Deploy Now

SaaS Alternative

CircleCI GitHub Actions Harness

Categories

Developer Tools DevOps AI Automation CI/CD Workflow Engine Code Quality

Stars

23,417

Forks

3,467

Watchers

226

Developer links

Last Updated: 09-10-2026
Share on X

Archon

Stop hoping your AI coding assistant remembers to plan before it codes, test after it implements, and review before it ships. Archon wraps Claude Code, OpenAI Codex, and other AI agents inside structured YAML workflows that enforce the same development process every single time. Define your pipeline as a directed acyclic graph of nodes (AI tasks, shell scripts, approval gates, loops) and Archon handles the orchestration: resolving dependencies, running independent nodes in parallel, passing artifacts between steps, and isolating every run in its own git worktree so five bug fixes can proceed simultaneously without conflicts. Ship with 17 pre-built workflows covering everything from "idea to merged PR" to automated conflict resolution, or author your own by committing YAML files to your repository's .archon/workflows/ directory. The web dashboard, launched with archon serve, provides a conversation interface with real-time streaming, a visual drag-and-drop workflow builder for creating DAG pipelines, step-by-step progress monitoring for every run, and a unified sidebar aggregating conversations from CLI, Slack, Telegram, and GitHub into one view. An NLP router parses natural language requests and automatically selects the right workflow. Structured JSON output schemas let you enforce typed responses from AI nodes, with validation and auto-repair for providers that lack native schema support. Every workflow file is version-controlled, portable, and reviewable in pull requests, so your entire team runs identical processes from day one. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Archon
Archon
Archon
Archon
Archon
Archon

Benefits

  • Deterministic AI Development Pipelines
  • YAML workflow definitions encode your exact development process as version-controlled DAGs. Every developer and every run follows the same plan-implement-test-review sequence regardless of which AI model executes the steps.
  • Parallel Isolated Execution
  • Each workflow run creates its own git worktree, enabling multiple bug fixes, features, or refactors to execute simultaneously without file conflicts. Independent DAG nodes run concurrently via Promise.allSettled.
  • Unified Cross-Platform Monitoring
  • The web dashboard aggregates conversations and workflow runs from CLI, Slack, Telegram, and GitHub into a single monitoring hub. Filter history by project, status, or date across all connected platforms.
  • Version-Controlled Team Processes
  • Commit workflow YAML files to your repository so every team member inherits identical development processes on git clone. New hires, CI pipelines, and cross-project workflows share the same portable definitions.

Features

  • YAML DAG Workflows
  • Define multi-step development processes as directed acyclic graphs with dependency resolution, conditional branching, loop-until-pass nodes, and artifact passing between steps.
  • Web Dashboard
  • Launch with archon serve for a real-time conversation interface, visual drag-and-drop workflow builder, step-by-step execution monitor, and cross-platform conversation aggregation.
  • Agent Adapters
  • Built-in adapters for Claude Code, OpenAI Codex CLI, OpenCode, Copilot, and Pi. Each adapter handles prompting, context injection, and structured output extraction.
  • Git Worktree Isolation
  • Every workflow run operates in a dedicated git worktree, preventing file conflicts during parallel execution. Clean up automatically when runs complete.
  • NLP Workflow Router
  • Natural language requests are parsed and matched to the most appropriate workflow from your library of 17 built-in plus custom definitions.