CodeChat: review your AI agent's code changes like a local PR via MCP
lemire · x · 2026-10-03
- CodeChat (open source, alexmx/codechat) adds human-in-the-loop code review for AI coding agents: a browser UI shows syntax-highlighted diffs (unified or split) where you leave inline comments, with real-time file-change updates and dark/light themes.
- After you submit, the agent reads your comments, makes fixes, and replies—a tight feedback loop. Sessions can be resumed by ID.
- It connects to any AI coding agent as an MCP server, reviews uncommitted changes in any git repo, and installs via brew install alexmx/tools/codechat.
- Author lemire notes the feedback is tied to file and line, making the loop elegant in practice.
Related event: CodeChat Lets Humans Review AI-Agent Code Like Pull Requests(2 posts)→
More from coding & agent
- New TLAPS-Bench blog: formally proving correctness of real-world system specs with TLA+ — tianyin_xu · 2026-11-19
- Rivet's lesson: JEV doesn't reason—split severity classification into tiny yes/no prompts — yawnxyz · 2026-11-19
- 16x Microsoft MVP demos a native PowerShell agent built on Microsoft's Intelligent Terminal — dfinke · 2026-11-19
- Musk: Treat Grok Bot like a really smart employee, says most users underuse it — elonmusk · 2026-11-19
- Eve agent tool cuts build time 8x to 6.9s by reusing compiler module graph — evilrabbit_ · 2026-11-19
- Dev shares NL-driven testing UI: 'the best interface is chat' — KlausCodes · 2026-11-19