[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-3721":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":25,"topics":26,"createdAt":10,"pushedAt":10,"updatedAt":37,"readmeContent":38,"aiSummary":39,"trendingCount":16,"starSnapshotCount":16,"syncStatus":40,"lastSyncTime":41,"discoverSource":42},3721,"Archon","coleam00\u002FArchon","coleam00","The first open-source harness builder for AI coding. Make AI coding deterministic and repeatable.","https:\u002F\u002Farchon.diy",null,"TypeScript",22345,3367,231,167,0,24,181,1044,141,45,"MIT License",false,"dev",true,[27,28,29,30,31,32,33,34,35,36],"ai","automation","bun","claude","cli","coding-assistant","developer-tools","typescript","workflow-engine","yaml","2026-06-12 02:00:53","\u003Cp align=\"center\">\n  \u003Cimg src=\"assets\u002Flogo.png\" alt=\"Archon\" width=\"160\" \u002F>\n\u003C\u002Fp>\n\n\u003Ch1 align=\"center\">Archon\u003C\u002Fh1>\n\n\u003Cp align=\"center\">\n  The first open-source harness builder for AI coding. Make AI coding deterministic and repeatable.\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Ftrendshift.io\u002Frepositories\u002F13964\" target=\"_blank\">\u003Cimg src=\"https:\u002F\u002Ftrendshift.io\u002Fapi\u002Fbadge\u002Frepositories\u002F13964\" alt=\"coleam00%2FArchon | Trendshift\" style=\"width: 250px; height: 55px;\" width=\"250\" height=\"55\"\u002F>\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"LICENSE\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-MIT-blue.svg\" alt=\"License: MIT\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fcoleam00\u002FArchon\u002Factions\u002Fworkflows\u002Ftest.yml\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Fcoleam00\u002FArchon\u002Factions\u002Fworkflows\u002Ftest.yml\u002Fbadge.svg\" alt=\"CI\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Farchon.diy\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fdocs-archon.diy-blue\" alt=\"Docs\" \u002F>\u003C\u002Fa>\n\u003C\u002Fp>\n\n---\n\nArchon is a workflow engine for AI coding agents. Define your development processes as YAML workflows - planning, implementation, validation, code review, PR creation - and run them reliably across all your projects.\n\nLike what Dockerfiles did for infrastructure and GitHub Actions did for CI\u002FCD - Archon does for AI coding workflows. Think n8n, but for software development.\n\n## Why Archon?\n\nWhen you ask an AI agent to \"fix this bug\", what happens depends on the model's mood. It might skip planning. It might forget to run tests. It might write a PR description that ignores your template. Every run is different.\n\nArchon fixes this. Encode your development process as a workflow. The workflow defines the phases, validation gates, and artifacts. The AI fills in the intelligence at each step, but the structure is deterministic and owned by you.\n\n- **Repeatable** - Same workflow, same sequence, every time. Plan, implement, validate, review, PR.\n- **Isolated** - Every workflow run gets its own git worktree. Run 5 fixes in parallel with no conflicts.\n- **Fire and forget** - Kick off a workflow, go do other work. Come back to a finished PR with review comments.\n- **Composable** - Mix deterministic nodes (bash scripts, tests, git ops) with AI nodes (planning, code generation, review). The AI only runs where it adds value.\n- **Portable** - Define workflows once in `.archon\u002Fworkflows\u002F`, commit them to your repo. They work the same from CLI, Web UI, Slack, Telegram, or GitHub.\n\n## What It Looks Like\n\nHere's an example of an Archon workflow that plans, implements in a loop until tests pass, gets your approval, then creates the PR:\n\n```yaml\n# .archon\u002Fworkflows\u002Fbuild-feature.yaml\nnodes:\n  - id: plan\n    prompt: \"Explore the codebase and create an implementation plan\"\n\n  - id: implement\n    depends_on: [plan]\n    loop:                                      # AI loop - iterate until done\n      prompt: \"Read the plan. Implement the next task. Run validation.\"\n      until: ALL_TASKS_COMPLETE\n      fresh_context: true                      # Fresh session each iteration\n\n  - id: run-tests\n    depends_on: [implement]\n    bash: \"bun run validate\"                   # Deterministic - no AI\n\n  - id: review\n    depends_on: [run-tests]\n    prompt: \"Review all changes against the plan. Fix any issues.\"\n\n  - id: approve\n    depends_on: [review]\n    loop:                                      # Human approval gate\n      prompt: \"Present the changes for review. Address any feedback.\"\n      until: APPROVED\n      interactive: true                        # Pauses and waits for human input\n\n  - id: create-pr\n    depends_on: [approve]\n    prompt: \"Push changes and create a pull request\"\n```\n\nTell your coding agent what you want, and Archon handles the rest:\n\n```\nYou: Use archon to add dark mode to the settings page\n\nAgent: I'll run the archon-idea-to-pr workflow for this.\n       → Creating isolated worktree on branch archon\u002Ftask-dark-mode...\n       → Planning...\n       → Implementing (task 1\u002F4)...\n       → Implementing (task 2\u002F4)...\n       → Tests failing - iterating...\n       → Tests passing after 2 iterations\n       → Code review complete - 0 issues\n       → PR ready: https:\u002F\u002Fgithub.com\u002Fyou\u002Fproject\u002Fpull\u002F47\n```\n\n## Previous Version\n\nLooking for the original Python-based Archon (task management + RAG)? It's fully preserved on the [`archive\u002Fv1-task-management-rag`](https:\u002F\u002Fgithub.com\u002Fcoleam00\u002FArchon\u002Ftree\u002Farchive\u002Fv1-task-management-rag) branch.\n\n## Getting Started\n\n> **Most users should start with the [Full Setup](#full-setup-5-minutes)** - it walks you through credentials, installs the Archon skill into your projects, and gives you the web dashboard.\n>\n> **Already have Claude Code and just want the CLI?** Jump to the [Quick Install](#quick-install-30-seconds).\n\n### Full Setup (5 minutes)\n\nClone the repo and use the guided setup wizard. This configures credentials, platform integrations, and copies the Archon skill into your target projects.\n\n\u003Cdetails>\n\u003Csummary>\u003Cb>Prerequisites\u003C\u002Fb> - Bun, Claude Code, and the GitHub CLI\u003C\u002Fsummary>\n\n**Bun** - [bun.sh](https:\u002F\u002Fbun.sh)\n\n```bash\n# macOS\u002FLinux\ncurl -fsSL https:\u002F\u002Fbun.sh\u002Finstall | bash\n\n# Windows (PowerShell)\nirm bun.sh\u002Finstall.ps1 | iex\n```\n\n**GitHub CLI** - [cli.github.com](https:\u002F\u002Fcli.github.com\u002F)\n\n```bash\n# macOS\nbrew install gh\n\n# Windows (via winget)\nwinget install GitHub.cli\n\n# Linux (Debian\u002FUbuntu)\nsudo apt install gh\n```\n\n**Claude Code** - [claude.ai\u002Fcode](https:\u002F\u002Fclaude.ai\u002Fcode)\n\n```bash\n# macOS\u002FLinux\u002FWSL\ncurl -fsSL https:\u002F\u002Fclaude.ai\u002Finstall.sh | bash\n\n# Windows (PowerShell)\nirm https:\u002F\u002Fclaude.ai\u002Finstall.ps1 | iex\n```\n\n\u003C\u002Fdetails>\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fcoleam00\u002FArchon\ncd Archon\nbun install\nclaude\n```\n\nThen say: **\"Set up Archon\"**\n\nThe setup wizard walks you through everything: CLI installation, authentication, platform selection, and copies the Archon skill to your target repo.\n\n### Quick Install (30 seconds)\n\nAlready have Claude Code set up? Install the standalone CLI binary and skip the wizard.\n\n**macOS \u002F Linux**\n```bash\ncurl -fsSL https:\u002F\u002Farchon.diy\u002Finstall | bash\n```\n\n**Windows (PowerShell)**\n```powershell\nirm https:\u002F\u002Farchon.diy\u002Finstall.ps1 | iex\n```\n\n**Homebrew**\n```bash\nbrew install coleam00\u002Farchon\u002Farchon\n```\n\n> **Compiled binaries need a `CLAUDE_BIN_PATH`.** The quick-install binaries\n> don't bundle Claude Code. Install it separately, then point Archon at it:\n>\n> ```bash\n> # macOS \u002F Linux \u002F WSL\n> curl -fsSL https:\u002F\u002Fclaude.ai\u002Finstall.sh | bash\n> export CLAUDE_BIN_PATH=\"$HOME\u002F.local\u002Fbin\u002Fclaude\"\n>\n> # Windows (PowerShell)\n> irm https:\u002F\u002Fclaude.ai\u002Finstall.ps1 | iex\n> $env:CLAUDE_BIN_PATH = \"$env:USERPROFILE\\.local\\bin\\claude.exe\"\n> ```\n>\n> Or set `assistants.claude.claudeBinaryPath` in `~\u002F.archon\u002Fconfig.yaml`.\n> The Docker image ships Claude Code pre-installed. See [AI Assistants → Binary path configuration](https:\u002F\u002Farchon.diy\u002Fdocs\u002Fgetting-started\u002Fai-assistants\u002F#binary-path-configuration-compiled-binaries-only) for details.\n\n### Start Using Archon\n\nOnce you've completed either setup path, go to your project and start working:\n\n```bash\ncd \u002Fpath\u002Fto\u002Fyour\u002Fproject\nclaude\n```\n\n```\nUse archon to fix issue #42\n```\n\n```\nWhat archon workflows do I have? When would I use each one?\n```\n\nThe coding agent handles workflow selection, branch naming, and worktree isolation for you. Projects are registered automatically the first time they're used.\n\n> **Important:** Always run Claude Code from your target repo, not from the Archon repo. The setup wizard copies the Archon skill into your project so it works from there.\n\n## Web UI\n\nArchon includes a web dashboard for chatting with your coding agent, running workflows, and monitoring activity. Binary installs: run `archon serve` to download and start the web UI in one step. From source: ask your coding agent to run the frontend from the Archon repo, or run `bun run dev` from the repo root yourself.\n\nRegister a project by clicking **+** next to \"Project\" in the chat sidebar - enter a GitHub URL or local path. Then start a conversation, invoke workflows, and watch progress in real time.\n\n**Key pages:**\n- **Chat** - Conversation interface with real-time streaming and tool call visualization\n- **Dashboard** - Mission Control for monitoring running workflows, with filterable history by project, status, and date\n- **Workflow Builder** - Visual drag-and-drop editor for creating DAG workflows with loop nodes\n- **Workflow Execution** - Step-by-step progress view for any running or completed workflow\n\n**Monitoring hub:** The sidebar shows conversations from **all platforms** - not just the web. Workflows kicked off from the CLI, messages from Slack or Telegram, GitHub issue interactions - everything appears in one place.\n\nSee the [Web UI Guide](https:\u002F\u002Farchon.diy\u002Fadapters\u002Fweb\u002F) for full documentation.\n\n## What Can You Automate?\n\nArchon ships with workflows for common development tasks:\n\n| Workflow | What it does |\n|----------|-------------|\n| `archon-assist` | General Q&A, debugging, exploration - full Claude Code agent with all tools |\n| `archon-fix-github-issue` | Classify issue → investigate\u002Fplan → implement → validate → PR → smart review → self-fix |\n| `archon-idea-to-pr` | Feature idea → plan → implement → validate → PR → 5 parallel reviews → self-fix |\n| `archon-plan-to-pr` | Execute existing plan → implement → validate → PR → review → self-fix |\n| `archon-issue-review-full` | Comprehensive fix + full multi-agent review pipeline for GitHub issues |\n| `archon-smart-pr-review` | Classify PR complexity → run targeted review agents → synthesize findings |\n| `archon-comprehensive-pr-review` | Multi-agent PR review (5 parallel reviewers) with automatic fixes |\n| `archon-create-issue` | Classify problem → gather context → investigate → create GitHub issue |\n| `archon-validate-pr` | Thorough PR validation testing both main and feature branches |\n| `archon-resolve-conflicts` | Detect merge conflicts → analyze both sides → resolve → validate → commit |\n| `archon-feature-development` | Implement feature from plan → validate → create PR |\n| `archon-architect` | Architectural sweep, complexity reduction, codebase health improvement |\n| `archon-refactor-safely` | Safe refactoring with type-check hooks and behavior verification |\n| `archon-ralph-dag` | PRD implementation loop - iterate through stories until done |\n| `archon-remotion-generate` | Generate or modify Remotion video compositions with AI |\n| `archon-test-loop-dag` | Loop node test workflow - iterative counter until completion |\n| `archon-piv-loop` | Guided Plan-Implement-Validate loop with human review between iterations |\n\nArchon ships 17 default workflows - run `archon workflow list` or describe what you want and the router picks the right one.\n\n**Or define your own.** Default workflows are great starting points - copy one from `.archon\u002Fworkflows\u002Fdefaults\u002F` and customize it. Workflows are YAML files in `.archon\u002Fworkflows\u002F`, commands are markdown files in `.archon\u002Fcommands\u002F`. Same-named files in your repo override the bundled defaults. Commit them - your whole team runs the same process.\n\nSee [Authoring Workflows](https:\u002F\u002Farchon.diy\u002Fguides\u002Fauthoring-workflows\u002F) and [Authoring Commands](https:\u002F\u002Farchon.diy\u002Fguides\u002Fauthoring-commands\u002F).\n\n## Add a Platform\n\nThe Web UI and CLI work out of the box. Optionally connect a chat platform for remote access:\n\n| Platform | Setup time | Guide |\n|----------|-----------|-------|\n| **Telegram** | 5 min | [Telegram Guide](https:\u002F\u002Farchon.diy\u002Fadapters\u002Ftelegram\u002F) |\n| **Slack** | 15 min | [Slack Guide](https:\u002F\u002Farchon.diy\u002Fadapters\u002Fslack\u002F) |\n| **GitHub Webhooks** | 15 min | [GitHub Guide](https:\u002F\u002Farchon.diy\u002Fadapters\u002Fgithub\u002F) |\n| **Discord** | 5 min | [Discord Guide](https:\u002F\u002Farchon.diy\u002Fadapters\u002Fcommunity\u002Fdiscord\u002F) |\n\n## Architecture\n\n```\n┌─────────────────────────────────────────────────────────┐\n│  Platform Adapters (Web UI, CLI, Telegram, Slack,       │\n│                    Discord, GitHub)                     │\n└──────────────────────────┬──────────────────────────────┘\n                           │\n                           ▼\n┌─────────────────────────────────────────────────────────┐\n│                     Orchestrator                        │\n│          (Message Routing & Context Management)         │\n└─────────────┬───────────────────────────┬───────────────┘\n              │                           │\n      ┌───────┴────────┐          ┌───────┴────────┐\n      │                │          │                │\n      ▼                ▼          ▼                ▼\n┌───────────┐  ┌────────────┐  ┌──────────────────────────┐\n│  Command  │  │  Workflow  │  │    AI Assistant Clients  │\n│  Handler  │  │  Executor  │  │   (Claude \u002F Codex \u002F Pi)  │\n│  (Slash)  │  │  (YAML)    │  │                          │\n└───────────┘  └────────────┘  └──────────────────────────┘\n      │              │                      │\n      └──────────────┴──────────────────────┘\n                           │\n                           ▼\n┌─────────────────────────────────────────────────────────┐\n│              SQLite \u002F PostgreSQL (7 Tables)             │\n│   Codebases • Conversations • Sessions • Workflow Runs  │\n│    Isolation Environments • Messages • Workflow Events  │\n└─────────────────────────────────────────────────────────┘\n```\n\n## Documentation\n\nFull documentation is available at **[archon.diy](https:\u002F\u002Farchon.diy)**.\n\n| Topic | Description |\n|-------|-------------|\n| [Getting Started](https:\u002F\u002Farchon.diy\u002Fgetting-started\u002Foverview\u002F) | Setup guide (Web UI or CLI) |\n| [The Book of Archon](https:\u002F\u002Farchon.diy\u002Fbook\u002F) | 10-chapter narrative tutorial |\n| [CLI Reference](https:\u002F\u002Farchon.diy\u002Freference\u002Fcli\u002F) | Full CLI reference |\n| [Authoring Workflows](https:\u002F\u002Farchon.diy\u002Fguides\u002Fauthoring-workflows\u002F) | Create custom YAML workflows |\n| [Authoring Commands](https:\u002F\u002Farchon.diy\u002Fguides\u002Fauthoring-commands\u002F) | Create reusable AI commands |\n| [Configuration](https:\u002F\u002Farchon.diy\u002Freference\u002Fconfiguration\u002F) | All config options, env vars, YAML settings |\n| [AI Assistants](https:\u002F\u002Farchon.diy\u002Fgetting-started\u002Fai-assistants\u002F) | Claude, Codex, and Pi setup details |\n| [Deployment](https:\u002F\u002Farchon.diy\u002Fdeployment\u002F) | Docker, VPS, production setup |\n| [Architecture](https:\u002F\u002Farchon.diy\u002Freference\u002Farchitecture\u002F) | System design and internals |\n| [Troubleshooting](https:\u002F\u002Farchon.diy\u002Freference\u002Ftroubleshooting\u002F) | Common issues and fixes |\n\n## Telemetry\n\nArchon sends a single anonymous event — `workflow_invoked` — each time a workflow starts, so maintainers can see which workflows get real usage and prioritize accordingly. **No PII, ever.**\n\n**What's collected:** the workflow name, the workflow description (both authored by you in YAML), the platform that triggered it (`cli`, `web`, `slack`, etc.), the Archon version, and a random install UUID stored at `~\u002F.archon\u002Ftelemetry-id`. Nothing else.\n\n**What's *not* collected:** your code, prompts, messages, git remotes, file paths, usernames, tokens, AI output, workflow node details — none of it.\n\n**Opt out:** set any of these in your environment:\n\n```bash\nARCHON_TELEMETRY_DISABLED=1\nDO_NOT_TRACK=1        # de facto standard honored by Astro, Bun, Prisma, Nuxt, etc.\n```\n\nSelf-host PostHog or use a different project by setting `POSTHOG_API_KEY` and `POSTHOG_HOST`.\n\n## Contributing\n\nContributions welcome! See the open [issues](https:\u002F\u002Fgithub.com\u002Fcoleam00\u002FArchon\u002Fissues) for things to work on.\n\nPlease read [CONTRIBUTING.md](CONTRIBUTING.md) before submitting a pull request.\n\n## Star History\n\n[![Star History Chart](https:\u002F\u002Fapi.star-history.com\u002Fchart?repos=coleam00\u002FArchon&type=date&legend=top-left)](https:\u002F\u002Fwww.star-history.com\u002F?repos=coleam00%2FArchon&type=date&legend=top-left)\n\n## License\n\n[MIT](LICENSE)\n","Archon 是一个用于AI编码的工作流引擎，旨在使AI编码过程变得可预测且可重复。它允许开发者通过YAML文件定义开发流程，包括规划、实施、验证、代码审查和PR创建等步骤，并确保这些流程在所有项目中可靠执行。其核心功能包括工作流的可重复性、隔离性（每个工作流运行都有独立的git工作树）、无需持续关注即可完成任务的能力以及与多种工具组合使用的灵活性。Archon适用于需要标准化AI辅助开发流程的企业或个人开发者，特别是在追求高质量代码产出及团队协作效率提升的场景下尤为适用。",2,"2026-06-11 02:55:47","top_language"]