#2727th of 43 in Code review and testing
crit
Browser UI for commenting on a coding agent's plans, diffs and running apps
- Stars
- 1.3k
- License
- MIT
- Last commit
- Nov 2026
- Last release
- Oct 2026
- Language
- Go
185 on 21 Apr 20261,301 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Crit is a single Go binary that opens a local browser review UI for markdown plans, git diffs, static HTML files, or a proxied dev server. You comment on lines or ranges, and the agent receives them through a /crit slash command or `crit comment`. It also syncs comments with GitHub PRs and GitLab MRs, and can share reviews through crit.md.
Who it is for: Developers who review coding-agent output and send line-level feedback
Strengths
- Runs locally as one binary; install via brew, Go, Nix, AUR or release download
- Separate review modes for markdown, git diffs, static HTML and a live proxied app
- Two-way comment sync with GitHub PRs and GitLab MRs, including self-managed GitLab
- Integrates with Claude Code, Cursor, Copilot, Codex, Aider, Cline and others
Weaknesses
- Live mode needs manual cookie forwarding when the app uses host-scoped session logins
- Story mode run from the terminal costs extra LLM spend, about $1 to $1.40 per complex PR
- Send-to-agent is experimental and needs agent_cmd set in global config
- Sharing relies on crit.md or a separately hosted crit-web instance
What it needs
- no GPU
- Needs git, gh (GitHub PR sync), glab (GitLab MR sync), a coding agent CLI
What changed
- v0.23.1 ↗ (opens in a new tab)Security fix
“fix: sanitize raw HTML in reviewed Markdown documents (#1088) by @tomasz-tomczyk in https://github.com/tomasz-tomczyk/crit/pull/1088”
From the release notes. No flag means the note does not say so, not that the upgrade is safe.
Also in Code review and testing
See all 43| Rank | Project | Score |
|---|---|---|
| 1 | playwrightCross-browser automation and end-to-end test framework for Chromium, Firefox and WebKit | 94 out of 100 |
| 2 | nxMonorepo build system with task caching, affected-only runs and CI integration | 93 out of 100 |
| 3 | open-code-reviewGo CLI that reviews Git diffs with an LLM agent and line-level comments | 92 out of 100 |
| #4 | bendDependent-typed language where AI-written code must prove rules in LAWS.bend | 88 out of 100 |
| #5 | maestroYAML-based UI and end-to-end test framework for Android, iOS and web | 88 out of 100 |