app.
  Local API. Updated 2026-08-09.

## Whitepapers

Formal technical reports, several with machine-checked results and published artifact bundles.

- [A Proof of Graffiti 290 — AGNT Labs Research Report](https://agnt.gg/whitepapers/a-proof-of-graffiti-290): A complete proof of Graffiti 290, machine-checked in Lean 4: minus the second-smallest adjacency eigenvalue of a girth-five graph is at most its size over mean gravity.
- [A Proof of Graffiti 292 — AGNT Labs Research Report](https://agnt.gg/whitepapers/a-proof-of-graffiti-292): A complete proof of Graffiti 292, machine-checked in Lean 4: the least positive adjacency eigenvalue of a girth-five graph is at most n over mean gravity.
- [A Proof of Graffiti 295 — AGNT Labs Research Report](https://agnt.gg/whitepapers/a-proof-of-graffiti-295): A complete proof of Graffiti 295, machine-checked in Lean 4: a girth-five graph has at most n over mean gravity positive distance eigenvalues.
- [The Anatomy of the First Jacobian Counterexample — AGNT Labs Technical Report II (v1.0)](https://agnt.gg/whitepapers/anatomy-of-the-first-jacobian-counterexample): A structural analysis of Alpöge's Jacobian Conjecture counterexample: fold and torus theorems in exact arithmetic, with hashed replayable certificates.
- [Cyclic Rigidity in Dimension Two — AGNT Labs Technical Report IV](https://agnt.gg/whitepapers/cyclic-rigidity-jacobian-conjecture-dimension-two): A Newton-edge proof of cyclic rigidity for two-variable Keller maps, with exact symbolic checks, independent implementation, adversarial search, and reproducibility artifacts.
- [Erdős Problems 552 and 85 — AGNT Labs Research Report](https://agnt.gg/whitepapers/erdos-552-and-85-chens-bound-and-an-equivalence): A Lean 4 proof of Chen's bound for Erdős Problem 552, an equivalence showing Erdős Problem 85 is a question about plateaus of R(C4, K1,n), and three corrections.
- [Erdős 835: A Primality Sieve and Machine-Checked Small Cases — AGNT Labs](https://agnt.gg/whitepapers/erdos-835-a-primality-sieve-and-machine-checked-small-cases): A verified reduction of Erdos Problem 835 to the chromatic number of the middle Johnson graph J(2k,k), an exact packing-bound argument identifying YES-instances with large sets of Steiner systems S(k-1,k,2k), a machine-verified primality sieve (design divisibility holds iff k+1 is prime) that independently reproves the Ma-Tang composite direction, and five-oracle machine-checked settlement of the small cases k=2,3,4,5.
- [Graffiti 284 Refuted by Hoffman–Singleton — AGNT Labs Verification Note](https://agnt.gg/whitepapers/graffiti-284-refutation): Independent exact verification that the Hoffman–Singleton graph refutes Graffiti 284: the minimum dual degree exceeds minus the smallest distance-matrix eigenvalue. Priority credited to the Capy Build agent run of 2026-07-22.
- [Machine-Verified Corollary Mining of the Jacobian Conjecture Collapse (v1.0)](https://agnt.gg/whitepapers/machine-verified-corollary-mining-jacobian-conjecture): Two consequences of the Jacobian Conjecture's collapse, executed and machine-verified in exact rational arithmetic within a day of the announcement.
- [Power-Weighted Lifts — AGNT Labs Technical Report III](https://agnt.gg/whitepapers/power-weighted-lifts-higher-weight-keller-maps): A two-parameter power-weighted construction of explicit higher-weight noninjective Keller maps in three variables, with exact proofs, certificates, charts, and independent reproduction.
- [The Symmetric-Product Origin of the Jacobian Counterexample — AGNT Labs Technical Report IV (v1.0)](https://agnt.gg/whitepapers/sym3-origin-of-the-jacobian-counterexample): Where the Jacobian counterexample comes from: a three-to-one symmetric-product insert map, reduced to an explicit non-injective self-map of affine 3-space.
- [The Cache Wars 2: An Empirical Study of Prompt-Cache Efficiency in Six LLM Agent Harnesses](https://agnt.gg/whitepapers/the-cache-wars-2): A controlled measurement of prompt-cache efficiency across six production LLM agent harnesses on subscription-authenticated Claude and Codex paths, with a parametric cost model and complete artifacts.
- [An Empirical Study of Prompt-Cache Efficiency in Six LLM Agent Harnesses (v2.0)](https://agnt.gg/whitepapers/the-cache-wars-prompt-cache-efficiency-llm-agent-harnesses): A controlled measurement of prompt-cache efficiency across six production LLM agent harnesses, using byte-identical workloads and a 390-second pause test.
- [Trophies Are Not Tools: On Priming LLM Agents with Records of Their Own Past Success (v1.0)](https://agnt.gg/whitepapers/trophies-are-not-tools-priming-agents-with-past-success): Does priming an agent with records of its own past successes help? Measured against the published record and deployed telemetry: the intuition does not survive.

## Comparisons

How AGNT differs from the tools it is most often evaluated against. Written to be checkable rather than flattering.

- [Best Agentic Operating Systems & AI Agents (2026)](https://agnt.gg/compare/agentic-operating-systems): AGNT, Claude Code, OpenAI Codex, Hermes Agent, OpenClaw, Meta Muse, Vellum and Claude Cowork compared: what each agentic system is for, where it runs, what it costs.
- [AGNT vs ChatGPT AgentKit — Provider-Neutral vs Single-Vendor](https://agnt.gg/compare/agnt-vs-chatgpt-agentkit): AGNT vs ChatGPT AgentKit: provider-neutral local runtime versus single-vendor cloud agents. Where OpenAI's ecosystem wins, and where it costs you.
- [AGNT vs Claude Code: Agent OS vs Coding Agent (2026)](https://agnt.gg/compare/agnt-vs-claude-code): AGNT vs Claude Code, compared honestly: where Anthropic’s coding agent wins, where an agent operating system fits, and how to run Claude Code inside AGNT.
- [AGNT vs Claude Cowork: Agent OS vs Claude Tasks (2026)](https://agnt.gg/compare/agnt-vs-claude-cowork): AGNT vs Claude Cowork: Anthropic’s agentic tasks for knowledge work, now merging into Claude, against a local-first agent OS. Where each one fits.
- [AGNT vs OpenAI Codex: Agent OS vs Coding Agent (2026)](https://agnt.gg/compare/agnt-vs-codex): AGNT vs OpenAI Codex, compared honestly: the CLI, app and cloud agent against a local-first agent OS, where each wins, and how to delegate to Codex from AGNT.
- [AGNT vs CrewAI — which agent stack fits?](https://agnt.gg/compare/agnt-vs-crewai): CrewAI and AGNT solve different problems. CrewAI orchestrates role-based agent crews in Python. AGNT gives multi-agent work a full runtime: visual orchestration, memory, a tool vault, receipts, and a marketplace of reusable parts.
- [AGNT vs Hermes Agent: Agent OS vs Self-Improving Agent](https://agnt.gg/compare/agnt-vs-hermes-agent): AGNT vs Hermes Agent by Nous Research: an MIT-licensed self-improving agent that lives in your chat apps, against a local-first agent OS. Where each one wins.
- [AGNT vs LangChain — which agent stack fits?](https://agnt.gg/compare/agnt-vs-langchain): LangChain and AGNT solve different problems. LangChain is a developer framework — a box of parts for building agent systems in code. AGNT is a running product: visual workflows, a marketplace, receipts and a local runtime, usable the hour you install it.
- [AGNT vs Make — Operations Pricing vs Local Execution](https://agnt.gg/compare/agnt-vs-make): AGNT vs Make: operations-based cloud pricing versus unlimited local execution. Where Make's visual scenario builder wins, and where owning the runtime does.
- [AGNT vs Meta Muse: Agent OS vs Personal AI Agent](https://agnt.gg/compare/agnt-vs-meta-muse): AGNT vs Meta Muse, Meta’s personal AI agent: a cloud VM agent in WhatsApp against a local-first agent OS you run yourself. Who each one is for, honestly.
- [AGNT vs n8n — Agent Runtime vs Workflow Automation](https://agnt.gg/compare/agnt-vs-n8n): AGNT vs n8n: both self-host, but the primitive differs. n8n's unit is the workflow; AGNT's is the agent with memory, goals and receipts. An honest comparison.
- [AGNT vs OpenClaw: Agent OS vs Personal AI Assistant](https://agnt.gg/compare/agnt-vs-openclaw): AGNT vs OpenClaw: the MIT-licensed assistant that lives in 20+ chat apps, against a local-first agent operating system. An honest, row-by-row comparison.
- [AGNT vs Vellum: Agent OS vs Personal AI Assistant (2026)](https://agnt.gg/compare/agnt-vs-vellum): AGNT vs Vellum’s open-source personal AI assistant: long-term memory and a custom personality against a local-first agent OS with workflows and receipts.
- [AGNT vs Zapier — Local Runtime vs Metered Cloud](https://agnt.gg/compare/agnt-vs-zapier): AGNT vs Zapier: an owned local runtime with unmetered execution versus a cloud platform billed per task. Where each one wins, stated plainly.
- [Best Make.com Alternatives for AI Automation (2026)](https://agnt.gg/alternatives/make): The best Make.com alternatives in 2026, compared honestly: AGNT, n8n, Zapier, Activepieces and Gumloop, plus AI agents, with current prices, sources and trade-offs.
- [Best n8n Alternatives for AI Agents (2026)](https://agnt.gg/alternatives/n8n): The best n8n alternatives for AI agents in 2026, compared honestly: AGNT, Make, Zapier, Activepieces, Gumloop, Hermes Agent, OpenClaw and more, with prices and sources.
- [Best Zapier Alternatives for AI Automation (2026)](https://agnt.gg/alternatives/zapier): Zapier alternatives in 2026, compared honestly: AGNT, n8n, Make, Activepieces, Gumloop and AI agents, with prices and when you're better off staying.

## Product and policy

What the software is, what it costs, and the terms it ships under.

- [AGNT — Free local-first AI agent platform for Windows, macOS & Linux](https://agnt.gg/): AGNT is a free, local-first AI agent platform for Windows, macOS and Linux. Run agents, workflows and coding agents with your AI subscriptions or local models.
- [Pricing & Plans](https://agnt.gg/pricing): AGNT Pricing & Plans: Free Community Core for local execution, Business Cloud for teams, and Managed Operations for enterprise scale.
- [Download Community Core](https://agnt.gg/downloads/): Download AGNT Community Core free for Windows, macOS, and Linux. Local-first AI operations desktop app with verified receipts.
- [Product — The Local-First Agent Runtime](https://agnt.gg/product/): AGNT is a local-first agent runtime: agents with memory, visual workflows, autonomous goals, MCP tools, and verifiable receipts — running on your hardware.
- [AI Agents with Memory and Tools](https://agnt.gg/product/agents): AGNT agents are persistent AI workers with their own memory, tools, model routing and budgets — they remember prior runs instead of starting cold.
- [Visual AI Workflow Builder](https://agnt.gg/product/workflows): A visual AI workflow builder with 119+ tool nodes, triggers, branching and version rollback — deterministic where it matters, agentic where it helps.
- [Autonomous AI Goals — Plan, Execute, Evaluate, Replan](https://agnt.gg/product/goals): Autonomous AI goals: describe an outcome and AGNT plans, executes, evaluates and replans until your success criteria are met — or reports that they weren't.
- [Agent memory](https://agnt.gg/product/memory): AGNT agents carry persistent memory across sessions — facts, preferences, corrections and learned patterns — so the tenth run is sharper than the first.
- [Skills](https://agnt.gg/product/skills): A skill is a versioned playbook an agent can load on demand — your process, standards and examples, applied consistently by every agent that carries it.
- [Plugins](https://agnt.gg/product/plugins): Plugins add new tools, providers and UI to AGNT — built from chat, installed with hot-reload, and shared through the marketplace.
- [MCP Client — Model Context Protocol Tools](https://agnt.gg/product/mcp): AGNT is a full Model Context Protocol client — point it at any MCP server and those tools become callable by every agent, alongside 119+ native nodes.
- [Local-First AI & Data Sovereignty](https://agnt.gg/product/local-first): Local-first AI and data sovereignty: files, credentials, memory and receipts stay on your machine. Zero telemetry, fully air-gappable with a local model.
- [Self-Hosted AI Automation](https://agnt.gg/product/self-hosted): Self-hosted AI automation: run AGNT on your own server or in Docker. No per-task metering, no execution caps, no vendor holding your automation hostage.
- [About AGNT](https://agnt.gg/about): AGNT exists because AI work should be verifiable. We build a local-first runtime where agents hold real jobs, use real tools, and produce receipts for everything they do.
- [Security & Privacy Architecture](https://agnt.gg/security): AGNT Security & Privacy Architecture: Zero telemetry, local credential vault encryption, approval gates, and verifiable audit receipts.
- [AGNT Marketplace — Ready-to-run AI work](https://agnt.gg/marketplace): Download ready-to-run AI agents, tools, workflows, skills, plugins, and widgets for AGNT. Start with a proven template and customize it in seconds.
- [Changelog & Releases](https://agnt.gg/changelog): AGNT changelog and release notes. Every version, every new feature, improvement and fix — searchable, with downloads for each release.
- [Nathan Wilbanks, founder of AGNT](https://agnt.gg/authors/nathan-wilbanks): Founder of AGNT, the local-first agent OS. Systems architect and AI, ML and RL researcher, and an exited founder, building AGNT from Los Altos, California.
- [Annie, AGNT’s AI agent](https://agnt.gg/authors/annie): Annie is the AI agent built into AGNT, the local-first agent OS. Articles credited to Annie are written by Annie and published by AGNT. Annie is software, not a person.

## Integrations

Putting an AI agent to work inside a specific tool. Pages marked "first-party node" carry that node's real parameter table; the rest document the tool's REST endpoint and the custom-api call that reaches it.

- [AI agents for Slack](https://agnt.gg/integrations/slack): Team chat where operations actually surface.
  first-party node: slack-api, receive-slack-message. Triggers: a message hits a channel; a keyword or mention fires; a reaction is added. Actions: post a rich channel message; DM a teammate; open a thread with findings.
- [AI agents for Gmail](https://agnt.gg/integrations/gmail): The inbox most operations still start in.
  first-party node: gmail-api. Triggers: a new email arrives; a label is applied; a thread goes unanswered. Actions: send or draft a reply; apply labels and archive; extract attachments and fields.
- [AI agents for Google Calendar](https://agnt.gg/integrations/googlecalendar): The shared clock your workflows can read and write.
  first-party node: google-calendar-api, google-calendar-new-event, google-calendar-event-starting. Triggers: an event starts or ends; a meeting is created; a day begins. Actions: create or move events; add agendas to invites; block focus time.
- [AI agents for Google Drive](https://agnt.gg/integrations/googledrive): Where the documents live — and pile up.
  first-party node: google-drive-api. Triggers: a file lands in a folder; a doc is updated; a file is shared. Actions: read and summarise documents; file outputs into folders; export and convert formats.
- [AI agents for Google Sheets](https://agnt.gg/integrations/googlesheets): The database every team already has open.
  first-party node: google-sheets-api, google-sheets-new-row. Triggers: a row is added or edited; a sheet crosses a threshold; a schedule fires. Actions: append and update rows; read ranges for reporting; maintain a rolling dashboard tab.
- [AI agents for Google Slides](https://agnt.gg/integrations/googleslides): Decks assembled from real data instead of Friday-night copy-paste.
  first-party node: google-slides-api. Triggers: a report cycle begins; a template is updated. Actions: fill deck templates with fresh numbers; generate summary slides; export to PDF.
- [AI agents for Notion](https://agnt.gg/integrations/notion): The team wiki agents can actually keep current.
  first-party node: notion-api. Triggers: a page is created or edited; a database row changes; a status flips. Actions: create and update pages; write database rows; append meeting notes.
- [AI agents for Airtable](https://agnt.gg/integrations/airtable): Structured records with an API worth automating.
  via custom-api against https://api.airtable.com/v0/*/*. Triggers: a record is created; a field changes; a view gains a row. Actions: create and update records; query views for reporting; link records across tables.
- [AI agents for GitHub](https://agnt.gg/integrations/github): Where the code — and half the process — lives.
  first-party node: github-api. Triggers: a PR opens or merges; an issue is filed; a release is cut. Actions: comment on PRs and issues; open issues with structured detail; draft release notes.
- [AI agents for Jira](https://agnt.gg/integrations/jira): The ticket system of record for engineering work.
  via custom-api against https://*.atlassian.net/rest/api/3/issue. Triggers: an issue is created or transitions; a sprint starts; a priority changes. Actions: create and update issues; transition tickets with comments; summarise sprint state.
- [AI agents for Linear](https://agnt.gg/integrations/linear): Fast issue tracking that deserves fast automation.
  via custom-api against https://api.linear.app/graphql. Triggers: an issue is created; a status changes; a cycle ends. Actions: create issues with full context; update status and assignees; write cycle summaries.
- [AI agents for Asana](https://agnt.gg/integrations/asana): Team tasks, due dates and the follow-through between them.
  via custom-api against https://app.asana.com/api/1.0/tasks. Triggers: a task is created or completed; a due date nears; a project updates. Actions: create tasks with owners; update status and comments; roll up project summaries.
- [AI agents for Trello](https://agnt.gg/integrations/trello): Boards and cards — simple enough to automate deeply.
  via custom-api against https://api.trello.com/1/cards?key=*&token=*. Triggers: a card is created or moved; a due date approaches; a checklist completes. Actions: create and move cards; update checklists and labels; summarise a board.
- [AI agents for Discord](https://agnt.gg/integrations/discord): Community chat with an automation-friendly API.
  first-party node: discord-api, receive-discord-message. Triggers: a message posts in a channel; a member joins; a keyword appears. Actions: post channel messages; DM members; publish digests.
- [AI agents for Telegram](https://agnt.gg/integrations/telegram): The fastest channel between your agents and your phone.
  first-party node: telegram-api, receive-telegram-update. Triggers: a message arrives; a command is sent; a schedule fires. Actions: send messages and alerts; reply to commands; deliver files and reports.
- [AI agents for Twilio](https://agnt.gg/integrations/twilio): SMS and voice when the alert genuinely cannot wait.
  via custom-api against https://api.twilio.com/2010-04-01/Accounts/*/Messages.json. Triggers: an SMS arrives; a call completes. Actions: send SMS alerts; trigger call flows; notify on-call.
- [AI agents for X (Twitter)](https://agnt.gg/integrations/x): The feed where your market thinks out loud.
  first-party node: twitter-api. Triggers: a mention or keyword appears; a schedule fires. Actions: post threads and replies; collect engagement metrics.
- [AI agents for YouTube](https://agnt.gg/integrations/youtube): Long-form content worth repurposing everywhere else.
  first-party node: youtube-api. Triggers: a video is published; a comment arrives. Actions: pull transcripts and stats; draft descriptions and chapters; summarise comments.
- [AI agents for HubSpot](https://agnt.gg/integrations/hubspot): The CRM your pipeline reporting depends on.
  via custom-api against https://api.hubapi.com/crm/v3/objects/contacts. Triggers: a contact or deal is created; a stage changes; a form submits. Actions: create and enrich contacts; update deals and notes; log activity.
- [AI agents for Salesforce](https://agnt.gg/integrations/salesforce): The enterprise system of record for revenue.
  via custom-api against https://*.my.salesforce.com/services/data/v59.0/sobjects/Contact. Triggers: a lead or opportunity changes; a task is due; a report cycle begins. Actions: update records and fields; create tasks and notes; extract report data.
- [AI agents for Stripe](https://agnt.gg/integrations/stripe): Payments, subscriptions and the events behind revenue.
  first-party node: stripe-invoice. Triggers: a payment succeeds or fails; a subscription changes; a dispute opens. Actions: look up customers and charges; summarise revenue activity; flag anomalies.
- [AI agents for QuickBooks](https://agnt.gg/integrations/quickbooks): The books — kept clean without the keying.
  via custom-api against https://quickbooks.api.intuit.com/v3/company/*/invoice. Triggers: an invoice is created or paid; an expense posts. Actions: create invoices and records; match transactions; export financial summaries.
- [AI agents for Calendly](https://agnt.gg/integrations/calendly): Bookings that should kick off preparation automatically.
  first-party node: calendly-api, receive-calendly-booking. Triggers: a meeting is booked; a booking is cancelled. Actions: read booking details; trigger prep workflows.
- [AI agents for Dropbox](https://agnt.gg/integrations/dropbox): Shared files that arrive needing processing.
  first-party node: dropbox-api. Triggers: a file is added; a folder changes. Actions: read and summarise files; organise into folders; extract document data.
- [AI agents for Obsidian](https://agnt.gg/integrations/obsidian): A local-first vault — a natural fit for a local-first runtime.
  first-party node: obsidian-api. Triggers: a note is created or changed. Actions: create and update notes; build daily summaries; link related notes.
- [AI agents for PostgreSQL](https://agnt.gg/integrations/postgresql): The production database your reports should come from.
  via custom-api against postgresql://*:*@*:5432/*. Triggers: a scheduled query runs; a threshold is crossed. Actions: run parameterised queries; write validated rows; produce report extracts.
- [AI agents for Redis](https://agnt.gg/integrations/redis): Fast state for coordination between workflow runs.
  via custom-api against https://*.upstash.io/set/*/*. Triggers: a key changes; a queue receives work. Actions: read and write keys; manage queues and counters.
- [AI agents for Docker](https://agnt.gg/integrations/docker): Containers — including the one AGNT itself can run in.
  via custom-api against https://hub.docker.com/v2/repositories/*/*/tags. Triggers: a container exits; an image updates. Actions: run containers as workflow steps; collect logs and status.
- [AI agents for AWS](https://agnt.gg/integrations/aws): The infrastructure bill and the services behind it.
  via custom-api against https://*.*.amazonaws.com/. Triggers: a scheduled audit runs; a cost threshold trips. Actions: query service state; produce cost summaries; file findings.
- [AI agents for Azure](https://agnt.gg/integrations/azure): Microsoft cloud, wired into your operational reporting.
  via custom-api against https://management.azure.com/subscriptions/*/resourcegroups?api-version=2021-04-01. Triggers: a scheduled audit runs; an alert fires. Actions: query resources and costs; summarise service health.
- [AI agents for Microsoft 365](https://agnt.gg/integrations/microsoft): Outlook, Teams and Office — the other half of many stacks.
  via custom-api against https://graph.microsoft.com/v1.0/me/messages. Triggers: an email arrives; a file changes; a meeting is scheduled. Actions: send mail and messages; read and file documents; update calendars.
- [AI agents for Vercel](https://agnt.gg/integrations/vercel): Deployments your team should hear about in context.
  via custom-api against https://api.vercel.com/v6/deployments. Triggers: a deploy succeeds or fails; a preview builds. Actions: read deployment status; summarise build failures.
- [AI agents for Netlify](https://agnt.gg/integrations/netlify): Sites and builds reporting into your workflows.
  via custom-api against https://api.netlify.com/api/v1/sites/*/deploys. Triggers: a build completes; a form submission arrives. Actions: read build status; process form submissions.
- [AI agents for Sentry](https://agnt.gg/integrations/sentry): Errors that deserve summaries, not just alerts.
  via custom-api against https://sentry.io/api/0/projects/*/*/issues/. Triggers: a new issue appears; an error spikes. Actions: read and group issues; summarise error trends; file tickets.
- [AI agents for Firecrawl](https://agnt.gg/integrations/firecrawl): Clean page extraction for research-grade scraping.
  first-party node: firecrawl-api. Triggers: a scheduled crawl runs. Actions: scrape pages to clean text; crawl site sections; extract structured fields.
- [AI agents for Unsplash](https://agnt.gg/integrations/unsplash): Licensed imagery for generated content.
  first-party node: unsplash-api. Triggers: . Actions: search and fetch images; attach imagery to drafts.
- [AI agents for Weights & Biases](https://agnt.gg/integrations/wandb): Experiment tracking your reports can read.
  via custom-api against https://api.wandb.ai/graphql. Triggers: a run completes; a metric crosses a threshold. Actions: read runs and metrics; summarise experiments.
- [AI agents for Zapier](https://agnt.gg/integrations/zapier): Keep your Zaps — give them a reasoning layer.
  first-party node: zapier-action, zapier-trigger. Triggers: a Zap forwards an event. Actions: receive from and trigger Zaps.
- [AI agents for NVIDIA](https://agnt.gg/integrations/nvidia): NIM endpoints and GPU-served models in your workflows.
  via custom-api against https://integrate.api.nvidia.com/v1/chat/completions. Triggers: . Actions: call NIM model endpoints; run GPU-served inference.

## Use cases

A job somebody actually needs doing, and the agent that does it.

- [Email triage, done before you open the inbox](https://agnt.gg/marketplace/email-triage): An AGNT agent reads incoming mail, classifies it, drafts replies for the routine cases, and escalates the ones that genuinely need you — all under rules you write.
  Every inbox eventually accumulates a stack of filters, and every stack has the same problem: it matches on surface features. A rule keyed to "invoice" misses the customer who writes about "the charge on my card", and catches the newsletter that mentions invoicing software. An agent classifies on meaning, which is why it handles the long tail that filters were never going to reach. Tools: gmail, slack, notion.
- [Customer support that answers from your own docs](https://agnt.gg/marketplace/customer-support): Agents resolve the questions your docs already answer and hand the rest to your team with full context — history, account state, and a suggested reply.
  Optimising purely for tickets closed without a human produces a support experience everybody recognises and nobody likes: a system that works hard to avoid connecting you to someone. The better target is time-to-correct-answer. Some of that is deflection on questions the docs genuinely answer; the rest is making escalation fast and well-informed instead of a restart from zero. Tools: gmail, slack, discord, notion.
- [A first pass on every pull request](https://agnt.gg/marketplace/code-review): An agent reviews diffs against your standards — bugs, security, style, missing tests — and leaves structured comments before a human ever looks.
  The purpose is not to replace the reviewer — it is to make sure the reviewer’s attention is spent on design rather than on catching a missing null check for the fortieth time. When mechanical issues are already flagged, human review shifts to the questions only a human can answer: is this the right abstraction, does it fit where we are going, is the complexity justified. Tools: github, slack.
- [Research briefings, sourced and cited](https://agnt.gg/marketplace/research-briefings): Point an agent at a question; get back a sourced briefing — market landscape, technical comparison, diligence pass — with every claim linked.
  A list of ten links is the beginning of the work. Research is reading them, noticing that three are reprints of one press release, finding that the fourth contradicts the others, and forming a view about which to believe. That synthesis step is what takes an afternoon, and it is the part an agent can genuinely take on — provided it shows the work rather than asserting a conclusion. Tools: firecrawl, notion, googledrive, slack, obsidian.
- [Competitor monitoring that reports what changed](https://agnt.gg/marketplace/competitor-monitoring): Agents watch competitor sites, changelogs, pricing pages and news — and brief you on what actually changed, with links to the evidence.
  Any single competitor change is mildly interesting. What is genuinely useful is the sequence: three enterprise-flavoured features shipped, two enterprise sales roles posted, an enterprise tier added to pricing. No individual alert says "they are moving upmarket"; the accumulation does. Because the agent keeps the history and reads across it, it can name the pattern rather than reporting the third event in isolation. Tools: firecrawl, slack, notion, googlesheets, x.
- [Content production, from idea to published](https://agnt.gg/marketplace/content-pipeline): Run research, drafting, review and publishing as one workflow: agents do the legwork, humans hold the gates that matter.
  Asking a model for a finished article produces something plausible and unusable, because writing is not one task. Research, outline, draft, edit against a standard, adapt per channel — each is a separate step with its own inputs and its own failure modes. Modelling them as separate steps means you can put a human gate exactly where taste is required and automate the rest honestly. Tools: notion, googledrive, x, youtube, unsplash.
- [Social posts written native to each platform](https://agnt.gg/marketplace/social-media-automation): Turn published work into platform-native posts, schedule them, and collect the engagement numbers back into one report.
  The same text pushed to four platforms is optimised for none of them. A thread needs a first line that earns the second; a short post needs the whole idea to land at once; a professional network rewards a different register entirely. Adapting properly is genuinely a rewrite each time, which is exactly why it stops happening in a busy week — and exactly the kind of work worth handing to an agent. Tools: x, youtube, notion, googlesheets, unsplash.
- [Release notes written from what actually merged](https://agnt.gg/marketplace/write-release-notes): An agent reads every pull request merged since your last release and writes the notes your team needs — what changed, what to watch, and what needs a migration.
  A commit message is written for the next person reading that diff, at the moment of committing — “fix flaky test”, “address review”, “wip”. Release notes are written for someone who never saw the diff and wants to know whether to upgrade. Stitching one into the other is why release notes end up as either a raw git log or a chore somebody does late on a Friday. The pull request is the better unit: it has a title someone thought about, a description, labels and a linked issue, and it maps to one change a reader can understand. Tools: github, notion, slack.
- [Dependency advisories, sorted by what touches you](https://agnt.gg/marketplace/monitor-dependency-advisories): An agent reads the security updates Dependabot or Renovate opens, searches your code for the affected package, and tells you which advisories actually reach code you run.
  A critical rating means the flaw is serious for somebody using the vulnerable code path. Whether that somebody is you depends on whether you call that function, whether the package ships in production, and whether untrusted input ever reaches it. The score cannot know any of that; a search of your own repository can begin to. That is the gap the agent fills — not by second-guessing the advisory, but by putting your code next to it. Tools: github, slack.
- [Where is this handled? Answered with file paths](https://agnt.gg/marketplace/answer-codebase-questions): Ask how something works in your repository and get an answer that points at the files, functions and call sites involved — read from the code, not remembered.
  A new engineer rarely struggles to understand a function once they are looking at it. What costs the time is finding it: which of four similar modules is live, which config file actually wins, where the handler is registered. That knowledge lives in people’s heads and leaks out one chat question at a time. An agent that searches and reads the repository on demand makes the codebase answer for itself, and leaves the senior people free for the questions that genuinely need judgement. Tools: github.
- [Pull request descriptions a reviewer can start from](https://agnt.gg/marketplace/draft-pr-descriptions): An agent reads the diff, the commits and the linked issue, and writes the description your reviewer needs — what changed, why, how to test it and where to look hardest.
  The author has spent days inside a change and the reviewer has spent none. A good description closes that gap in two minutes: the problem, the approach, the alternatives rejected, and the places where the author is least sure. Without it the reviewer reverse-engineers intent from the diff, which is slow and is exactly where review comments about the wrong thing come from. The agent writes that orientation from material that already exists but that nobody assembled. Tools: github.
- [A changelog kept current, one pull request at a time](https://agnt.gg/marketplace/maintain-changelog): An agent adds an entry for every merged pull request to your changelog under Unreleased, proposes it as a pull request, and rolls it into a version when you cut a release.
  Someone deciding whether to move from 3.2 to 3.4 reads the changelog, not your commit history. They want to know what was removed, what behaves differently and what they must do. A changelog assembled in a hurry from git log tends to answer the question of what engineers did, which is the wrong question. Writing each entry from the pull request, at the time it merges, keeps the focus on what changed for the reader. Tools: github, notion.

## Solutions by team

The same product framed for the function that buys it.

- [AGNT for sales teams](https://agnt.gg/solutions/sales): Every lead enriched, every meeting logged, every follow-up drafted — the CRM keeps itself current while reps talk to buyers.
  Ask any sales team where the week goes and the answer is not selling. It is research before calls, notes after calls, CRM updates, follow-up drafting and chasing internal answers. None of that requires the specific talent you hired for, and all of it is exactly the shape of work an agent handles well: frequent, describable, and judgment-light once the context is assembled. Use cases: email-triage, research-briefings, competitor-monitoring, customer-support.
- [AGNT for marketing teams](https://agnt.gg/solutions/marketing): Research, drafting, repurposing and reporting — agents take the production work while your team keeps strategy and taste.
  Most marketing teams have a backlog of things worth making and no room to make them. The bottleneck is production: the research, the first draft, the four channel variants, the reporting pass. Handing that to agents does not make the team less creative — it moves their hours from assembly to the parts that require taste and judgment, which is where the returns actually are. Use cases: content-pipeline, competitor-monitoring, social-media-automation, research-briefings.
- [AGNT for engineering teams](https://agnt.gg/solutions/engineering): PR triage, release notes, incident summaries, dependency watch — agents handle the process work that surrounds shipping.
  Engineering time disappears into process: triaging issues, chasing reproduction steps, writing release notes, summarising incidents, checking dependency advisories. It is genuinely necessary and it is nobody’s reason for being an engineer. It is also unusually well suited to agents, because the inputs are structured, the systems have good APIs, and the judgment required is real but bounded. Use cases: code-review, write-release-notes, monitor-dependency-advisories, answer-codebase-questions.
- [AGNT for operations teams](https://agnt.gg/solutions/operations): Data entry, reconciliation, vendor tracking, recurring reports — turned into verified workflows with receipts on every run.
  Every process that was too variable for a rules engine and too frequent to ignore ended up here, absorbed by people with spreadsheets. That is precisely the profile agents change: work that needs reading and judgment on each item, but the same kind of judgment every time. Most operations backlogs contain several processes that were only manual because the previous generation of automation could not read. Use cases: email-triage, customer-support, research-briefings, competitor-monitoring.
- [AGNT for support teams](https://agnt.gg/solutions/support): Docs-grounded answers for the repetitive tickets, rich escalation for the hard ones, and a knowledge base that learns from resolutions.
  Optimising for tickets closed without a human produces the support experience everyone has suffered: a system working hard to avoid connecting you to a person. The metric worth moving is how long it takes a customer to get a correct answer. Some of that is genuine deflection on documented questions; much of it is making escalation fast and well-informed. Use cases: customer-support, email-triage, write-release-notes, research-briefings.
- [AGNT for finance teams](https://agnt.gg/solutions/finance): Invoice processing, expense review, variance reporting — agents do the collection and matching, humans approve what posts.
  Most of the close is gathering: pulling figures from several systems, chasing the ones that are late, matching things that should match and investigating the ones that do not. Very little of it requires an accountant’s judgment, and the part that does gets squeezed into the final day because the collection consumed the rest. Automating collection buys back exactly the time the judgment needed. Use cases: email-triage, research-briefings, competitor-monitoring, customer-support.
- [AGNT for agencies](https://agnt.gg/solutions/agencies): Client reporting, research, content production and monitoring — productised as workflows you run for every client at once.
  Agency economics come down to hours per client against fee per client, and the hours are dominated by production work that is nearly identical between accounts: reporting, monitoring, research, first drafts. Productising that work as a workflow you run per client is the difference between growth that requires hiring and growth that requires configuration. Use cases: social-media-automation, competitor-monitoring, content-pipeline, research-briefings.
- [AGNT for founders](https://agnt.gg/solutions/founders): One person with AGNT covers research, outreach drafts, support and reporting — the operational load that usually eats the week.
  Early-stage work fails on context-switching more than on capacity. Twenty minutes of lead research here, an hour of support there, the weekly numbers on Sunday — each is small and together they fragment the day so completely that nothing hard gets thought about. Handing the recurring pieces to agents is less about saving hours than about protecting contiguous attention. Use cases: email-triage, research-briefings, competitor-monitoring, answer-codebase-questions.

## Model providers

Which model to point at which step, and why the choice is per-step rather than per-product.

- [OpenAI with AGNT](https://agnt.gg/providers/openai): GPT-class models for general reasoning, tool use and code.
  Models: GPT-5.2, GPT-5 mini, o-series reasoning. Strengths: strongest ecosystem and tool-calling conventions; reliable structured output; broad task competence.
- [Anthropic with AGNT](https://agnt.gg/providers/anthropic): Claude models — long context, careful reasoning, strong code.
  Models: Claude Opus, Claude Sonnet, Claude Haiku. Strengths: long-document work; nuanced instruction following; agentic coding.
- [Google Gemini with AGNT](https://agnt.gg/providers/gemini): Google’s multimodal family with massive context windows.
  Models: Gemini 3 Pro, Gemini 3 Flash. Strengths: multimodal input; very large context; fast flash tier for volume work.
- [xAI Grok with AGNT](https://agnt.gg/providers/grok): xAI’s models with real-time X data affinity.
  Models: Grok 4.1, Grok 4.1 Fast. Strengths: current-events awareness; fast reasoning tier; competitive pricing.
- [Meta Llama with AGNT](https://agnt.gg/providers/meta): The open-weight family the local ecosystem is built on.
  Models: Llama 4 herd, Llama 3.3. Strengths: run anywhere, including fully local; huge fine-tune ecosystem; no vendor lock-in.
- [Mistral with AGNT](https://agnt.gg/providers/mistral): European frontier lab with strong small models.
  Models: Mistral Large, Mistral Small, Codestral. Strengths: efficient small models; strong code variants; EU data residency options.
- [DeepSeek with AGNT](https://agnt.gg/providers/deepseek): Frontier-quality reasoning at disruptive cost.
  Models: DeepSeek-V3, DeepSeek-R1. Strengths: exceptional price-performance; open reasoning traces; strong math and code.
- [Qwen with AGNT](https://agnt.gg/providers/qwen): Alibaba’s open family — dense to massive MoE.
  Models: Qwen3 family, Qwen3-Coder. Strengths: broad size range for any hardware; multilingual strength; permissive licensing.
- [Kimi with AGNT](https://agnt.gg/providers/kimi): Moonshot’s long-context agentic models.
  Models: Kimi K2. Strengths: agentic tool use; long context; aggressive pricing.
- [MiniMax with AGNT](https://agnt.gg/providers/minimax): Efficient frontier models with huge context.
  Models: MiniMax-M2. Strengths: million-token context; strong coding; cost-efficient serving.
- [Z.ai with AGNT](https://agnt.gg/providers/zai): GLM models tuned for agentic work.
  Models: GLM-4.7. Strengths: tool-calling reliability; open weights available; competitive pricing.
- [Cohere with AGNT](https://agnt.gg/providers/cohere): Enterprise-focused models with first-class RAG.
  Models: Command R+, Embed, Rerank. Strengths: retrieval-optimised stack; enterprise deployment options; strong embeddings.
- [Groq with AGNT](https://agnt.gg/providers/groq): LPU-served open models at extreme speed.
  Models: Llama on LPU, open-weight menu. Strengths: lowest latency serving; high throughput for agent loops; simple flat pricing.
- [Cerebras with AGNT](https://agnt.gg/providers/cerebras): Wafer-scale inference for open models.
  Models: Llama and Qwen at speed. Strengths: thousands of tokens/sec; great for iterative agents; generous free tier.
- [Together AI with AGNT](https://agnt.gg/providers/together): One API over the open-weight universe.
  Models: 200+ open models. Strengths: model breadth; fine-tuning platform; dedicated endpoints.
- [OpenRouter with AGNT](https://agnt.gg/providers/openrouter): Every major model behind one key.
  Models: all major providers, routed. Strengths: one key, every model; automatic fallbacks; transparent pricing.
- [Replicate with AGNT](https://agnt.gg/providers/replicate): Run community models — vision, audio, image — by API.
  Models: thousands of hosted models. Strengths: long-tail model access; image and audio generation; pay-per-run.
- [Hugging Face with AGNT](https://agnt.gg/providers/huggingface): The hub — inference endpoints over the open ecosystem.
  Models: hub-hosted checkpoints. Strengths: direct hub access; serverless inference; the widest model catalogue.
- [Perplexity with AGNT](https://agnt.gg/providers/perplexity): Answer models with live web grounding built in.
  Models: Sonar family. Strengths: citations by default; live web knowledge; research-agent fit.
- [Ollama with AGNT](https://agnt.gg/providers/ollama): One command to run open models on your own machine.
  Models: Llama, Qwen, Mistral, Gemma locally. Strengths: zero cloud dependency; total data privacy; free unlimited runs.
- [LM Studio with AGNT](https://agnt.gg/providers/lmstudio): A desktop app for local models with an OpenAI-style server.
  Models: any GGUF checkpoint. Strengths: GUI model management; drop-in local endpoint; works offline.
- [ElevenLabs with AGNT](https://agnt.gg/providers/elevenlabs): Production text-to-speech for agents that talk.
  Models: Multilingual v3, Flash. Strengths: most natural TTS; voice cloning; realtime streaming.

## Definitions

Plain definitions of the vocabulary, for when a term needs to be quoted exactly.

- [AI agent](https://agnt.gg/glossary/ai-agent): An AI system that pursues a goal by taking actions — calling tools, reading data, making decisions — rather than only generating text. Where a chatbot answers, an agent does: it plans steps, executes them against real systems, observes results and adjusts.
  In AGNT, agents hold real jobs with assigned tools, persistent memory and receipts for every action.
- [Agentic workflow](https://agnt.gg/glossary/agentic-workflow): A workflow where one or more steps are performed by a reasoning agent instead of fixed logic. Traditional automation branches on rules written in advance; an agentic workflow can read, judge and decide at the points where rules run out.
  AGNT’s canvas mixes deterministic nodes with agent steps, so the routine stays cheap and the judgment calls get a mind.
- [Autonomous agent](https://agnt.gg/glossary/autonomous-agent): An agent that operates without step-by-step supervision: given an objective, it plans, acts, evaluates its own results and continues until done or blocked. Autonomy is a spectrum — most production systems bound it with approval gates and budgets.
  AGNT goals run autonomous loops with iteration caps, spend limits and human gates exactly where you place them.
- [Multi-agent system](https://agnt.gg/glossary/multi-agent-system): Multiple agents cooperating on work too broad for one — a researcher feeding a writer feeding a reviewer, or specialists coordinated by an orchestrator. The hard problems are hand-off quality and shared state.
  AGNT runs multi-agent setups with shared memory and per-agent toolkits, coordinated on one canvas.
- [Agent orchestration](https://agnt.gg/glossary/agent-orchestration): Coordinating which agent or tool acts, in what order, with what context — routing tasks, merging results, retrying failures and enforcing gates. Orchestration turns capable-but-isolated models into a system.
  The AGNT orchestrator routes work across agents, workflows and tools while keeping every step attributable.
- [Agent memory](https://agnt.gg/glossary/agent-memory): Persistent state an agent carries across sessions: facts about its user, corrections received, patterns that worked. Without it every run starts from zero; with it the tenth run outperforms the first.
  AGNT stores typed memories — facts, preferences, corrections, insights — locally, and retrieves them when relevant.
- [Agent skills](https://agnt.gg/glossary/agent-skills): Packaged, versioned expertise an agent loads on demand — a playbook containing process, standards and examples for one class of task. Skills make competence reusable and reviewable instead of trapped in prompts.
  AGNT skills are files you can diff, share and install from the marketplace; agents activate them when the task matches.
- [MCP (Model Context Protocol)](https://agnt.gg/glossary/mcp): An open protocol for connecting AI models to tools and data sources through a standard interface. Instead of custom integrations per model per tool, MCP servers expose capabilities any compliant client can use.
  AGNT speaks MCP natively — plug MCP servers in as tool sources alongside built-in nodes.
- [MCP server](https://agnt.gg/glossary/mcp-server): A process exposing tools, resources or prompts over the Model Context Protocol. One well-built server — for a database, an API, a filesystem — becomes usable by every MCP-capable client without further glue.
  Connect MCP servers to AGNT and their tools appear in agent toolkits like any native node.
- [Tool calling](https://agnt.gg/glossary/tool-calling): A model invoking external functions — search, database queries, file writes — by emitting structured calls its runtime executes. Tool calling is what turns language models from advisors into actors.
  Every AGNT tool call is executed by the runtime, logged, and shown in the run’s receipt.
- [Function calling](https://agnt.gg/glossary/function-calling): The model-side mechanism behind tool use: the model returns a structured invocation — name plus JSON arguments — matching a declared schema, which the host executes and feeds back.
  AGNT normalises function calling across providers, so the same workflow runs on GPT, Claude, Gemini or a local model.
- [LLM runtime](https://agnt.gg/glossary/llm-runtime): The environment that turns model output into real work: executing tool calls, managing context and memory, enforcing permissions, retrying failures, recording what happened. Models reason; runtimes act.
  AGNT is a local-first LLM runtime — the layer where agents, tools, memory and receipts actually live.
- [Local-first AI](https://agnt.gg/glossary/local-first-ai): AI software whose data, credentials and execution live on hardware you control, with cloud as an option rather than a requirement. Privacy, cost and ownership follow from that architectural choice.
  AGNT Community Core runs entirely on your machine — keys, memory and history included — free.
- [Self-hosted AI](https://agnt.gg/glossary/self-hosted-ai): Running AI infrastructure — runtimes, models, or both — on your own servers. Teams self-host for data control, compliance, predictable cost and independence from vendor availability.
  AGNT ships Docker images for headless self-hosting; pair with Ollama and the entire stack is yours.
- [Prompt caching](https://agnt.gg/glossary/prompt-caching): Reusing computation for the repeated prefix of prompts — system instructions, tool schemas, standing context — so consecutive calls pay only for what changed. For agent loops sharing a large stable prefix, cost and latency can drop dramatically.
  AGNT’s cache-efficiency research measured exactly this across agent harnesses — see The Cache Wars whitepaper.
- [RAG (Retrieval-Augmented Generation)](https://agnt.gg/glossary/rag): Fetching relevant documents at query time and placing them in the model’s context, so answers ground in your data instead of training memory. The retrieval layer determines most of the quality.
  AGNT workflows compose retrieval steps — files, databases, web — ahead of generation, with sources kept for the receipt.
- [Context window](https://agnt.gg/glossary/context-window): The maximum text a model attends to in one call — instructions, history, retrieved material and its own output. Managing what earns a place in that window is a core engineering discipline of agent systems.
  AGNT manages context per step: skills load on demand and memory retrieves selectively, keeping windows lean.
- [Fine-tuning](https://agnt.gg/glossary/fine-tuning): Continuing a model’s training on domain examples to shift behaviour — terminology, format, tone — into the weights. Powerful when in-context approaches plateau, at the price of maintenance per model version.
  Most AGNT teams get further with skills and memory first; fine-tuned checkpoints plug in via local or hosted providers when justified.
- [Inference](https://agnt.gg/glossary/inference): Running a trained model to produce output — the operational, per-request phase of AI, as opposed to training. Latency, throughput and cost per token are its economics.
  AGNT points inference anywhere: frontier APIs, fast-inference clouds, or fully local through Ollama.
- [Token](https://agnt.gg/glossary/token): The unit models read and write — roughly three-quarters of an English word. Context limits and API pricing are both denominated in tokens, which makes token discipline cost discipline.
  AGNT meters usage per run, so a workflow’s token economics are visible instead of a surprise invoice.
- [System prompt](https://agnt.gg/glossary/system-prompt): The standing instruction that defines a model’s role, rules and boundaries before any user input arrives. In agent systems it carries identity, tool policy and safety rails — and deserves version control.
  AGNT agents keep system prompts as editable, versioned configuration — not text lost in a chat box.
- [Webhook automation](https://agnt.gg/glossary/webhook-automation): Triggering workflows from HTTP callbacks the moment events happen — a payment, a form, a commit — instead of polling on a schedule. Webhooks are the event backbone of most integration work.
  AGNT workflows expose webhook triggers, so any system that can POST can start verified agent work.
- [Human-in-the-loop](https://agnt.gg/glossary/human-in-the-loop): Automation that pauses for human judgment at defined points — approving an outbound email, releasing a payment, accepting a diff. The design question is which decisions warrant a human, not whether automation is safe.
  AGNT approval gates park a run mid-flight until a person signs off, with the full context attached.
- [Execution receipt](https://agnt.gg/glossary/execution-receipt): A structured record an agent produces for each operation: what was read, which tools ran with what arguments, what was decided and what was written. Receipts make AI work reviewable and attributable after the fact.
  Receipts are AGNT’s core primitive — every run explains itself, which is what makes delegation safe.
- [What is an AI agent?](https://agnt.gg/what-is/an-ai-agent): An AI agent is software that pursues a goal by acting — not just answering. Give it an objective and it plans steps, calls tools, reads results and keeps going until the job is done or a human gate stops it.
  A chatbot’s output is text you act on. An agent’s output is the acted-upon result: the report filed, the ticket created, the inbox triaged. The model is the same species; the difference is a runtime that lets it use tools, hold memory and be held to account.
- [What is agentic automation?](https://agnt.gg/what-is/agentic-automation): Agentic automation puts reasoning inside your workflows. Classic automation executes rules you wrote in advance; agentic automation adds steps that can read, judge and decide when the rules run out.
  Rule chains break on the first input nobody predicted. An agent step handles the unpredicted case the way a person would — read it, weigh it, act — while everything routine still runs as cheap deterministic nodes.
- [What is an agent runtime?](https://agnt.gg/what-is/an-agent-runtime): An agent runtime is the environment where agents actually live: it executes their tool calls, manages memory and context, enforces permissions, and records what happened. Models think; runtimes act.
  An LLM emits text — including text that says "call this tool". Something must execute that call, handle the failure, retry, log it and feed the result back. That something is the runtime, and its quality decides whether agents are reliable.
- [What is MCP?](https://agnt.gg/what-is/mcp): The Model Context Protocol (MCP) is an open standard for connecting AI models to tools and data. One MCP server — for a database, an API, a filesystem — becomes usable by any compliant client, ending the era of custom glue per model per tool.
  Before MCP, every model-tool pairing needed bespoke integration. With it, tool builders expose one server and model clients speak one protocol — the integration matrix collapses to N+M.
- [What is local-first software?](https://agnt.gg/what-is/local-first-software): Local-first software keeps your data and computation on devices you control, treating the cloud as an optional accessory rather than the landlord. You own the files; sync and scale are choices.
  Whether you control your data is decided by where the software runs, not by a privacy policy. Local-first puts the primary copy — and for AI, the keys and memory — on your machine by construction.
- [What is a workflow engine?](https://agnt.gg/what-is/a-workflow-engine): A workflow engine executes multi-step processes reliably: triggers start runs, steps execute in order or in parallel, failures retry, and state survives restarts. It is the machinery under serious automation.
  A script runs once and dies with its terminal. A workflow engine gives the same logic triggers, retries, logging, and a place to live — the difference between an experiment and an operation.
- [What is an AI operating system?](https://agnt.gg/what-is/an-ai-operating-system): An AI operating system is the layer that turns models into a working environment: agents as processes, tools as devices, memory as the filesystem, and receipts as the audit log. It is where AI work runs, not just where it is imagined.
  Operating systems exist to schedule work, mediate access to resources, and keep processes from trampling each other. Swap processes for agents and devices for tools and the job description transfers exactly.
- [What is agent verification?](https://agnt.gg/what-is/agent-verification): Agent verification is proving what an AI agent actually did: which sources it read, which tools it invoked, what it decided and what it changed. Without verification, delegation to agents is faith; with it, it is management.
  A verification-first runtime emits a structured receipt per operation — inputs, tool calls with arguments, outputs, approvals. Review shifts from "do we trust the model?" to "check the record", which is a solvable problem.