OpenSwarm

Agentic CI/CD gate — review, fix, re-review, and deterministic verification for pull requests and local changes
💬 Help shape OpenSwarm. Share feature ideas, vote on the roadmap, and ask questions in GitHub Discussions. The roadmap is built in the open — your feedback decides what ships next.

OpenSwarm is an agentic CI/CD gate for the change path that matters: it reviews a committed or working-tree diff, can group and fix confirmed findings in isolated sandboxes, re-reviews the result, then requires deterministic repository checks before it publishes a PR. It runs with OpenAI Codex/GPT, any OpenRouter model, local open-source models (Ollama, LM Studio), or Claude Code (claude -p, opt-in) — with cost-aware routing measured on an L0–L6 benchmark ladder.

Use it locally before a commit or from the included GitHub Action on a pull request. The Linear-backed autonomous daemon, notifications, and long-term repository memory remain available as an optional orchestration layer; they are not required to use the merge gate.

Verified on real GitHub issues: the agentic harness solves SWE-bench Lite instances graded by the official harness. Hybrid mode — a frontier model diagnoses read-only, a lightweight model implements with a verification loop — resolved 3/3 attempted instances that every single lightweight model had failed, at a fraction of frontier-only cost. Workers also learn each repository over time: task outcomes are stored as per-repo knowledge and recalled into future prompts. (benchmark rubric & results)

Sponsors

OpenSwarm is proudly supported by Atlas Cloud — an enterprise AI infrastructure platform serving fast, stable LLM, image, and video APIs (partnered with OpenRouter and SGLang).

As an official provider sponsor, Atlas Cloud ships as the built-in atlascloud…