HomeProduct › Agents
Reasoning Layer

AI agents with memory and tools.

A chat session forgets everything the moment you close it. An AGNT agent is a persistent worker — it has its own memory, its own tool permissions, its own model, and a record of everything it has done before.

Download free Agent docs
What an Agent Is

Configuration, not conversation

Every agent is a stored, versioned object. You define what it can touch and what it costs, and that definition persists across sessions, restarts, and machines.

01 / IDENTITY

Scope and purpose

Name, description, icon, and category. An agent is built for a job — a research agent, a release agent, a support triage agent — not as a general chat window.

02 / CAPABILITY

Assigned tools

You grant an explicit tool set and workflow set. An agent cannot reach for something it was never given, which makes its blast radius a design decision rather than a surprise.

03 / BUDGET

Credit limits

Each agent carries a credit ceiling and tracks consumption against it. Autonomous work cannot quietly run up an unbounded bill.

Persistent Memory

Agents that compound instead of resetting

Memory is typed, not a single undifferentiated blob. The type determines how a memory is retrieved and how heavily it is weighted — so a correction you made once does not get lost among a hundred trivia facts.

Memory typeWhat it captures
factStable truths about you, your stack, or your business
preferenceHow you like things done — style, format, tone, defaults
correctionSomething the agent got wrong and you fixed, so it does not recur
contextBackground on a project, codebase, or ongoing situation
patternAn approach that worked and is worth repeating
tool_insightHard-won knowledge about a specific tool's quirks and failure modes
workflow_insightOptimizations discovered while running a workflow
prompt_guidancePrompt phrasing that reliably produces better results

Memory is stored locally alongside your execution history. It is yours, it is inspectable, and it never gets shipped to a vendor for training.

Accountability

Every run leaves evidence

Full execution traces

An agent run is not a black box. Each execution records what was asked, what was answered, and every tool call in between.

  • The exact prompt that started the run
  • Every tool call with its input, output, and any error
  • Timestamps, token usage, and cost per step
  • The final response, stored verbatim

Searchable history

Traces are indexed, so "what did we do about that bug last week" is a query rather than an archaeology project.

  • Full-text search across every past run
  • Success rate tracked per agent over time
  • Reconstruct any run step by step, months later
  • Receipts stored locally in SQLite, not in a vendor's cloud