Open-source harness builder for AI coding

Archon, an open-source workflow engine for AI coding agents, has been released to make AI coding deterministic and repeatable by defining development processes as YAML workflows. The tool, created by coleam00, allows developers to encode phases like planning, implementation, validation, and PR creation, with the AI filling in intelligence at each step while the structure remains deterministic. Archon is positioned as a Dockerfile or GitHub Actions equivalent for AI coding workflows, offering repeatability, isolation via git worktrees, fire-and-forget execution, composability of deterministic and AI nodes, and portability across CLI, Web UI, Slack, Telegram, or GitHub.

The first open-source harness builder for AI coding. Make AI coding deterministic and repeatable. Archon 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. Like what Dockerfiles did for infrastructure and GitHub Actions did for CI/CD - Archon does for AI coding workflows. Think n8n, but for software development. When 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. Archon 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. Repeatable - Same workflow, same sequence, every time. Plan, implement, validate, review, PR. Isolated - Every workflow run gets its own git worktree. Run 5 fixes in parallel with no conflicts. Fire and forget - Kick off a workflow, go do other work. Come back to a finished PR with review comments. Composable - Mix deterministic nodes bash scripts, tests, git ops with AI nodes planning, code generation, review . The AI only runs where it adds value. Portable - Define workflows once in .archon/workflows/ , commit them to your repo. They work the same from CLI, Web UI, Slack, Telegram, or GitHub. Here's an example of an Archon workflow that plans, implements in a loop until tests pass, gets your approval, then creates the PR: .archon/workflows/build-feature.yaml nodes: - id: plan prompt: "Explore the codebase and create an implementation plan" - id: implement depends on: plan loop: AI loop - iterate until done prompt: "Read the plan. Implement the next task. Run validation." until: ALL TASKS COMPLETE fresh context: true Fresh session each iteration - id: run-tests depends on: implement bash: "bun run validate" Deterministic - no AI - id: review depends on: run-tests prompt: "Review all changes against the plan. Fix any issues." - id: approve depends on: review loop: Human approval gate prompt: "Present the changes for review. Address any feedback." until: APPROVED interactive: true Pauses and waits for human input - id: create-pr depends on: approve prompt: "Push changes and create a pull request" Tell your coding agent what you want, and Archon handles the rest: You: Use archon to add dark mode to the settings page Agent: I'll run the archon-idea-to-pr workflow for this. → Creating isolated worktree on branch archon/task-dark-mode... → Planning... → Implementing task 1/4 ... → Implementing task 2/4 ... → Tests failing - iterating... → Tests passing after 2 iterations → Code review complete - 0 issues → PR ready: https://github.com/you/project/pull/47 Looking for the original Python-based Archon task management + RAG ? It's fully preserved on the archive/v1-task-management-rag https://github.com/coleam00/Archon/tree/archive/v1-task-management-rag branch. Most users should start with the- it walks you through credentials, installs the Archon skill into your projects, and gives you the web dashboard. Full Setup Already have Claude Code and just want the CLI?Jump to the Quick Install . Clone the repo and use the guided setup wizard. This configures credentials, platform integrations, and copies the Archon skill into your target projects. Prerequisites - Bun, Claude Code, and the GitHub CLI Bun - bun.sh https://bun.sh macOS/Linux curl -fsSL https://bun.sh/install | bash Windows PowerShell irm bun.sh/install.ps1 | iex GitHub CLI - cli.github.com https://cli.github.com/ macOS brew install gh Windows via winget winget install GitHub.cli Linux Debian/Ubuntu sudo apt install gh Claude Code - claude.ai/code https://claude.ai/code macOS/Linux/WSL curl -fsSL https://claude.ai/install.sh | bash Windows PowerShell irm https://claude.ai/install.ps1 | iex git clone https://github.com/coleam00/Archon cd Archon bun install claude Then say: "Set up Archon" The setup wizard walks you through everything: CLI installation, authentication, platform selection, and copies the Archon skill to your target repo. Already have Claude Code set up? Install the standalone CLI binary and skip the wizard. macOS / Linux curl -fsSL https://archon.diy/install | bash x64 compatibility:The macOS/Linux quick install requires AVX2 on x64 CPUs. Older Intel/AMD hardware and virtual machines that mask AVX2 should use the source installation guide . ARM64 quick installs are unaffected. Windows PowerShell irm https://archon.diy/install.ps1 | iex Homebrew brew install coleam00/archon/archon Compiled binaries need aThe quick-install binaries don't bundle Claude Code. Install it separately, then point Archon at it: CLAUDE BIN PATH . macOS / Linux / WSL curl -fsSL https://claude.ai/install.sh | bash export CLAUDE BIN PATH="$HOME/.local/bin/claude" Windows PowerShell irm https://claude.ai/install.ps1 | iex $env:CLAUDE BIN PATH = "$env:USERPROFILE\.local\bin\claude.exe" Or set assistants.claude.claudeBinaryPath in ~/.archon/config.yaml . The Docker image ships Claude Code pre-installed. See AI Assistants → Binary path configuration for details. Once you've completed either setup path, go to your project and start working: cd /path/to/your/project claude Use archon to fix issue 42 What archon workflows do I have? When would I use each one? The coding agent handles workflow selection, branch naming, and worktree isolation for you. Projects are registered automatically the first time they're used. 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. Archon 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. Register 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. Key pages: Chat - Conversation interface with real-time streaming and tool call visualization Dashboard - Mission Control for monitoring running workflows, with filterable history by project, status, and date Workflow Builder - Visual drag-and-drop editor for creating DAG workflows with loop nodes Workflow Execution - Step-by-step progress view for any running or completed workflow 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. See the Web UI Guide https://archon.diy/adapters/web/ for full documentation. Archon ships with workflows for common development tasks: | Workflow | What it does | |---|---| archon-assist | General Q&A, debugging, exploration - full Claude Code agent with all tools | archon-fix-github-issue | Classify issue → investigate/plan → implement → validate → PR → smart review → self-fix | archon-create-issue | Classify problem → gather context → investigate → create GitHub issue | archon-issue-review-full | Comprehensive fix + full multi-agent review pipeline for GitHub issues | archon-piv-loop | Guided Plan-Implement-Validate loop with human review between iterations | archon-idea-to-pr | Feature idea → plan → implement → validate → PR → 5 parallel reviews → self-fix | archon-plan-to-pr | Execute existing plan → implement → validate → PR → review → self-fix | archon-feature-development | Implement feature from plan → validate → create PR | archon-adversarial-dev | Build a complete application from scratch using adversarial development | archon-smart-pr-review | Classify PR complexity → run targeted review agents → synthesize findings | archon-comprehensive-pr-review | Multi-agent PR review 5 parallel reviewers with automatic fixes | archon-validate-pr | Thorough PR validation testing both main and feature branches | archon-architect | Architectural sweep, complexity reduction, codebase health improvement | archon-refactor-safely | Safe refactoring with type-check hooks and behavior verification | archon-interactive-prd | Create a PRD through guided conversation | archon-ralph-dag | PRD implementation loop - iterate through stories until done | archon-workflow-builder | Generate a new Archon workflow YAML for your project | archon-remotion-generate | Generate or modify Remotion video compositions with AI | archon-resolve-conflicts | Detect merge conflicts → analyze both sides → resolve → validate → commit | Archon ships 19 default workflows - run archon workflow list or describe what you want and the router picks the right one. Or define your own. Default workflows are great starting points - copy one from .archon/workflows/defaults/ and customize it. Workflows are YAML files in .archon/workflows/ , commands are markdown files in .archon/commands/ . Same-named files in your repo override the bundled defaults. Commit them - your whole team runs the same process. See Authoring Workflows https://archon.diy/guides/authoring-workflows/ and Authoring Commands https://archon.diy/guides/authoring-commands/ . The Web UI and CLI work out of the box. Optionally connect a chat platform for remote access: | Platform | Setup time | Guide | |---|---|---| Telegram | 5 min | | Slack Slack Guide https://archon.diy/adapters/slack/ GitHub Webhooks GitHub Guide https://archon.diy/adapters/github/ Discord Discord Guide https://archon.diy/adapters/community/discord/ ┌─────────────────────────────────────────────────────────┐ │ Platform Adapters Web UI, CLI, Telegram, Slack, │ │ Discord, GitHub │ └──────────────────────────┬──────────────────────────────┘ │ ▼ ┌─────────────────────────────────────────────────────────┐ │ Orchestrator │ │ Message Routing & Context Management │ └─────────────┬───────────────────────────┬───────────────┘ │ │ ┌───────┴────────┐ ┌───────┴────────┐ │ │ │ │ ▼ ▼ ▼ ▼ ┌───────────┐ ┌────────────┐ ┌──────────────────────────┐ │ Command │ │ Workflow │ │ AI Assistant Clients │ │ Handler │ │ Executor │ │ Claude / Codex / Pi │ │ Slash │ │ YAML │ │ │ └───────────┘ └────────────┘ └──────────────────────────┘ │ │ │ └──────────────┴──────────────────────┘ │ ▼ ┌─────────────────────────────────────────────────────────┐ │ SQLite / PostgreSQL 14 core tables │ │ Codebases • Conversations • Sessions • Workflow Runs │ │ Isolation Environments • Messages • Workflow Events │ │ Users • User Identities • Workflow Node Sessions │ │ Codebase Env Vars • User GitHub Tokens │ │ User Provider Keys • User AI Prefs │ │ + Better Auth tables, Postgres only │ └─────────────────────────────────────────────────────────┘ Full documentation is available at archon.diy/docs . | Topic | Description | |---|---| | The Book of Archon https://archon.diy/book/ CLI Reference https://archon.diy/reference/cli/ Authoring Workflows https://archon.diy/guides/authoring-workflows/ Authoring Commands https://archon.diy/guides/authoring-commands/ Configuration https://archon.diy/reference/configuration/ AI Assistants https://archon.diy/getting-started/ai-assistants/ Deployment https://archon.diy/deployment/ Architecture https://archon.diy/reference/architecture/ Troubleshooting https://archon.diy/reference/troubleshooting/ For AI tools: Point your LLM at /llms.txt https://archon.diy/llms.txt for an index of all documentation, for the complete docs in a single file, or https://archon.diy/llms-full.txt /llms-full.txt for a condensed version. https://archon.diy/llms-small.txt /llms-small.txt Archon sends a few anonymous events so maintainers can see which workflows get real usage, on what platforms, and whether runs succeed — and prioritize accordingly. No PII, ever. Events: archon started once per CLI invocation / server boot , archon active daily heartbeat while a server is running, so long-running installs stay counted , chat turn handled each direct AI chat turn — platform, provider, model, duration, and usage totals; never message content , workflow invoked each workflow start , workflow completed / workflow failed each run outcome , workflow approval resolved each human approve/reject decision — the binary resolution only, never comments or reasons , and codebase registered a pure count when a project is registered — no name, path, or URL . What's collected categorical only : Workflow name — the real name for bundled Archon-authored workflows; "custom" for your own workflows, so private names never leave your machine. Run shape & outcome — platform cli / web / slack /… , provider id plus the model id on workflow invoked , node count, which node types and features are used loop/approval/script/bash, structured output, persisted sessions, MCP, skills, fresh-context loops , success/failure, duration, a categorical failure reason, and a fixed-enum failure class fatal / transient / unknown — never raw error text plus the failed node's type. Chat activity — one event per direct-chat AI turn with platform, provider, model, duration, and completed/failed. Message content, prompts, and conversation ids are never sent. Aggregate usage — provider-reported token counts and cost USD per workflow run and chat turn, plus total loop iterations per run. Numeric totals only — never the content the tokens represent. Machine context — OS, architecture, Archon version, runtime, whether it's a binary build, and a CI flag. Deployment shape server only — which adapters are enabled booleans , database kind sqlite / postgresql , whether web auth and multi-user mode are on, and the GitHub auth mode. Configuration values tokens, URLs, hosts are never sent.- A random install UUID stored at ~/.archon/telemetry-id . Nothing else. What's not collected: your code, prompts, messages, custom workflow names, workflow descriptions, git remotes, file paths, usernames, tokens, AI output, error message text, your IP address, your geographic location — none of it. Opt out: set any of these in your environment: ARCHON TELEMETRY DISABLED=1 DO NOT TRACK=1 de facto standard honored by Astro, Bun, Prisma, Nuxt, etc. POSTHOG API KEY=off off | 0 | false | disabled | "" all disable CI environments CI=true are auto-disabled — forks running fixtures in GitHub Actions, CircleCI, etc. do not send events. Check the current state: run archon telemetry status to see whether telemetry is enabled, why if not , the install UUID, and the active host. Run archon telemetry reset to rotate the install UUID. archon doctor also surfaces the current state in its check list. Self-host PostHog or use a different project by setting POSTHOG API KEY and POSTHOG HOST . Contributions welcome See the open issues https://github.com/coleam00/Archon/issues for things to work on. Please read CONTRIBUTING.md /coleam00/Archon/blob/dev/CONTRIBUTING.md before submitting a pull request.