Crit: Local-first, single-binary CLI for reviewing agent plans and diffs
Crit is a local-first review tool packaged as a single binary. It opens your file or code diff in a browser with a GitHub-inspired interface, lets you leave comments, then your agent acts on the feedback automatically. Repeat until satisfied — all before hitting GitHub.
Core loop: comment, agent updates, diff refreshes
Drag across a range of lines, leave comments, hit Finish Review. The agent picks up the feedback, edits the file, and Crit reloads with the updated diff. Previous comments stay visible; resolve only when you're satisfied. Works for both plans and code — same UI, beautifully rendered markdown with syntax highlighting for 190+ languages.
Install in one command
$ brew install crit $ go install github.com/tomasz-tomczyk/crit@latest $ nix profile install github:tomasz-tomczyk/crit # Windows: PS> iwr https://github.com/tomasz-tomczyk/crit/releases/latest/download/crit-windows-amd64.exe -OutFile crit.exe
Then run crit or crit plan.md. Pre-built binaries for ARM64, WSL also available.
Integrates with 11 agents
One-command setup for Claude Code, Cursor, Copilot, Codex, OpenCode, Gemini, Qwen, Hermes, Windsurf, Cline, Aider. Example:
$ claude plugin add tomasz-tomczyk/crit $ claude plugin install crit@crit $ crit install cursor $ crit install github-copilot $ crit install codex
See full setup docs for each agent.
Multi-round and concurrent reviews
Iterate over multiple rounds per file. Run several reviews in parallel without stepping on each other — useful when juggling multiple agents.
Optional sharing and self-hosting
Reviews stay local by default. One click generates a public link — no install, no login for viewers. You can self-host the share target (crit-web) for privacy. Without sharing, reviews auto-delete after 30 days of inactivity.
Small quality-of-life features
- Vim keybindings
- Git diffs (split & unified)
- Round-over-round diffs
- Mermaid diagrams
- Table of contents
- Dark & light themes
- Draft autosave
- Insert suggestions
Who it's for
Developers who frequently review AI-generated plans and code diffs and want a dedicated local UI to batch feedback and iterate without leaving their workflow.
📖 Read the full source: HN AI Agents
👀 See Also
OpenClaw React Client Update Adds Model Per Agent, CLI Tool, and Auto-Start
The open-source OpenClaw client has received a major update with four key features: model assignment per agent, automatic updates, a new CLI tool for management, and auto-start after system reboot.
Free Model Alert: Tencent Hy3 Available on OpenRouter for 2 Weeks — Try It Now
Tencent Hy3 is free on OpenRouter for 2 weeks. Use it in OpenClaw via openrouter/tencent/hy3:free. Full details from r/openclaw.
Open-source CLI uses Claude Haiku to automate Xero expense auditing
A developer has released an open-source Python CLI tool that uses Claude Haiku 4.5 to automate Xero expense auditing. The tool follows a 'deterministic code first, then AI to fill in the gaps' approach, keeping costs to a few cents per audit run.
Antigravity 2.0 Tops OpenSCAD Architectural 3D Benchmark – ModelRift Tests 6 LLMs on the Pantheon
ModelRift benchmarked 6 LLMs on building the Pantheon in OpenSCAD. Antigravity scored 4.5/5 in architectural quality, beating baseline Codex 5.5. Cursor 3.5 was fastest but weakest.