[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-75041":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":25,"hasPages":23,"topics":26,"createdAt":10,"pushedAt":10,"updatedAt":34,"readmeContent":35,"aiSummary":36,"trendingCount":16,"starSnapshotCount":16,"syncStatus":37,"lastSyncTime":38,"discoverSource":39},75041,"takt","nrslib\u002Ftakt","nrslib","TAKT Agent Koordination Topology - Define how AI agents coordinate, where humans intervene, and what gets recorded — in YAML","",null,"TypeScript",1122,70,3,34,0,8,18,97,24,88.25,"MIT License",false,"main",true,[27,28,29,30,31,32,33],"agent-orchestration","agent-team","ai-agents","claude-code","codex","multi-agent","opencode","2026-06-12 04:01:17","# TAKT\n\n🇯🇵 [日本語ドキュメント](.\u002Fdocs\u002FREADME.ja.md) | 💬 [Discord Community](https:\u002F\u002Fdiscord.gg\u002FR2Xz3uYWxD)\n\n**T**AKT **A**gent **K**oordination **T**opology — Give your AI coding agents structured review loops, managed prompts, and guardrails — so they deliver quality code, not just code.\n\nTAKT runs AI agents (Claude Code, Codex, OpenCode, Cursor, GitHub Copilot CLI) through YAML-defined workflows with built-in review cycles. You talk to AI to define what you want, queue tasks, and let TAKT handle the execution — planning, implementation, multi-stage review, and fix loops — all governed by declarative workflow files.\n\nTAKT is built with TAKT itself (dogfooding).\n\n## Why TAKT\n\n**Batteries included** — Architecture, security, and AI antipattern review criteria are built in. Ship code that meets a quality bar from day one.\n\n**Practical** — A tool for daily development, not demos. Talk to AI to refine requirements, queue tasks, and run them. Worktree isolation on task execution, PR creation, and retry on failure.\n\n**Reproducible** — Execution paths are declared in YAML, keeping results consistent. Workflows are shareable — a workflow built by one team member can be used by anyone else to run the same quality process. Every step is logged in NDJSON for full traceability from task to PR.\n\n**Multi-agent** — Orchestrate multiple agents with different personas, permissions, and review criteria. Run parallel reviewers, route failures back to implementers, aggregate results with declarative rules. Prompts are managed as independent facets (persona, policy, knowledge, instruction) that compose freely across workflows ([Faceted Prompting](.\u002Fdocs\u002Ffaceted-prompting.md)).\n\n## Requirements\n\nThe provider you choose determines whether you need to install an external CLI or can run on Node.js alone via a TypeScript SDK.\n\nThese providers run via SDK (no CLI required, Node.js only):\n\n- `claude-sdk` — `@anthropic-ai\u002Fclaude-agent-sdk`\n- `codex` — `@openai\u002Fcodex-sdk`\n- `opencode` — `@opencode-ai\u002Fsdk`\n\nThese providers require an external CLI:\n\n- `claude` — [Claude Code](https:\u002F\u002Fclaude.ai\u002Fcode)\n- `copilot` — [GitHub Copilot CLI](https:\u002F\u002Fdocs.github.com\u002Fen\u002Fcopilot\u002Fgithub-copilot-in-the-cli)\n- `cursor` — [Cursor Agent](https:\u002F\u002Fdocs.cursor.com\u002F)\n\nOptional:\n\n- [GitHub CLI](https:\u002F\u002Fcli.github.com\u002F) (`gh`) — for `takt #N` (GitHub Issue tasks)\n- [GitLab CLI](https:\u002F\u002Fgitlab.com\u002Fgitlab-org\u002Fcli) (`glab`) — for GitLab Issue\u002FMR integration (auto-detected from remote URL)\n\n> **OAuth usage:** Whether OAuth is permitted varies by provider and use case. Check each provider's terms of service before using TAKT.\n\n## Quick Start\n\n### Install\n\n```bash\nnpm install -g takt\n```\n\n### Talk to AI and queue tasks\n\n```\n$ takt\n\nSelect workflow:\n  ❯ 🎼 default (current)\n    📁 🚀 Quick Start\u002F\n    📁 🎨 Frontend\u002F\n    📁 ⚙️ Backend\u002F\n\n> Add user authentication with JWT\n\n[AI clarifies requirements and organizes the task]\n\n> \u002Fgo\n\nProposed task:\n  ...\n\nWhat would you like to do?\n    Execute now\n    Create GitHub Issue\n  ❯ Queue as task          # ← normal flow\n    Continue conversation\n```\n\nChoosing \"Queue as task\" saves the task to `.takt\u002Ftasks\u002F`. Run `takt run` to execute — TAKT creates an isolated worktree, runs the workflow (plan → implement → review → fix loop), and offers to create a PR when done.\n\n```bash\n# Execute queued tasks\ntakt run\n\n# You can also queue from GitHub Issues\ntakt add #6\ntakt add #12\n\n# Execute all pending tasks\ntakt run\n```\n\n> **\"Execute now\"** runs the workflow directly in your current directory without worktree isolation. Useful for quick experiments, but note that changes go straight into your working tree.\n\n### Manage results\n\n```bash\n# List task branches — merge, retry, requeue, force-fail, or delete\ntakt list\n```\n\n## How It Works\n\nThe name TAKT comes from the German word for \"beat\" or \"baton stroke,\" used in conducting to keep an orchestra in time. TAKT uses **workflow** and **step** consistently in both user-facing and implementation-facing terminology.\n\nA workflow is defined by a sequence of steps. Use `steps`, `initial_step`, and `max_steps`. Each step specifies a persona (who), permissions (what's allowed), and rules (what happens next). Here's a minimal example:\n\n```yaml\nname: plan-implement-review\ninitial_step: plan\nmax_steps: 10\n\nsteps:\n  - name: plan\n    persona: planner\n    edit: false\n    rules:\n      - condition: Planning complete\n        next: implement\n\n  - name: implement\n    persona: coder\n    edit: true\n    required_permission_mode: edit\n    rules:\n      - condition: Implementation complete\n        next: review\n\n  - name: review\n    persona: reviewer\n    edit: false\n    rules:\n      - condition: Approved\n        next: COMPLETE\n      - condition: Needs fix\n        next: implement    # ← fix loop\n```\n\nRules determine the next step. `COMPLETE` ends the workflow successfully, `ABORT` ends with failure. See the [Workflow Guide](.\u002Fdocs\u002Fworkflows.md) for the full schema, parallel steps, and rule condition types.\n\nWorkflow files live in `workflows\u002F` as the official directory name.\n\nWhen the same workflow name exists in multiple locations, TAKT resolves in this order: `.takt\u002Fworkflows\u002F` → `~\u002F.takt\u002Fworkflows\u002F` → builtins.\n\n## Recommended Workflows\n\n| Workflow | Use Case |\n|-------|----------|\n| `default` | Standard development workflow. Test-first with AI antipattern review and parallel review (architecture + supervisor). |\n| `frontend` | Frontend development workflow. |\n| `backend` | Backend development workflow. |\n| `dual` | Combined frontend + backend workflow. |\n| `takt-default` | The workflow used to develop TAKT itself. Directly applicable to other CLI tool development. |\n| `*-mini` series | Lightweight variants of each workflow (`default-mini` \u002F `frontend-mini` \u002F `backend-mini` \u002F `dual-mini`). Omits `write_tests`. |\n\nSee the [Builtin Catalog](.\u002Fdocs\u002Fbuiltin-catalog.md) for all workflows and personas.\n\n## Key Commands\n\n| Command | Description |\n|---------|-------------|\n| `takt` | Talk to AI, refine requirements, execute or queue tasks |\n| `takt run` | Execute all pending tasks |\n| `takt list` | Manage task branches (merge, retry, requeue, force-fail, instruct, delete) |\n| `takt #N` | Execute GitHub Issue as task |\n| `takt eject` | Copy builtin workflows\u002Ffacets for customization |\n| `takt workflow init` | Create a new workflow scaffold |\n| `takt workflow doctor` | Validate workflow definitions |\n| `takt repertoire add` | Install a repertoire package from GitHub |\n\nSee the [CLI Reference](.\u002Fdocs\u002Fcli-reference.md) for all commands and options.\n\n## Configuration\n\nMinimal `~\u002F.takt\u002Fconfig.yaml`:\n\n```yaml\nprovider: claude    # claude, claude-sdk, codex, opencode, cursor, or copilot\nmodel: sonnet       # passed directly to provider\nlanguage: en        # en or ja\n```\n\nOr use API keys directly (no CLI installation required for Claude, Codex, OpenCode):\n\n```bash\nexport TAKT_ANTHROPIC_API_KEY=sk-ant-...   # Anthropic (Claude)\nexport TAKT_OPENAI_API_KEY=sk-...          # OpenAI (Codex)\nexport TAKT_OPENCODE_API_KEY=...           # OpenCode\nexport TAKT_CURSOR_API_KEY=...             # Cursor Agent (optional if logged in)\nexport TAKT_COPILOT_GITHUB_TOKEN=ghp_...   # GitHub Copilot CLI\n```\n\nSee the [Configuration Guide](.\u002Fdocs\u002Fconfiguration.md) for all options, provider profiles, and model resolution.\n\n## Customization\n\n### Custom workflows\n\n```bash\ntakt workflow init my-flow   # Create a new workflow scaffold\ntakt workflow doctor my-flow # Validate a workflow definition\ntakt eject default           # Copy builtin workflow to ~\u002F.takt\u002Fworkflows\u002F and edit\n```\n\n### Custom personas\n\nCreate a Markdown file in `~\u002F.takt\u002Fpersonas\u002F`:\n\n```markdown\n# ~\u002F.takt\u002Fpersonas\u002Fmy-reviewer.md\nYou are a code reviewer specialized in security.\n```\n\nReference it in your workflow: `persona: my-reviewer`\n\nSee the [Workflow Guide](.\u002Fdocs\u002Fworkflows.md) for details. The list of builtin personas is in the [Builtin Catalog](.\u002Fdocs\u002Fbuiltin-catalog.md).\n\n## CI\u002FCD\n\nTAKT provides [takt-action](https:\u002F\u002Fgithub.com\u002Fnrslib\u002Ftakt-action) for GitHub Actions:\n\n```yaml\n- uses: nrslib\u002Ftakt-action@main\n  with:\n    anthropic_api_key: ${{ secrets.TAKT_ANTHROPIC_API_KEY }}\n    github_token: ${{ secrets.GITHUB_TOKEN }}\n```\n\nFor other CI systems, use pipeline mode:\n\n```bash\ntakt --pipeline --task \"Fix the bug\" --auto-pr\n```\n\nSee the [CI\u002FCD Guide](.\u002Fdocs\u002Fci-cd.md) for full setup instructions.\n\n## Project Structure\n\n```\n~\u002F.takt\u002F                    # Global config\n├── config.yaml             # Provider, model, language, etc.\n├── workflows\u002F              # User workflow definitions\n├── facets\u002F                 # User facets (personas, policies, knowledge, etc.)\n└── repertoire\u002F             # Installed repertoire packages\n\n.takt\u002F                      # Project-level\n├── config.yaml             # Project config\n├── workflows\u002F              # Project workflow overrides\n├── facets\u002F                 # Project facets\n├── tasks.yaml              # Pending tasks\n├── tasks\u002F                  # Task specifications\n└── runs\u002F                   # Execution reports, logs, context\n```\n\nWorkflow definitions are stored under `workflows\u002F`.\n\n## Adopting Spec-Driven Development\n\nTAKT enforces phase transitions declaratively as a YAML state machine, formalizes the artifact of each phase with output contracts, and routes deviations back via parallel review and fix loops. This structure is particularly well-suited for users who follow Spec-Driven Development (SDD) and keep the spec at the center of the process. Once the spec is well-defined, the AI cannot silently skip a phase, drop an acceptance criterion, or claim \"done\" without passing the verification gate.\n\nFor users who want to adopt SDD, the community provides [j5ik2o\u002Ftakt-sdd](https:\u002F\u002Fgithub.com\u002Fj5ik2o\u002Ftakt-sdd) as a ready-made implementation. It ships pieces for Requirements → Gap Analysis → Design → Tasks → Implementation → Validation, plus an OpenSpec-style change-proposal flow. Install in one command:\n\n```bash\nnpx create-takt-sdd\n```\n\nSee [External Integrations](.\u002Fdocs\u002Fexternal-integrations.md) for other community integrations.\n\n## Documentation\n\n| Document | Description |\n|----------|-------------|\n| [CLI Reference](.\u002Fdocs\u002Fcli-reference.md) | All commands and options |\n| [Configuration](.\u002Fdocs\u002Fconfiguration.md) | Global and project settings |\n| [Workflow Guide](.\u002Fdocs\u002Fworkflows.md) | Creating and customizing workflows |\n| [Builtin Catalog](.\u002Fdocs\u002Fbuiltin-catalog.md) | All builtin workflows and personas |\n| [Faceted Prompting](.\u002Fdocs\u002Ffaceted-prompting.md) | Prompt design methodology |\n| [Repertoire Packages](.\u002Fdocs\u002Frepertoire.md) | Installing and sharing packages |\n| [Task Management](.\u002Fdocs\u002Ftask-management.md) | Task queuing, execution, isolation |\n| [CI\u002FCD Integration](.\u002Fdocs\u002Fci-cd.md) | GitHub Actions and pipeline mode |\n| [External Integrations](.\u002Fdocs\u002Fexternal-integrations.md) | Community examples that extend TAKT without modifying core (audit trails, etc.) |\n| [Changelog](.\u002FCHANGELOG.md) ([日本語](.\u002Fdocs\u002FCHANGELOG.ja.md)) | Version history |\n\n## Community\n\nJoin the [TAKT Discord](https:\u002F\u002Fdiscord.gg\u002FR2Xz3uYWxD) for questions, discussions, and updates.\n\n## Contributing\n\nSee [CONTRIBUTING.md](.\u002FCONTRIBUTING.md) for details.\n\n## License\n\nMIT — See [LICENSE](.\u002FLICENSE) for details.\n","TAKT 是一个用于定义AI代理如何协调、人类何时介入以及记录哪些内容的工具，使用YAML进行配置。它通过预定义的工作流来运行AI编码代理（如Claude Code、Codex等），这些工作流内置了审查循环，帮助开发者从一开始就产出高质量代码。项目采用TypeScript编写，支持多代理协作，每个步骤都可以在NDJSON中记录以保证可追溯性。适合需要提高开发效率和代码质量的软件开发场景，特别是在团队协作和持续集成环境中。",2,"2026-06-11 03:52:04","high_star"]