roborev - roborev

Skip to content

CLI Commands

Terminal UI

Configuration

Supported Agents

GitHub Integration

GitLab Integration

Guides

Advanced Features

Integrations

Troubleshooting

Development

Changelog

roborev¶

Continuous code review for coding agents. Review commits immediately, catch<br>issues early, and fix them while context is fresh.

Read Docs<br>View on GitHub

How roborev works&para;

roborev reviews every commit in the background and feeds findings back to your<br>coding agent so the write -> review -> fix loop runs hands-off.

Post-commit reviews - every commit is reviewed automatically, with any<br>agent.

Agent hook - nudges your CLI agent to fix findings mid-session.

Refine before you ship - /roborev-refine re-reviews and fixes your whole<br>branch until every review passes, catching bugs before the PR.

Set up automation ->

Droid<br>Kilo<br>Kiro

Quick Start&para;

curl -fsSL https://roborev.io/install.sh | bash

Then from within your git repositories:

roborev init # Install post-commit hook<br># do some work, generate commits<br>roborev tui # Browse reviews in the terminal UI

For Windows, see the<br>installation guide.

For LLMs&para;

This docs site publishes source Markdown next to each rendered page. Prefer the<br>.md URL when reading or citing docs programmatically: /changelog.md for<br>/changelog/, /guides/reviewing-code.md for /guides/reviewing-code/, and<br>/index.md for this page.

Why roborev?&para;

AI coding agents write code fast, but they make mistakes. Most review feedback<br>comes too late. The agent has moved on and context is lost. roborev changes<br>this:

Ask your agents to commit often , ideally every turn of work

roborev reviews each commit in the background

Bring review work back into the agent session with<br>agent-hook (--agent droid for Factory Droid) or check<br>the TUI (roborev tui) as findings arrive

Address findings by letting the hook prompt the fix skill, copying<br>reviews into your agent, using /roborev-fix, or<br>running roborev fix

Every commit gets reviewed. Issues surface in seconds, not hours. Open reviews<br>stay in the TUI queue until explicitly addressed and closed, so nothing falls<br>through the cracks.

Review Ledger

Every commit is reviewed automatically via git hooks. Reviews accumulate in a<br>persistent queue that acts as a ledger: nothing is closed until explicitly<br>addressed.

Agent-Ready Feedback

Use agent-hook to prompt Codex, Claude Code, or Droid (--agent droid) to<br>run the fix skill when review work piles up. You can also copy findings into<br>your agent session, use /roborev-fix, or run roborev fix to apply fixes<br>automatically.

Code Analysis

Built-in analysis types (duplication, complexity, refactoring, test fixtures,<br>dead code) that agents can address directly.

Multi-Agent

Works with Codex, Claude Code, Gemini, Copilot, OpenCode, Cursor, Droid, Kilo,<br>Kiro, Pi, and Grok Build. Auto-detects installed agents.

Rich Markdown Display

Reviews render with full Markdown formatting: syntax-highlighted code blocks,<br>headings, lists, and inline styles, right in your terminal.

Runs Locally

No hosted service or additional infrastructure. Reviews are orchestrated on<br>your machine using the coding agents you already have configured.

Multi-Machine Sync

Bi-directionally sync reviews across machines via PostgreSQL.

Architecture&para;

Daemon : HTTP server on port 7373 (auto-finds available port if busy)

Workers : Pool of 4 (configurable) parallel review workers

Storage : SQLite at ~/.roborev/reviews.db with WAL mode

Config : Global at ~/.roborev/config.toml, per-repo at .roborev.toml

Federated Multiplayer&para;

Bi-directionally sync reviews across machines with a shared PostgreSQL database.<br>Each daemon maintains its local SQLite for fast access while syncing changes to<br>the central database.