Back to directory

OpenSwarm

An agentic CI/CD gate that reviews a code diff, fixes confirmed findings in sandboxes, re-reviews the result, and requires passing repository checks before it opens a pull request.

OpenSwarm

OpenSwarm reviews a committed or working-tree diff, can group and fix confirmed findings in isolated sandboxes, re-reviews the fixed result, and then requires deterministic repository checks to pass before it publishes a pull request. It runs with OpenAI Codex or GPT, any OpenRouter model, local models through Ollama or LM Studio, or Claude Code, with cost-aware routing measured against a benchmark ladder.

It can be run locally before a commit, from a bundled GitHub Action on a pull request, or as an autonomous daemon that also integrates with Linear for issue tracking and stores per-repository task outcomes as long-term memory for future runs; that daemon and the memory layer are optional and not required to use the core review gate. It installs globally from npm.

More in Code quality

See all 94
  • Critic

    critic.run

    A code-change viewer, backed by Y Combinator, built for reviewing work written by coding agents, presenting a plain-language narrative of each change alongside the diff and a running conversation with the agent.

  • GitIntel

    hoangsonww.github.io

    An MCP server that computes git repository analytics such as hotspots, churn, temporal coupling, knowledge maps and risk scoring entirely from local commit history, for AI coding agents like Claude Code and Codex.

  • Axint

    axint.ai

    A verification layer for AI coding agents working on Apple projects: it runs real Xcode builds and tests against the Swift an agent wrote, reconciles static analysis findings against that evidence, and returns a signed proof with the exact repairs still needed.