Back to directory

TAKT

An open-source CLI that turns AI coding agents into repeatable YAML-defined workflows, giving each step of planning, implementation, review, and fix loops its own role, permissions, and human checkpoints.

TAKT

TAKT (Agent Koordination Topology) is an open-source CLI that turns AI coding agents into repeatable development workflows instead of asking one agent to remember an entire process. Planning, implementation, review, fix loops, human checkpoints, permissions, and output contracts are defined in YAML, and each workflow step gets its own persona, policy, knowledge, instructions, and output contract rather than leaving the process to the agent's discretion.

A task defined through conversation is queued and run with takt run, executing in isolated worktrees and producing traceable logs and reports that can be inspected afterward. TAKT can coordinate Claude Code, the Claude SDK, Codex SDK, OpenCode SDK, Pi SDK, the DeepSeek Harness SDK, Cursor, GitHub Copilot CLI, or Kiro as providers, each with different roles, permissions, and context, and the same coordination model applies to any multi-step task with review and feedback loops, not only coding.

TAKT is itself built using TAKT. It is written in TypeScript and MIT licensed.

More in Coding agents

See all 793
  • The City

    github.com

    A native macOS app that shows Claude Code runs as a city, with each project as a building, each team as a floor of robots, and every animation driven by a real event from the claude CLI's stream.

  • rig

    tryrig.ai

    A small, single-binary agent runtime that points at any OpenAI-compatible model, local or hosted, reads and edits a repository's code, runs its tests and remembers what it learned, with a loop implemented in a few hundred lines.

  • Jauvex

    jauvex.reindent.com

    An Electron desktop app that puts Claude Code, Codex and Grok coding-agent sessions side by side and lets you steer them by voice, with a small model handling fast routing decisions.