LaReview
The Code Review
Workbench.
Turn code changes into a clear review plan and high-signal feedback, without comment spam. Works with your existing AI coding agent.
LICENSE: MIT / APACHE 2.0
BUILT WITH FUN
Not Another Bot.
Most AI tools are bots that post comment spam.
LaReview is a reviewer-first workbench. We help you understand the change, plan your review, and ship feedback that matters.
- Plan First vs Comment Dump
- Flow-Based Review vs File-by-File
- Zero Data Leaks vs Cloud Data Leaks
The Workbench Philosophy
"Merge confidence, not just merge speed."
Senior engineers know that catching a bug is good, but understanding the system impact is better. LaReview is designed for the deep dive.
Features
AI-Powered Planning
Input a PR (GitHub/GitLab) or diff. LaReview acts as a staff engineer, looking for flows and hazards to build a structured review plan.
Task-Focused Review
See all your review tasks at a glance, grouped by flow and ordered by risk. Track progress, view feedback items, and navigate the change with a files heatmap.
High-Signal Framework
The AI proactively identifies bugs and authenticates them against your rules. No comment spam, just focused feedback threads anchored to specific lines.
Custom Rules
Define rules like "DB queries must have timeouts" or "API changes need a migration note" to enforce standards automatically.
Local Context
Link local Git repos to give the agent full access to search your codebase without upload. Works with your existing AI coding agent.
Git Host Sync
Submit your review feedback directly to GitHub/GitLab PRs with automatic summary generation.
Visual Diagrams
Visualize the flow. Automatically generate diagrams to see architectural changes before you read a single line of code.
Learning Patterns
The AI learns from rejected feedback. Mark suggestions as "ignored" during reviews, then analyze rejections to discover patterns that calibrate future reviews—fewer nitpicks, more signal.
CLI Support
Launch reviews directly from your terminal. Load PRs or pipe a git diff
Workflow
Input
Paste a unified diff or a GitHub/GitLab PR URL (e.g., owner/repo#123).
Fetch
LaReview fetches data locally via the GitHub/GitLab CLI (`gh`/`glab`). No intermediate servers.
Generate
Your chosen AI coding agent (opencode, claude code, codex, etc.) analyzes intent and builds a task tree.
Review
Execute the plan. Add notes, track status, and export to Markdown.
Push
Submit your review directly to GitHub or GitLab with auto-generated summaries.
Start Reviewing
Local-first. Free. Open Source.