TAKT

🇯🇵 日本語ドキュメント

Task Agent Koordination Tool - Define how AI agents coordinate, where humans intervene, and what gets recorded — in YAML

TAKT runs multiple AI agents (Claude Code, Codex) through YAML-defined workflows. Each step — who runs, what's allowed, what happens on failure — is declared in a piece file, not left to the agent.

TAKT is built with TAKT itself (dogfooding).

Metaphor

TAKT uses a music metaphor to describe orchestration:

• Piece: A task execution definition (what to do and how agents coordinate)
• Movement: A step inside a piece (a single stage in the flow)
• Orchestration: The engine that coordinates agents across movements

You can read every term as standard workflow language (piece = workflow, movement = step), but the metaphor is used to keep the system conceptually consistent.

Why TAKT

• AI agents are powerful but non-deterministic — TAKT makes their decisions visible and replayable
• Multi-agent coordination needs structure — pieces define who does what, in what order, with what permissions
• CI/CD integration needs guardrails — pipeline mode runs agents non-interactively with full audit logs

What TAKT is NOT

• Not an autonomous engineer — TAKT coordinates agents but doesn't decide what to build. You provide the task, TAKT governs the execution.
• Not a Skill or Swarm replacement — Skills extend a single agent's knowledge. Swarm parallelizes agents. TAKT defines the workflow structure across agents — which agent runs, in what order, with what rules.