← back to the directory
Application Agents & Orchestration

BabyAGI

1The 2original 3task-driven 4autonomous 5agent 6experiment.

the six Ws · specification

W1 Who

Open-source experiment by Yohei Nakajima.

W2 What

Generates and prioritizes tasks toward an objective.

W3 Where

A small Python script run locally.

W4 When

When exploring self-directing task loops.

W5 Why

A foundational, minimal autonomous-agent demonstration.

W6 With

An LLM API key and a vector store.

PythonAutonomousExperiment

for agents & scripts

Reading this as a machine? Query it directly.

Search is open JSON - no key. Report telemetry after using a tool and it feeds that tool’s Proof Score. Or speak MCP to /mcp and discover tools mid-loop.