Crit

Crit is a local code review tool for AI agents that provides a browser-based interface for inline comments, diff visualization, and iterative feedback.

Crit provides a browser-based review surface for AI agent outputs, including code, plans, and documentation. It runs locally as a single binary and enables users to comment on specific lines or sections within generated files. The tool offers five review modes, including branch and pull request diffs, rendered Markdown plans, live previews of running applications, and static HTML rendering. Users can track changes across iterations with round-to-round diffs and persistent comment threads. It integrates with various coding agents such as Claude Code, Cursor, Copilot, Aider, and Windsurf by reading structured review files.

Crit at a glance

Best for: Software engineer
Runs on: macOS, Windows, Linux
Pricing: Free
Released: March 2026
Category: AI coding tool
Website: crit.md

Key features

Line-specific inline commenting
Round-to-round diff visualization
Markdown document rendering
Syntax-highlighted code diffs
Local proxy for live running applications
Static HTML iframe previews
Persistent feedback threads across iterations

Use it for

Reviewing complex AI-generated development plans
Iterating on code changes via local browser interface
Providing precise feedback on generated frontend UI elements
Managing multi-file diffs during agentic coding tasks

Companions

Tools that articles about Crit recommend using with it, each with its job.

Claude Code — Terminal-first agent that handles multi-hour refactors and migrations
Linear — Reviews check the change against the issue it came from.
Jira — Plans and reviews start from the Jira ticket.
Claude — Strong writing and coding help, with projects, memory and connectors
Context7 — Provides up-to-date documentation for AI agents and code editors.
Ollama — Run local models at zero marginal cost, with code kept on your machine.

Alternatives to Crit

jevgrep — Reduces coding agent costs by providing targeted, relevant repository context.
agent.reviews — Real tool reviews written directly by coding agents after task completion.
pstack — Improves AI coding agent outcomes with rigorous workflows.
CodeRabbit — Most-installed AI PR reviewer, built to check code from coding agents
OpenCode — Works with 75+ model providers, local models, and existing subscriptions
Code Review Graph — Provides a median 63x context reduction while keeping all code processing local.
Reviewer Agent — It uses a separate AI model to review code and prevent premature agent stopping.
Review — Reviews code locally with optional AI and complete privacy.
Git AI — It moves work to the server and handles concurrent tasks without standard Git bottlenecks.
Reviu — Review agent diffs, send fixes back, and clean branches with real Git before opening PRs.
Agentation — It translates clicks into CSS selectors and source paths for agents.
OpenClaude — Connects one terminal interface to over 200 different AI models.

All Crit alternatives