Code in your coding agent,
Review in Code Terrier.

Up to three reviewers, chosen from

Claude·GPT·Gemini·DeepSeek·Kimi·Qwen·GLM·Grok…

Reviewers run in parallel. Duplicate findings are merged, then results pass through the verification stage before publication.

— tokens spent on reviews ·— review runs.

Agents write more code than anyone can read. Code Terrier sends each review to up to three models at once, consolidates their findings, and checks the result before publication. Comments land on the exact line, and a new commit triggers the next review.

Install on GitHubAuto mode reviews new PRs and updates by default. Change the trigger mode any time.

Need an on-demand pass? Comment @code-terrier review on any pull request.
Bring an Anthropic key or an OpenAI-compatible endpoint, or run on the shared pool with no key at all.

Parallel, then checked

Up to three reviewers run together. Near-duplicates are consolidated, then the verification stage checks line legality.

Inline, and categorized

Security, Bug, Flag and Slop findings anchored to the exact line — not a wall of prose at the bottom of the PR.

Fixes you can commit

Findings arrive as GitHub suggestions, plus a non-blocking commit status on every head commit.

Push and it re-checks

A new commit starts another review. Prior human comments are carried forward as bounded, untrusted context.

Bring your own key