Back to directory

OpenFactory

An autonomous software factory that turns tickets from a project board into reviewed pull requests, orchestrating coding agents such as Claude Code, Codex, Kimi or OpenCode under a merge policy the team chooses.

OpenFactory

OpenFactory takes tickets from a project board and returns pull requests that have been planned, implemented, validated against the project's own test suite, independently reviewed, and merged under a policy the team sets. It does not run its own model; instead it orchestrates coding agents already in use, including Claude Code, Codex, Kimi and OpenCode, behind one adapter contract, and it runs on the team's own machines and credentials rather than as a hosted service.

A manifest declares the merge policy, a quality floor and a promotion chain, and a project with no declared test command is held rather than marked as passing. Before work starts, a proving step runs the project's own setup and validation commands inside the real sandbox, so a misconfigured environment is reported as a finding rather than spent on a wasted agent run. Reviews can run on a different engine from the one that wrote the change, and a blocked job is parked with options for a human instead of waiting silently.

Tracker, forge, continuous-integration observer, notifier, coding agent and sandbox are each separate, swappable adapters, with support for GitHub Issues and Projects, Jira, and Azure DevOps.

More in Coding agents

See all 793
  • The City

    github.com

    A native macOS app that shows Claude Code runs as a city, with each project as a building, each team as a floor of robots, and every animation driven by a real event from the claude CLI's stream.

  • rig

    tryrig.ai

    A small, single-binary agent runtime that points at any OpenAI-compatible model, local or hosted, reads and edits a repository's code, runs its tests and remembers what it learned, with a loop implemented in a few hundred lines.

  • Jauvex

    jauvex.reindent.com

    An Electron desktop app that puts Claude Code, Codex and Grok coding-agent sessions side by side and lets you steer them by voice, with a small model handling fast routing decisions.