Built a Local AI Code Reviewer with Ollama | Private & Open Source 🚀

Описание и применение

Местный AI‑ревьюер, использующий Ollama и модель Qwen2.5‑Coder, автоматически проверяет PR‑ы, выявляя ошибки за 2 минуты, сохраняя конфиденциальность кода и экономя время.

Задача

Code reviews are essential but draining; reviewing every changed line of a PR is time‑consuming and can let issues slip through.

Результат

The reviewer posted a review in about 2 minutes, identified two real bugs, and eliminated the 15–20 minute manual first‑pass review.

Рабочий процесс

• Configure .env with OLLAMA_MODEL and GITHUB_TOKEN
• Run the Python script managed by uv
• Ollama serves the Qwen2.5‑Coder model via /api/chat in JSON mode
• GitHub REST API reads PR diffs and posts review comments
• Reviewer runs continuously while the developer works
• Developer reviews AI‑generated comments and focuses on design decisions

Доказательства

Local AI PR Reviewer does the first pass for you. It watches your chosen repos, reviews every new or updated PR with a local open-weight model on Ollama, and posts senior-engineer-style feedback: critical issues, why they matter, and suggested fixes.

Источник

I ran it on my own demo repo this week. On the note deletion and search PR, it posted a review in about 2 minutes without me opening a single file, and caught two real bugs: a missing useEffect cleanup and unhandled errors in deleteNote.

Источник

Reviews are generated by Qwen2.5-Coder, an open-weight coding model, running locally through Ollama.

Источник