The idea
PeerFoil is an open-source workflow for AI coding with independent AI code review. It helps solo developers use different AI model families to plan, create, test, and review their projects together. Agents check your work and each other's contributions to catch mistakes a single model might miss.
How the review works
Work starts with a reviewed architecture and a plan you approve. The agents produce and validate the work, and a fresh reviewer from another model family checks it against your requirements and the results of the project tests. Accepted repairs go through the checks and a fresh review again. PeerFoil pauses for your decision when it is blocked or when review limits are reached. Authorship stays separate from approval: the author never approves its own work.
Status
PeerFoil has not been released yet. The first release will connect Claude Code and Codex in a guided multi-agent workflow. Software development comes first, with project packs planned for documentation, business plans, and research reports. The repository documents the workflow, the architecture, and the implementation plan.