roborev

Documentation | Quick Start | Installation

Continuous code review for coding agents. roborev reviews every commit as you work, catches issues before they reach a pull request, and can automatically fix what it finds.

https://github.com/user-attachments/assets/0ea4453d-d156-4502-a30a-45ddfe300574

Why roborev?

AI coding agents write code fast, but they make mistakes. Most people still operate in a "commit when it's ready" mindset, which means review feedback comes too late to be useful. The agent has moved on and context is lost. roborev changes this by giving your agents continuous review feedback while they are working on your prompts:

1. Agents commit often - ideally every turn of work
2. roborev reviews each commit in the background
3. Feed findings into your agent sessions, or fix them autonomously with roborev fix

Every commit gets reviewed. Issues surface in seconds, not hours. You catch problems while context is fresh instead of waiting for PR review.

Features

• Background Reviews - Every commit is reviewed automatically via git hooks. No workflow changes required.
• Auto-Fix - roborev fix feeds review findings to an agent that applies fixes and commits. roborev refine iterates until reviews pass.
• Code Analysis - Built-in analysis types (duplication, complexity, refactoring, test fixtures, dead code) that agents can fix automatically.
• Multi-Agent - Works with Codex, Claude Code, Gemini, Copilot, OpenCode, Cursor, and Droid.
• Runs Locally - No hosted service or additional infrastructure. Reviews are orchestrated on your machine using the coding agents you already have configured.
• Interactive TUI - Real-time review queue with vim-style navigation.
• Extensible Hooks - Run shell commands on review events. Built-in beads integration creates trackable issues from review failures automatically.

Installation

Shell Script (macOS / Linux):

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

Homebrew (macOS / Linux):

brew install roborev-dev/tap/roborev

Windows (PowerShell):

powershell -ExecutionPolicy ByPass -c "irm https://roborev.io/install.ps1 | iex"

With Go:

go install github.com/roborev-dev/roborev/cmd/roborev@latest

Quick Start

cd your-repo
roborev init          # Install post-commit hook
git commit -m "..."   # Reviews happen automatically
roborev tui           # View reviews in interactive UI

https://github.com/user-attachments/assets/c72d7189-9a31-4c1a-a43f-c788cbd97182

The Fix Loop

When reviews find issues, fix them with a single command:

roborev fix                     # Fix all open reviews
roborev fix 123                 # Fix a specific job

fix shows the review findings to an agent, which applies changes and commits. The new commit gets reviewed automatically, closing the loop.

For fully automated iteration, use refine:

roborev refine                  # Fix, re-review, repeat until passing

refine runs in an isolated worktree and loops: fix findings, wait for re-review, fix again, until all reviews pass or --max-iterations is hit.

Code Analysis

Run targeted analysis across your codebase and optionally auto-fix:

roborev analyze duplication ./...           # Find duplication
roborev analyze refactor --fix *.go         # Suggest and apply refactors
roborev analyze complexity --wait main.go   # Analyze and show results
roborev analyze test-fixtures *_test.go     # Find test helper opportunities

Available types: test-fixtures, duplication, refactor, complexity, api-design, dead-code, architecture.

Analysis jobs appear in the review queue. Use roborev fix <id> to apply findings later, or pass --fix to apply immediately.

Review Verification

When committing frequently, reviews can accumulate open findings - some valid, some false positives due to limited context. compact automates verification and consolidation:

roborev compact                      # Verify and consolidate findings (background)
roborev compact --wait               # Wait for completion
roborev compact --branch main        # Compact jobs on main branch

compact uses an agent to verify each finding against the current codebase. The agent searches code, filters out false positives and already-fixed issues, consolidates related findings across multiple reviews, and creates a single consolidated review. roborev automatically closes original jobs when consolidation succeeds.

This adds a quality layer between review and fix, reducing noise and making human review easier. Check progress with roborev status or roborev tui.

Commands

See full command reference for all options.

Configuration

Create .roborev.toml in your repo:

agent = "claude-code"
review_guidelines = """
Project-specific review instructions here.
"""

See configuration guide for all options.

Hooks

Run custom commands when reviews complete or fail. Add to .roborev.toml:

[[hooks]]
event = "review.completed"
command = "notify-send 'Review done for {repo_name} ({sha})'"

Template variables: {job_id}, {repo}, {repo_name}, {sha}, {verdict}, {error}.

Beads Integration

The built-in beads hook type creates beads issues from review failures, giving your agents a task queue of findings to fix:

[[hooks]]
event = "review.*"
type = "beads"

When a review fails or finds issues, a beads issue is created with the job ID and a roborev fix command, so agents can pick it up and resolve it autonomously.

See hooks guide for details.

Supported Agents

roborev auto-detects installed agents.

Documentation

Full documentation available at roborev.io:

• Quick Start
• Installation
• Commands Reference
• Configuration
• Auto-Fixing with Refine
• Code Analysis and Assisted Refactoring
• Hooks
• Agent Skills
• PostgreSQL Sync

Development

git clone https://github.com/roborev-dev/roborev
cd roborev
go test ./...
make lint            # run full static lint checks locally
make install
make install-hooks   # install pre-commit hook to run lint before commit
# optional ACP end-to-end smoke test (Codex adapter)
make test-acp-integration
# disable mode negotiation for adapters that do not support session modes yet
make test-acp-integration ACP_TEST_DISABLE_MODE=1
# optional adapter-specific smoke tests
make test-acp-integration-codex   # codex target auto-disables mode negotiation
make test-acp-integration-claude  # claude target auto-disables mode negotiation
make test-acp-integration-gemini  # gemini target auto-disables mode negotiation

License

MIT