coleam00/ArchonPublic

The first open-source harness builder for AI coding. Make AI coding deterministic and repeatable.

AI summary: An open-source harness builder designed to make AI coding workflows deterministic and repeatable.

Stars
23.9K
+26 today
Forks
3.5K
Watchers
213
Open issues
166
Open PRs
13
Contributors
~91
Commits
4.4K
Branches
999
Views (30d)
5

TypeScriptMITCreated Feb 7, 2025Last push 2d agoLatest release v0.14.0+62 stars this week+221 this month

Quick answers

What is Archon?
An open-source harness builder designed to make AI coding workflows deterministic and repeatable.
What does Archon do?
Archon addresses the inherent unpredictability of LLM-based coding tools by providing a framework to build deterministic execution harnesses. It allows developers to define strict boundaries, state transitions, and validation steps that an AI agent must adhere to during code generation. By wrapping the AI's execution in a controlled harness, it ensures that outputs meet specific architectural standards and pass automated tests before being presented to the user. The system intercepts hallucinations or infinite loops, forcing the agent to self-correct based on explicit error feedback. This transforms stochastic AI code generation into a reliable, pipeline-ready process.
Who is Archon for?
Software engineers, DevOps professionals, and AI researchers who require reliability and strict control over AI-generated code. Familiarity with testing frameworks and pipeline automation is necessary.
How do I get started with Archon?
npm install -g @archon/cli
How popular is Archon on GitHub?
coleam00/Archon has 23,948 stars and 3,534 forks on GitHub, and gained 62 stars in the last 7 days.
What license does Archon use?
coleam00/Archon is released under the MIT license.

Star history

since Jul 29, 2026
010K20KJul 2026Sep 2026Oct 2026Nov 2026
23.9K stars as of Nov 18, 2026. Measured daily since Jul 29, 2026; GitHub no longer exposes earlier star timestamps.

Update history

3 recorded
  • Nov 14, 2026New release v0.14.0 (previously v0.13.2).
  • Nov 3, 2026New release v0.13.2 (previously v0.12.1).
  • Oct 25, 2026New release v0.12.1 (previously v0.11.1).

Contribution activity

commits per day, last 52 weeks
NovDecJanFebMarAprMayJunJulAugSepOctNovMonWedFri2025-11-16: 0 commits2025-11-17: 0 commits2025-11-18: 0 commits2025-11-19: 0 commits2025-11-20: 1 commit2025-11-21: 0 commits2025-11-22: 0 commits2025-11-23: 0 commits2025-11-24: 0 commits2025-11-25: 0 commits2025-11-26: 0 commits2025-11-27: 1 commit2025-11-28: 2 commits2025-11-29: 0 commits2025-11-30: 0 commits2025-12-01: 38 commits2025-12-02: 16 commits2025-12-03: 7 commits2025-12-04: 14 commits2025-12-05: 5 commits2025-12-06: 0 commits2025-12-07: 5 commits2025-12-08: 3 commits2025-12-09: 1 commit2025-12-10: 0 commits2025-12-11: 0 commits2025-12-12: 0 commits2025-12-13: 0 commits2025-12-14: 0 commits2025-12-15: 4 commits2025-12-16: 3 commits2025-12-17: 20 commits2025-12-18: 4 commits2025-12-19: 0 commits2025-12-20: 0 commits2025-12-21: 0 commits2025-12-22: 0 commits2025-12-23: 0 commits2025-12-24: 0 commits2025-12-25: 0 commits2025-12-26: 0 commits2025-12-27: 0 commits2025-12-28: 0 commits2025-12-29: 0 commits2025-12-30: 4 commits2025-12-31: 0 commits2026-01-01: 0 commits2026-01-02: 16 commits2026-01-03: 8 commits2026-01-04: 1 commit2026-01-05: 2 commits2026-01-06: 2 commits2026-01-07: 6 commits2026-01-08: 0 commits2026-01-09: 0 commits2026-01-10: 0 commits2026-01-11: 0 commits2026-01-12: 10 commits2026-01-13: 16 commits2026-01-14: 6 commits2026-01-15: 9 commits2026-01-16: 3 commits2026-01-17: 12 commits2026-01-18: 15 commits2026-01-19: 14 commits2026-01-20: 4 commits2026-01-21: 9 commits2026-01-22: 15 commits2026-01-23: 1 commit2026-01-24: 0 commits2026-01-25: 0 commits2026-01-26: 0 commits2026-01-27: 0 commits2026-01-28: 0 commits2026-01-29: 6 commits2026-01-30: 24 commits2026-01-31: 1 commit2026-02-01: 0 commits2026-02-02: 0 commits2026-02-03: 0 commits2026-02-04: 1 commit2026-02-05: 4 commits2026-02-06: 0 commits2026-02-07: 0 commits2026-02-08: 0 commits2026-02-09: 0 commits2026-02-10: 0 commits2026-02-11: 0 commits2026-02-12: 0 commits2026-02-13: 0 commits2026-02-14: 0 commits2026-02-15: 0 commits2026-02-16: 16 commits2026-02-17: 23 commits2026-02-18: 14 commits2026-02-19: 6 commits2026-02-20: 7 commits2026-02-21: 1 commit2026-02-22: 0 commits2026-02-23: 5 commits2026-02-24: 8 commits2026-02-25: 4 commits2026-02-26: 9 commits2026-02-27: 1 commit2026-02-28: 1 commit2026-03-01: 1 commit2026-03-02: 0 commits2026-03-03: 0 commits2026-03-04: 15 commits2026-03-05: 15 commits2026-03-06: 12 commits2026-03-07: 0 commits2026-03-08: 2 commits2026-03-09: 2 commits2026-03-10: 9 commits2026-03-11: 8 commits2026-03-12: 22 commits2026-03-13: 22 commits2026-03-14: 14 commits2026-03-15: 16 commits2026-03-16: 7 commits2026-03-17: 10 commits2026-03-18: 10 commits2026-03-19: 27 commits2026-03-20: 4 commits2026-03-21: 0 commits2026-03-22: 0 commits2026-03-23: 4 commits2026-03-24: 16 commits2026-03-25: 29 commits2026-03-26: 12 commits2026-03-27: 5 commits2026-03-28: 6 commits2026-03-29: 16 commits2026-03-30: 26 commits2026-03-31: 11 commits2026-04-01: 35 commits2026-04-02: 51 commits2026-04-03: 3 commits2026-04-04: 1 commit2026-04-05: 5 commits2026-04-06: 66 commits2026-04-07: 29 commits2026-04-08: 23 commits2026-04-09: 14 commits2026-04-10: 49 commits2026-04-11: 0 commits2026-04-12: 8 commits2026-04-13: 8 commits2026-04-14: 7 commits2026-04-15: 5 commits2026-04-16: 19 commits2026-04-17: 5 commits2026-04-18: 1 commit2026-04-19: 4 commits2026-04-20: 12 commits2026-04-21: 4 commits2026-04-22: 19 commits2026-04-23: 2 commits2026-04-24: 6 commits2026-04-25: 0 commits2026-04-26: 0 commits2026-04-27: 13 commits2026-04-28: 7 commits2026-04-29: 15 commits2026-04-30: 1 commit2026-05-01: 3 commits2026-05-02: 0 commits2026-05-03: 0 commits2026-05-04: 12 commits2026-05-05: 0 commits2026-05-06: 1 commit2026-05-07: 0 commits2026-05-08: 0 commits2026-05-09: 1 commit2026-05-10: 0 commits2026-05-11: 11 commits2026-05-12: 9 commits2026-05-13: 5 commits2026-05-14: 11 commits2026-05-15: 8 commits2026-05-16: 0 commits2026-05-17: 0 commits2026-05-18: 3 commits2026-05-19: 4 commits2026-05-20: 2 commits2026-05-21: 8 commits2026-05-22: 3 commits2026-05-23: 0 commits2026-05-24: 0 commits2026-05-25: 4 commits2026-05-26: 7 commits2026-05-27: 0 commits2026-05-28: 14 commits2026-05-29: 9 commits2026-05-30: 0 commits2026-05-31: 0 commits2026-06-01: 2 commits2026-06-02: 3 commits2026-06-03: 0 commits2026-06-04: 14 commits2026-06-05: 10 commits2026-06-06: 0 commits2026-06-07: 0 commits2026-06-08: 15 commits2026-06-09: 2 commits2026-06-10: 3 commits2026-06-11: 5 commits2026-06-12: 6 commits2026-06-13: 0 commits2026-06-14: 0 commits2026-06-15: 1 commit2026-06-16: 0 commits2026-06-17: 0 commits2026-06-18: 0 commits2026-06-19: 1 commit2026-06-20: 0 commits2026-06-21: 0 commits2026-06-22: 0 commits2026-06-23: 0 commits2026-06-24: 0 commits2026-06-25: 0 commits2026-06-26: 17 commits2026-06-27: 2 commits2026-06-28: 0 commits2026-06-29: 0 commits2026-06-30: 0 commits2026-07-01: 0 commits2026-07-02: 0 commits2026-07-03: 2 commits2026-07-04: 3 commits2026-07-05: 0 commits2026-07-06: 0 commits2026-07-07: 0 commits2026-07-08: 3 commits2026-07-09: 0 commits2026-07-10: 1 commit2026-07-11: 0 commits2026-07-12: 0 commits2026-07-13: 1 commit2026-07-14: 22 commits2026-07-15: 8 commits2026-07-16: 16 commits2026-07-17: 14 commits2026-07-18: 0 commits2026-07-19: 1 commit2026-07-20: 24 commits2026-07-21: 31 commits2026-07-22: 0 commits2026-07-23: 1 commit2026-07-24: 0 commits2026-07-25: 0 commits2026-07-26: 0 commits2026-07-27: 3 commits2026-07-28: 0 commits2026-07-29: 4 commits2026-07-30: 7 commits2026-07-31: 10 commits2026-08-01: 3 commits2026-08-02: 3 commits2026-08-03: 24 commits2026-08-04: 8 commits2026-08-05: 12 commits2026-08-06: 6 commits2026-08-07: 0 commits2026-08-08: 0 commits2026-08-09: 0 commits2026-08-10: 0 commits2026-08-11: 1 commit2026-08-12: 7 commits2026-08-13: 3 commits2026-08-14: 4 commits2026-08-15: 0 commits2026-08-16: 1 commit2026-08-17: 18 commits2026-08-18: 13 commits2026-08-19: 78 commits2026-08-20: 15 commits2026-08-21: 71 commits2026-08-22: 76 commits2026-08-23: 24 commits2026-08-24: 81 commits2026-08-25: 69 commits2026-08-26: 11 commits2026-08-27: 60 commits2026-08-28: 125 commits2026-08-29: 48 commits2026-08-30: 26 commits2026-08-31: 64 commits2026-09-01: 74 commits2026-09-02: 67 commits2026-09-03: 1 commit2026-09-04: 0 commits2026-09-05: 0 commits2026-09-06: 1 commit2026-09-07: 0 commits2026-09-08: 12 commits2026-09-09: 21 commits2026-09-10: 42 commits2026-09-11: 17 commits2026-09-12: 0 commits2026-09-13: 0 commits2026-09-14: 1 commit2026-09-15: 1 commit2026-09-16: 0 commits2026-09-17: 0 commits2026-09-18: 0 commits2026-09-19: 0 commits2026-09-20: 0 commits2026-09-21: 25 commits2026-09-22: 5 commits2026-09-23: 12 commits2026-09-24: 24 commits2026-09-25: 27 commits2026-09-26: 0 commits2026-09-27: 0 commits2026-09-28: 0 commits2026-09-29: 0 commits2026-09-30: 0 commits2026-10-01: 0 commits2026-10-02: 7 commits2026-10-03: 38 commits2026-10-04: 37 commits2026-10-05: 60 commits2026-10-06: 34 commits2026-10-07: 16 commits2026-10-08: 14 commits2026-10-09: 0 commits2026-10-10: 0 commits2026-10-11: 0 commits2026-10-12: 3 commits2026-10-13: 34 commits2026-10-14: 78 commits2026-10-15: 58 commits2026-10-16: 41 commits2026-10-17: 39 commits2026-10-18: 72 commits2026-10-19: 63 commits2026-10-20: 68 commits2026-10-21: 43 commits2026-10-22: 71 commits2026-10-23: 47 commits2026-10-24: 28 commits2026-10-25: 1 commit2026-10-26: 7 commits2026-10-27: 1 commit2026-10-28: 30 commits2026-10-29: 11 commits2026-10-30: 18 commits2026-10-31: 2 commits2026-11-01: 0 commits2026-11-02: 10 commits2026-11-03: 2 commits2026-11-04: 2 commits2026-11-05: 0 commits2026-11-06: 18 commits2026-11-07: 18 commits2026-11-08: 0 commits2026-11-09: 15 commits2026-11-10: 15 commits2026-11-11: 42 commits2026-11-12: 27 commits2026-11-13: 23 commits2026-11-14: 0 commits
3,762 commits in the last yearLessMore

Signals and awards

derived from tracked data
  • Widely adopted

    23,948 stars

  • Very active

    3,762 commits in 52 weeks

  • Outside contributions

    91% of recent commits from the community

  • Well documented

    High community health score

  • Permissive license

    MIT

  • Continuous integration

    Automated checks passing

What Archon does

Archon addresses the inherent unpredictability of LLM-based coding tools by providing a framework to build deterministic execution harnesses. It allows developers to define strict boundaries, state transitions, and validation steps that an AI agent must adhere to during code generation. By wrapping the AI's execution in a controlled harness, it ensures that outputs meet specific architectural standards and pass automated tests before being presented to the user. The system intercepts hallucinations or infinite loops, forcing the agent to self-correct based on explicit error feedback. This transforms stochastic AI code generation into a reliable, pipeline-ready process.

Software engineers, DevOps professionals, and AI researchers who require reliability and strict control over AI-generated code. Familiarity with testing frameworks and pipeline automation is necessary.

  • Deterministic Workflows: Enforces strict state machines that dictate exactly how an AI agent progresses through a coding task.
  • Automated Validation: Integrates directly with testing frameworks to automatically reject and iterate on failing AI-generated code.
  • State Rollbacks: Automatically reverts the codebase to a clean state if the agent's proposed changes cause compilation or logic errors.
  • Audit Logging: Records the complete prompt chain and execution path to ensure total transparency in how the AI reached its solution.
  • Framework Agnostic: Designed to wrap around various underlying LLMs and coding agents without being locked into a specific provider.

Where teams use it

Automated Test Generation

QA teams use Archon to ensure AI-generated test suites compile successfully and achieve required coverage metrics before committing.

Safe Refactoring

Engineers deploy the harness to allow AI agents to refactor legacy code, relying on the automated rollback if integration tests fail.

Pipeline Integration

DevOps engineers integrate AI code generation directly into CI/CD pipelines, confident that the harness will enforce strict quality gates.

Agent Benchmarking

AI researchers utilize the deterministic environment to accurately measure and compare the coding proficiency of different foundation models.

Getting started: npm install -g @archon/cli

README

dev branch

Archon

Archon

The simplest way to build the software that builds your software.
YAML workflows that can do anything.

coleam00%2FArchon | Trendshift

License: MIT CI Docs


Archon is a factory builder. You describe how work should get done as YAML workflows, and Archon runs them with AI agents, scripts and your decisions in the places that need them. Software is the first factory: the bundled SDLC pack takes an issue to a merged pull request. The same engine runs any process you can describe.

Take yourself out of the loop and sit on top of it. Runs do the work, queues keep it moving, and a run comes to you only when it needs a decision you own.

Why Archon

Ask a coding agent to fix a bug and the result depends on the run. It may skip the plan, forget the tests or ignore your PR template. You end up supervising every step.

Archon turns your process into a workflow you own. The workflow fixes the steps, the checks and the gates. The agent supplies the judgment inside each step. That gives you:

  • The same process every time. Plan, implement, review, validate, open the PR, in the order you wrote down.
  • Human on the loop, not in it. Queues take work forward on their own. When a run reaches a decision it can't make, it pauses as one attention item: what it is, why it matters, a recommendation and the choices. You answer and it carries on.
  • Governance built in. Approval gates, a full event log and transcript for every run, and the cost of every run, all stored in your own database.
  • Your agents, your subscriptions. Archon is not another coding agent. It runs Claude Code, Codex and Pi through their own CLIs and SDKs, with the accounts and project guidance you already have.
  • Self-hosted. One install on your machine or server. SQLite by default, PostgreSQL if you want it.

What it looks like

A workflow is a graph of nodes. Agents judge, code computes, and you decide where it matters:

# .archon/workflows/build-feature.yaml
name: build-feature
description: Plan, implement until the tests pass, ask for approval, open the PR.
nodes:
  - id: plan
    prompt: "Read the request and the code. Write an implementation plan."

  - id: implement
    depends_on: [plan]
    loop:
      prompt: "Implement the next step of the plan."
      until_bash: "bun run test"          # your test command; code decides when it is done
      max_iterations: 10
      fresh_context: true

  - id: approve
    depends_on: [implement]
    wait:                                 # the run pauses and asks you
      attention: "Review the change. Approve, or reject to stop."
      form: approval

  - id: stop
    depends_on: [approve]
    when: "$approve.output.decision == 'reject'"
    cancel: "Rejected at review."

  - id: pr
    depends_on: [approve]
    when: "$approve.output.decision == 'approve'"
    prompt: "Push the branch and open a pull request."
flowchart LR
  plan["plan<br/>(agent)"] --> implement["implement<br/>(agent, loops until the tests pass)"]
  implement --> approve{"approve<br/>(waits for you)"}
  approve -- reject --> stop["stop"]
  approve -- approve --> pr["pr<br/>(agent)"]
Loading

Save it in your repository's .archon/workflows/, swap bun run test for your own test command, and run it:

archon workflow run build-feature "Add dark mode to the settings page"

Repository runs get their own git worktree by default, so several can work on one repository at once.

A software factory: issue in, merged PR out

The bundled sdlc pack is a working factory for a repository:

  1. You open an issue. archon-intake checks it against the current code and decides what it needs: a plan, an investigation, straight to delivery, or a maintainer's look.
  2. The build queue picks it up. archon-build-queue claims the next ready issue, writes the brief and runs archon-ship: plan, implement, review through specialist lenses, fix the findings, wait for CI. It stops at a pull request whose review says Ready, asking once for any check no round can run, or at one a maintainer's ready answer hands on; the merge gate checks either the same way.
  3. The merge queue lands it. archon-merge-queue merges the clear ready pull requests that merge cleanly, through a gate that checks the review verdict and CI at the head commit and that the base branch is not red. The queue judges open review threads itself and sends a pull request that conflicts back to the build queue.
  4. You answer what's unclear. A scope question, a schema change or a stuck round becomes one attention item with a recommendation. Your answer is written into the issue as the new scope.
  5. Nothing found along the way is lost. archon-discoveries reads what runs noticed outside their task and files it, tracks it on an existing issue, or drops it.

Archon builds Archon: of the 524 pull requests merged into this repository between 1 and 19 October 2026, Archon runs built 363.

You start the queues by hand or bind them to a schedule or issue events with a trigger. The pack binds nothing by default. The pack reaches GitHub through the forge plugin (archon plugin add coleam00/Archon/plugins/forge-github); see the forge path. The SDLC factory introduces it and links its setup guide, and SDLC pack workflows describes every workflow in it.

Build any factory

Workflows are not tied to code. A node can be an agent prompt, a bash command, a script, a loop, a wait for a person or a child workflow, so any process with steps, checks and decisions fits: content production, research, operations, support. Write it as YAML, keep its commands and scripts beside it, and share it as a pack.

A reliable core, extensible at the seams

The core stays small: the workflow engine, isolation, durable state, the attention queue and an audit trail. Everything that talks to the outside world plugs in through a published contract, and you can build your own plugin for any of them:

Plugin kind What it adds Maintained here
Workflow pack Workflows, commands and scripts sdlc
Provider An agent runtime Claude Code, Codex, Pi
Forge A code host GitHub
Chat A conversation surface Slack

GitHub is the registry: publish in your own repository and install with archon plugin add owner/repo. See Publish a plugin and the plugin index.

Quickstart

  1. Install Claude Code and sign in, or install Codex.

  2. Install Archon. The installer asks which providers to add:

    curl -fsSL https://archon.diy/install | bash        # macOS / Linux
    irm https://archon.diy/install.ps1 | iex             # Windows (PowerShell)
    brew install coleam00/archon/archon                 # Homebrew, then: archon setup
  3. Run a workflow in any git repository:

    cd your-project
    archon workflow list
    archon workflow run archon-investigate "Why does the login test fail?"
  4. Watch runs and answer their questions in the web console with archon serve, or from the terminal with archon workflow attention.

To let your coding agent drive Archon for you, run archon skill add in your project, then ask it to "use archon to fix issue #42".

Other installs (from source, Docker, servers), provider setup and the Claude Code binary path are in the installation guide. The quick start shows how to write a brief a run can deliver against.

Connect a platform

The CLI and web console work out of the box. Connect a chat platform or forge to start and follow runs from there:

Platform Guide
Slack Slack guide
Telegram Telegram guide
GitHub webhooks GitHub guide
Discord Discord guide

Documentation

Full documentation is at archon.diy/docs.

Topic Description
Quickstart Install and first run
Workflow language Write your own YAML workflows
Operate runs Watch runs, answer the ones that need you, read results
CLI reference Every command and flag
Configuration Config options, model tiers and aliases, env vars
AI assistants Claude Code, Codex and Pi setup
Deployment Docker, VPS and production setup
Architecture Packages and boundaries
Troubleshooting Common issues and fixes

For AI tools: point your LLM at /llms.txt for an index of the docs, /llms-full.txt for all of them in one file, or /llms-small.txt for a condensed version.

Previous version

Looking for the original Python-based Archon (task management and RAG)? It is preserved on the archive/v1-task-management-rag branch.

Telemetry

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 (at most once a day each for the CLI and the server, with the store it uses: files, sqlite or postgresql; archon serve reports as the server, and a detached run's worker process is counted by the command that started it), 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, and again for each resumed segment), workflow_completed / workflow_failed / workflow_cancelled (sent once when a run's final status is saved, whichever path ended it), 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. The discovery source (bundled/global/project) is sent alongside.

  • Run shape & outcome: platform (cli/web/slack/…), provider and model ids, node count, how many nodes of each type, graph depth and widest fan-out, how many distinct commands are referenced, the total inline prompt size as a bucket (none/lt_1k/1k_5k/5k_20k/gte_20k characters), which node types and features are used (loop/approval/script/bash, structured output, persisted sessions, MCP, skills, fresh-context loops), whether the run is interactive, isolated in a worktree, a resume, or a child of another run, the outcome, duration (from the run's first start to its end, including approval and wait time), a categorical exit or cancel reason, and a fixed-enum failure class recorded where the first failed node failed (fatal/transient/unknown for provider errors; timeout, exec_failed, output_contract, max_iterations, child_failed, cancelled, config for engine-detected causes; never raw error text) plus that node's type.

  • Run reference: run_ref, a one-way hash of the install UUID and the run id, so a run's start, resumes and outcome can be joined. The run id itself is never sent.

  • Bundled ancestry: when one of your workflows is a copy of a bundled workflow, the bundled workflow's name and whether the copy is identical or modified (derived_from, derived_similarity). Only the bundled name is sent; nothing about your copy's name, node ids or prompts.

  • Workflow no match: workflow_no_match, a count of agent decisions that no available workflow fits, with only the transport (native_tool or cli).

  • Chat activity: one event per direct-chat AI turn with platform, provider, model, duration, and completed/failed; a turn whose provider errors out mid-turn counts as failed. Message content, prompts, and conversation ids are never sent.

  • Aggregate usage: provider-reported gross input, output, optional cache-read/cache-write token totals (with a flag when those totals are a floor), and cost (USD) per workflow run across all of its resumed segments (a parent run's total includes its child runs' spend, so sum spend over runs that are not children), plus direct-chat usage and total loop iterations. Numeric totals only, never the content the tokens represent.

  • Machine context: OS, architecture, Archon version, runtime, whether it's a binary build, the install channel (binary/docker/source), the short commit of the running build when known, whether stderr is a terminal, and a CI flag.

  • Store kind: where runs are kept, files, sqlite or postgresql, sent on archon_started by the CLI and the server.

  • Deployment shape (server only): which adapters are enabled (booleans), how many chat plugins it hosts (a count; plugin names are not sent), 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_HOME/telemetry-id (~/.archon/telemetry-id by default, /.archon/telemetry-id in Docker). Nothing else.

  • A schema_version number on every event, bumped whenever this list changes.

Workflow runs and direct-chat turns both report optional cache_read_tokens, cache_write_tokens, and true-only cache_partial. An unreported axis is absent; a reported zero stays zero. When cache_partial is true, cache totals are floors because some contributing results did not report cache usage. When telemetry is enabled and stderr is a terminal, the updated first-run notice appears once again for existing installs to disclose direct-chat cache capture. Headless installs show no notice; see telemetry settings for capture details and opt-outs.

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.

Shutdown gives pending telemetry a 75 ms flush window, then cancels outstanding requests. Slow or unreachable ingestion can lose events; it does not hold up command exit. Far from the ingest host (for example, about 250 ms TLS handshake from Europe to the default US host), events from short commands like --help are usually dropped; longer commands flush in the background while they run.

Self-host PostHog or use a different project by setting POSTHOG_API_KEY and POSTHOG_HOST.

Contributing

Contributions welcome. See the open issues for things to work on, and read CONTRIBUTING.md before opening a pull request.

Star history

Star History Chart

License

MIT

View on GitHub

Recent activity

commits and pull requests

Releases and announcements

30 total
  1. Archon CLI v0.14.0v0.14.0Nov 7, 20263.2K downloads

    The SDLC pack reaches GitHub only through the forge plugin, packs can declare settings, and `archon metrics` measures the factory. ### Breaking - The bundled SDLC pack reaches the forge only through `archon forge` and an installed forge plugin; the pack's `gh` path is gone and nothing falls back to `gh`. Install the plugin with `archon plugin add coleam00/Archon/plugins/forge-github`. Delivery and the merge queue need plugin v0.13.0 or later, and their forge checks refuse a plugin missing an operation they need; the metrics workflows and the build queue's lookup of a dead round's pull request need this release's plugin, for `pr.view` timestamps, `pr.view` of a head in any state, `pr.files` and `repo.file`. Your existing `gh auth login`, `GH_TOKEN` or `GITHUB_TOKEN` is still the credential, and a leftover `ARCHON_SDLC_FORGE` is ignored. A pack run in a container refuses at its forge check, since a container has no host command. The merge queue's own-PR enrollment notes that the forge cannot list a maintainer's pull requests and continues with the queue's other work. A red default branch is now always raised to a maintainer instead of rerun, because the forge reruns checks only on

  2. Archon CLI v0.13.2v0.13.2Oct 29, 20265.1K downloads

    Upgrading from 0.13.0 with providers installed works in one command again. ### Fixed - `archon provider add` and `archon plugin update` now replace a maintained provider installed by 0.13.0, whose receipt declares the older plugin protocol, including several providers in one command. On 0.13.1 they refused, saying the executable "may belong to a plugin whose receipt cannot be read", so the documented upgrade step failed and workflows that used that provider stopped loading. A file with an unreadable receipt or a different plugin ID is still refused, and the existing repair for a provider's own malformed receipt is unchanged. (#5287) - `archon isolation cleanup` help and the CLI reference describe the container threshold as age since the environment was created, which is what cleanup uses. (#5283) - The source-install guide points to the Bun version the repository pins instead of `>= 1.0.0`. (#5275) ## Installation ### Quick Install (Recommended) **macOS / Linux** ```bash curl -fsSL https://archon.diy/install | bash ``` **Windows (PowerShell)** ```powershell irm https://archon.diy/install.ps1 | iex ``` **Homebrew (macOS / Linux)** ```bash brew install coleam00/archon/archon

  3. Archon CLI v0.13.1v0.13.1Oct 29, 2026327 downloads

    Workflow names must match exactly, provider plugins move to protocol 3, and a batch of fixes for Postgres boots, Codex runs, cleanup and cost accounting. > **Upgrading from 0.13.0 with providers installed:** use [v0.13.2](https://github.com/coleam00/Archon/releases/tag/v0.13.2). In 0.13.1, `archon provider add` refused to replace providers installed by 0.13.0 (#5272). 0.13.2 fixes it, and `archon provider add claude codex pi` works in one step. ### Breaking - The provider plugin protocol is now 3. After upgrading, run `archon provider add` again for each provider you use. Third-party provider plugins must rebuild against protocol 3. A provider installed by 0.13.0 is reported as unavailable, naming its protocol, this Archon's protocol and the command that fixes it, instead of failing workflow discovery with `Invalid input`. (#5252, #5270) - Workflow names resolve by exact name everywhere: `archon workflow run`, the chat `/workflow` command, the run API, `workflow:` children, `include:`, composed fan-outs and resume. `archon workflow run review` no longer selects `archon-review`; the error suggests the closest names instead. A `workflow:` or `include:` target that is not an exact

  4. Archon CLI v0.13.0v0.13.0Oct 28, 202610.9K downloads

    Slack runs only as a plugin. Declared MCP servers and misplaced node keys fail before any tokens are spent. Completed runs clean up their own worktrees and scratch space. The SDLC merge queue merges clean PRs at once, and queue answers continue without waiting for the next pass. ### Breaking - The server no longer contains a Slack adapter; Slack runs only as the `chat-slack` plugin. Docker images ship a verified release and install it offline on startup when `SLACK_BOT_TOKEN` is set, including on existing volumes, and boot logs explain what was installed; valid installed versions are kept. Removing the plugin while tokens are still set reinstalls it on restart, so remove the tokens from every env source too to keep Slack off. Outside Docker, run `archon plugin add coleam00/Archon/plugins/chat-slack` and restart. A token without an installed plugin logs `chat.bundled_adapter_retired` with the Docker guidance and the manual command. The Slack app, `SLACK_BOT_TOKEN`, `SLACK_APP_TOKEN`, `SLACK_ALLOWED_USER_IDS`, `SLACK_STREAMING_MODE`, and existing Slack conversations, linked identities and workspaces are unchanged. In Slack, `/archon connect github` now points to the Web UI or `arc

  5. Archon CLI v0.12.1v0.12.1Oct 17, 20269.8K downloads

    Release binaries no longer hand a target repository's `.env` to providers. ### Security - Release binaries, including the Claude, Codex and Pi provider plugins and the forge-github and chat-slack plugins, no longer load `.env` or `bunfig.toml` from their working directory. In v0.12.0 a provider started in a target repository loaded that repository's `.env` and undid Archon's strip of it, so a project's `ANTHROPIC_API_KEY` could reach Claude and override your subscription. Source installs were not affected. If you ran v0.12.0 in a repository whose `.env` holds provider keys, upgrade, then run `archon provider add` again for each provider you use. (#4426, #4427) ## Installation ### Quick Install (Recommended) **macOS / Linux** ```bash curl -fsSL https://archon.diy/install | bash ``` **Windows (PowerShell)** ```powershell irm https://archon.diy/install.ps1 | iex ``` **Homebrew (macOS / Linux)** ```bash brew install coleam00/archon/archon ``` **Docker** ```bash docker run --rm -v "$PWD:/workspace" ghcr.io/coleam00/archon:latest workflow list ``` ### Manual Installation **macOS (Apple Silicon)** ```bash curl -fsSL https://github.com/coleam00/Archon/releases/latest/download/a

Code frequency

additions and deletions
+435.5K-435.5KWeek of 2025-11-16: +3 linesWeek of 2025-11-16: -3 linesWeek of 2025-11-23: +118 linesWeek of 2025-11-23: -30 linesWeek of 2025-11-30: +33,607 linesWeek of 2025-11-30: -11,097 linesWeek of 2025-12-07: +5,084 linesWeek of 2025-12-07: -85 linesWeek of 2025-12-14: +45,584 linesWeek of 2025-12-14: -18,454 linesWeek of 2025-12-21: +0 linesWeek of 2025-12-21: -0 linesWeek of 2025-12-28: +19,292 linesWeek of 2025-12-28: -5,364 linesWeek of 2026-01-04: +6,245 linesWeek of 2026-01-04: -199 linesWeek of 2026-01-11: +35,025 linesWeek of 2026-01-11: -8,230 linesWeek of 2026-01-18: +76,253 linesWeek of 2026-01-18: -42,177 linesWeek of 2026-01-25: +29,839 linesWeek of 2026-01-25: -36,094 linesWeek of 2026-02-01: +3,231 linesWeek of 2026-02-01: -2,106 linesWeek of 2026-02-08: +0 linesWeek of 2026-02-08: -0 linesWeek of 2026-02-15: +35,601 linesWeek of 2026-02-15: -87,757 linesWeek of 2026-02-22: +37,649 linesWeek of 2026-02-22: -28,712 linesWeek of 2026-03-01: +9,384 linesWeek of 2026-03-01: -15,112 linesWeek of 2026-03-08: +28,430 linesWeek of 2026-03-08: -3,524 linesWeek of 2026-03-15: +19,921 linesWeek of 2026-03-15: -5,514 linesWeek of 2026-03-22: +24,811 linesWeek of 2026-03-22: -20,025 linesWeek of 2026-03-29: +28,088 linesWeek of 2026-03-29: -5,671 linesWeek of 2026-04-05: +35,045 linesWeek of 2026-04-05: -27,617 linesWeek of 2026-04-12: +22,540 linesWeek of 2026-04-12: -13,412 linesWeek of 2026-04-19: +10,986 linesWeek of 2026-04-19: -1,118 linesWeek of 2026-04-26: +20,841 linesWeek of 2026-04-26: -15,144 linesWeek of 2026-05-03: +4,439 linesWeek of 2026-05-03: -356 linesWeek of 2026-05-10: +18,476 linesWeek of 2026-05-10: -3,110 linesWeek of 2026-05-17: +2,345 linesWeek of 2026-05-17: -515 linesWeek of 2026-05-24: +57,529 linesWeek of 2026-05-24: -3,008 linesWeek of 2026-05-31: +20,266 linesWeek of 2026-05-31: -1,222 linesWeek of 2026-06-07: +24,877 linesWeek of 2026-06-07: -2,706 linesWeek of 2026-06-14: +317 linesWeek of 2026-06-14: -12 linesWeek of 2026-06-21: +68,340 linesWeek of 2026-06-21: -5,523 linesWeek of 2026-06-28: +161 linesWeek of 2026-06-28: -23 linesWeek of 2026-07-05: +113 linesWeek of 2026-07-05: -0 linesWeek of 2026-07-12: +31,120 linesWeek of 2026-07-12: -2,863 linesWeek of 2026-07-19: +58,914 linesWeek of 2026-07-19: -7,785 linesWeek of 2026-07-26: +4,736 linesWeek of 2026-07-26: -574 linesWeek of 2026-08-02: +49,041 linesWeek of 2026-08-02: -4,637 linesWeek of 2026-08-09: +9,012 linesWeek of 2026-08-09: -2,486 linesWeek of 2026-08-16: +70,946 linesWeek of 2026-08-16: -16,226 linesWeek of 2026-08-23: +72,172 linesWeek of 2026-08-23: -28,132 linesWeek of 2026-08-30: +182,048 linesWeek of 2026-08-30: -76,911 linesWeek of 2026-09-06: +17,651 linesWeek of 2026-09-06: -9,938 linesWeek of 2026-09-13: +195 linesWeek of 2026-09-13: -221 linesWeek of 2026-09-20: +176,729 linesWeek of 2026-09-20: -97,589 linesWeek of 2026-09-27: +31,629 linesWeek of 2026-09-27: -40,302 linesWeek of 2026-10-04: +91,410 linesWeek of 2026-10-04: -27,067 linesWeek of 2026-10-11: +435,507 linesWeek of 2026-10-11: -156,433 linesWeek of 2026-10-18: +427,408 linesWeek of 2026-10-18: -371,080 linesWeek of 2026-10-25: +390,458 linesWeek of 2026-10-25: -298,422 linesWeek of 2026-11-01: +58,334 linesWeek of 2026-11-01: -20,847 linesWeek of 2026-11-08: +48,637 linesWeek of 2026-11-08: -22,814 linesNov 16, 2025Nov 8, 2026
+2.9M lines added, -1.5M removed over the last year.

Commits per week

last 52 weeks
4180Week of 2025-11-16: 1 commitsWeek of 2025-11-23: 3 commitsWeek of 2025-11-30: 80 commitsWeek of 2025-12-07: 9 commitsWeek of 2025-12-14: 31 commitsWeek of 2025-12-21: 0 commitsWeek of 2025-12-28: 28 commitsWeek of 2026-01-04: 11 commitsWeek of 2026-01-11: 56 commitsWeek of 2026-01-18: 58 commitsWeek of 2026-01-25: 31 commitsWeek of 2026-02-01: 5 commitsWeek of 2026-02-08: 0 commitsWeek of 2026-02-15: 67 commitsWeek of 2026-02-22: 28 commitsWeek of 2026-03-01: 43 commitsWeek of 2026-03-08: 79 commitsWeek of 2026-03-15: 74 commitsWeek of 2026-03-22: 72 commitsWeek of 2026-03-29: 143 commitsWeek of 2026-04-05: 186 commitsWeek of 2026-04-12: 53 commitsWeek of 2026-04-19: 47 commitsWeek of 2026-04-26: 39 commitsWeek of 2026-05-03: 14 commitsWeek of 2026-05-10: 44 commitsWeek of 2026-05-17: 20 commitsWeek of 2026-05-24: 34 commitsWeek of 2026-05-31: 29 commitsWeek of 2026-06-07: 31 commitsWeek of 2026-06-14: 2 commitsWeek of 2026-06-21: 19 commitsWeek of 2026-06-28: 5 commitsWeek of 2026-07-05: 4 commitsWeek of 2026-07-12: 61 commitsWeek of 2026-07-19: 57 commitsWeek of 2026-07-26: 27 commitsWeek of 2026-08-02: 53 commitsWeek of 2026-08-09: 15 commitsWeek of 2026-08-16: 272 commitsWeek of 2026-08-23: 418 commitsWeek of 2026-08-30: 232 commitsWeek of 2026-09-06: 93 commitsWeek of 2026-09-13: 2 commitsWeek of 2026-09-20: 93 commitsWeek of 2026-09-27: 45 commitsWeek of 2026-10-04: 161 commitsWeek of 2026-10-11: 253 commitsWeek of 2026-10-18: 392 commitsWeek of 2026-10-25: 70 commitsWeek of 2026-11-01: 50 commitsWeek of 2026-11-08: 122 commitsNov 16, 2025Nov 8, 2026
3.8K commits in the last 52 weeks.

When work happens

weekday and hour
SunMonTueWedThuFriSat036912151821Sun 0:00 — 19 commitsSun 1:00 — 15 commitsSun 2:00 — 12 commitsSun 3:00 — 6 commitsSun 4:00 — 6 commitsSun 5:00 — 5 commitsSun 6:00 — 3 commitsSun 7:00 — 10 commitsSun 8:00 — 12 commitsSun 9:00 — 8 commitsSun 10:00 — 19 commitsSun 11:00 — 7 commitsSun 12:00 — 19 commitsSun 13:00 — 11 commitsSun 14:00 — 12 commitsSun 15:00 — 6 commitsSun 16:00 — 9 commitsSun 17:00 — 6 commitsSun 18:00 — 12 commitsSun 19:00 — 7 commitsSun 20:00 — 12 commitsSun 21:00 — 11 commitsSun 22:00 — 9 commitsSun 23:00 — 5 commitsMon 0:00 — 1 commitsMon 1:00 — 3 commitsMon 2:00 — 2 commitsMon 3:00 — 2 commitsMon 4:00 — 0 commitsMon 5:00 — 2 commitsMon 6:00 — 1 commitsMon 7:00 — 3 commitsMon 8:00 — 9 commitsMon 9:00 — 22 commitsMon 10:00 — 36 commitsMon 11:00 — 62 commitsMon 12:00 — 37 commitsMon 13:00 — 35 commitsMon 14:00 — 53 commitsMon 15:00 — 68 commitsMon 16:00 — 52 commitsMon 17:00 — 34 commitsMon 18:00 — 43 commitsMon 19:00 — 52 commitsMon 20:00 — 40 commitsMon 21:00 — 54 commitsMon 22:00 — 41 commitsMon 23:00 — 32 commitsTue 0:00 — 33 commitsTue 1:00 — 24 commitsTue 2:00 — 12 commitsTue 3:00 — 13 commitsTue 4:00 — 4 commitsTue 5:00 — 2 commitsTue 6:00 — 7 commitsTue 7:00 — 18 commitsTue 8:00 — 35 commitsTue 9:00 — 41 commitsTue 10:00 — 31 commitsTue 11:00 — 28 commitsTue 12:00 — 61 commitsTue 13:00 — 65 commitsTue 14:00 — 57 commitsTue 15:00 — 46 commitsTue 16:00 — 29 commitsTue 17:00 — 24 commitsTue 18:00 — 23 commitsTue 19:00 — 17 commitsTue 20:00 — 10 commitsTue 21:00 — 6 commitsTue 22:00 — 8 commitsTue 23:00 — 6 commitsWed 0:00 — 12 commitsWed 1:00 — 3 commitsWed 2:00 — 4 commitsWed 3:00 — 3 commitsWed 4:00 — 5 commitsWed 5:00 — 6 commitsWed 6:00 — 8 commitsWed 7:00 — 9 commitsWed 8:00 — 20 commitsWed 9:00 — 31 commitsWed 10:00 — 34 commitsWed 11:00 — 64 commitsWed 12:00 — 59 commitsWed 13:00 — 35 commitsWed 14:00 — 73 commitsWed 15:00 — 59 commitsWed 16:00 — 44 commitsWed 17:00 — 38 commitsWed 18:00 — 30 commitsWed 19:00 — 29 commitsWed 20:00 — 16 commitsWed 21:00 — 34 commitsWed 22:00 — 40 commitsWed 23:00 — 21 commitsThu 0:00 — 23 commitsThu 1:00 — 11 commitsThu 2:00 — 9 commitsThu 3:00 — 10 commitsThu 4:00 — 9 commitsThu 5:00 — 2 commitsThu 6:00 — 3 commitsThu 7:00 — 22 commitsThu 8:00 — 29 commitsThu 9:00 — 38 commitsThu 10:00 — 40 commitsThu 11:00 — 54 commitsThu 12:00 — 51 commitsThu 13:00 — 38 commitsThu 14:00 — 42 commitsThu 15:00 — 40 commitsThu 16:00 — 51 commitsThu 17:00 — 35 commitsThu 18:00 — 26 commitsThu 19:00 — 26 commitsThu 20:00 — 16 commitsThu 21:00 — 27 commitsThu 22:00 — 17 commitsThu 23:00 — 23 commitsFri 0:00 — 16 commitsFri 1:00 — 9 commitsFri 2:00 — 8 commitsFri 3:00 — 6 commitsFri 4:00 — 4 commitsFri 5:00 — 0 commitsFri 6:00 — 5 commitsFri 7:00 — 2 commitsFri 8:00 — 14 commitsFri 9:00 — 39 commitsFri 10:00 — 50 commitsFri 11:00 — 69 commitsFri 12:00 — 56 commitsFri 13:00 — 61 commitsFri 14:00 — 42 commitsFri 15:00 — 65 commitsFri 16:00 — 43 commitsFri 17:00 — 53 commitsFri 18:00 — 27 commitsFri 19:00 — 14 commitsFri 20:00 — 14 commitsFri 21:00 — 15 commitsFri 22:00 — 18 commitsFri 23:00 — 19 commitsSat 0:00 — 12 commitsSat 1:00 — 6 commitsSat 2:00 — 9 commitsSat 3:00 — 5 commitsSat 4:00 — 3 commitsSat 5:00 — 4 commitsSat 6:00 — 7 commitsSat 7:00 — 9 commitsSat 8:00 — 12 commitsSat 9:00 — 14 commitsSat 10:00 — 13 commitsSat 11:00 — 14 commitsSat 12:00 — 8 commitsSat 13:00 — 14 commitsSat 14:00 — 22 commitsSat 15:00 — 24 commitsSat 16:00 — 20 commitsSat 17:00 — 22 commitsSat 18:00 — 10 commitsSat 19:00 — 10 commitsSat 20:00 — 12 commitsSat 21:00 — 22 commitsSat 22:00 — 15 commitsSat 23:00 — 21 commits
Commit volume by weekday and hour (UTC). Larger dots mean more commits.

Who is committing

last 52 weeks
Maintainer commits398 (9%)
Community commits3,986 (91%)

4,384 commits in total over the last year.

DateListRankStars gained
Apr 11, 2026daily#21+241
  • morluto/rea

    Reverse engineer anything with agents, from app behavior down to native binaries.

    471.6K stars · TypeScript

  • freeCodeCamp/freeCodeCamp

    freeCodeCamp.org's open-source codebase and curriculum. Learn math, programming, and computer science for free.

    459.4K stars · TypeScript

  • openclaw/openclaw

    The AI that really does things. Any OS. Any Platform. The lobster way. 🦞

    394.9K stars · TypeScript

  • obra/superpowers

    An agentic skills framework & software development methodology that works.

    322.9K stars · Shell

  • affaan-m/ECC

    The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

    307.9K stars · JavaScript

  • NousResearch/hermes-agent

    The agent that grows with you

    265K stars · Python