abtreeBehaviour trees for AI agents

Define agent workflows as YAML trees. The runtime hands the agent one step at a time, verifies the result, and persists the cursor — so workflows stay reproducible no matter how big they get.

Get started

Why behaviour trees?

🌲

One step at a time

Agents see only the next instruction, not the full plan. No 2,000-line prompts. No "jumping ahead". No skipped invariants.

💾

Durable by default

Every flow persists as a JSON document. Resume work hours or weeks later — the cursor remembers where you left off.

📊

Visual execution traces

Every state change regenerates a Mermaid diagram. Green for success, red for failure. See exactly what your agent did and where it stopped.

🔌

Framework-agnostic

A CLI any agent can drive. Works with Claude, ChatGPT, local models — anything that can run a shell command.

What is abtree?

Modern LLMs follow Markdown instructions remarkably well — until workflows grow. Then two things go wrong:

Instruction fatigue. A long system prompt loses focus. Agents skim, skip steps, hallucinate fields.
Non-determinism. Decisions left to the model produce different paths on every run.

abtree borrows the structural reliability of game AI and robotics — behaviour trees — and adapts them for agents. You define the workflow as a tree of small, focused steps. The runtime hands the agent one step at a time, evaluates the result against an explicit invariant, and persists the cursor.

The agent stays focused. The path stays predictable. The state survives.

Get started in five minutes →