{"slug": "roborev-continuous-code-review-for-coding-agents", "title": "Roborev – Continuous code review for coding agents", "summary": "Roborev, a new open-source tool, provides continuous code review for AI coding agents by automatically reviewing every commit and feeding findings back to the agent, enabling a hands-off write-review-fix loop. The tool, which runs locally and supports multiple agents including Codex, Claude Code, and Gemini, surfaces issues in seconds and maintains a persistent review ledger until problems are resolved.", "body_md": "# roborev[¶](#roborev)\n\nContinuous code review for coding agents. Review commits immediately, catch issues early, and fix them while context is fresh.\n\n## How roborev works[¶](#how-roborev-works)\n\nroborev reviews every commit in the background and feeds findings back to your coding agent so the write -> review -> fix loop runs hands-off.\n\n**Post-commit reviews**- every commit is reviewed automatically, with any agent.** Agent hook**- nudges your CLI agent to fix findings mid-session.** Refine before you ship**-`/roborev-refine`\n\nre-reviews and fixes your whole branch until every review passes, catching bugs before the PR.\n\n## Quick Start[¶](#quick-start)\n\n```\ncurl -fsSL https://roborev.io/install.sh | bash\n```\n\nThen from within your git repositories:\n\n```\nroborev init          # Install post-commit hook\n# do some work, generate commits\nroborev tui           # Browse reviews in the terminal UI\n```\n\nFor Windows, see the\n[installation guide](/installation/#quick-install-recommended).\n\n## For LLMs[¶](#for-llms)\n\nThis docs site publishes source Markdown next to each rendered page. Prefer the\n`.md`\n\nURL when reading or citing docs programmatically: `/changelog.md`\n\nfor\n`/changelog/`\n\n, `/guides/reviewing-code.md`\n\nfor `/guides/reviewing-code/`\n\n, and\n`/index.md`\n\nfor this page.\n\n## Why roborev?[¶](#why-roborev)\n\nAI coding agents write code fast, but they make mistakes. Most review feedback comes too late. The agent has moved on and context is lost. roborev changes this:\n\n**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(`agent-hook`\n\n`--agent droid`\n\nfor Factory Droid) or check the TUI (`roborev tui`\n\n) as findings arrive**Address findings** by letting the hook prompt the fix skill, copying reviews into your agent, using, or running`/roborev-fix`\n\n`roborev fix`\n\nEvery commit gets reviewed. Issues surface in seconds, not hours. Open reviews stay in the TUI queue until explicitly addressed and closed, so nothing falls through the cracks.\n\n-\n**Review Ledger** Every commit is reviewed automatically via git hooks. Reviews accumulate in a persistent queue that acts as a ledger: nothing is closed until explicitly addressed.\n\n-\n**Agent-Ready Feedback** Use\n\n`agent-hook`\n\nto prompt Codex, Claude Code, or Droid (`--agent droid`\n\n) to run the fix skill when review work piles up. You can also copy findings into your agent session, use`/roborev-fix`\n\n, or run`roborev fix`\n\nto apply fixes automatically. -\n**Code Analysis** Built-in analysis types (duplication, complexity, refactoring, test fixtures, dead code) that agents can address directly.\n\n-\n**Multi-Agent** Works with Codex, Claude Code, Gemini, Copilot, OpenCode, Cursor, Droid, Kilo, Kiro, Pi, and Grok Build. Auto-detects installed agents.\n\n-\n**Rich Markdown Display** Reviews render with full Markdown formatting: syntax-highlighted code blocks, headings, lists, and inline styles, right in your terminal.\n\n-\n**Runs Locally** No hosted service or additional infrastructure. Reviews are orchestrated on your machine using the coding agents you already have configured.\n\n-\n**Multi-Machine Sync** Bi-directionally sync reviews across machines via PostgreSQL.\n\n## Architecture[¶](#architecture)\n\n**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`\n\nwith WAL mode**Config**: Global at`~/.roborev/config.toml`\n\n, per-repo at`.roborev.toml`\n\n## Federated Multiplayer[¶](#federated-multiplayer)\n\nBi-directionally sync reviews across machines with a shared PostgreSQL database. Each daemon maintains its local SQLite for fast access while syncing changes to the central database.", "url": "https://wpnews.pro/news/roborev-continuous-code-review-for-coding-agents", "canonical_source": "https://www.roborev.io/", "published_at": "2026-08-13 06:11:40+00:00", "updated_at": "2026-08-13 06:40:25.555573+00:00", "lang": "en", "topics": ["developer-tools", "ai-agents", "ai-tools"], "entities": ["Roborev", "Codex", "Claude Code", "Gemini", "Copilot", "OpenCode", "Cursor", "Droid"], "alternates": {"html": "https://wpnews.pro/news/roborev-continuous-code-review-for-coding-agents", "markdown": "https://wpnews.pro/news/roborev-continuous-code-review-for-coding-agents.md", "text": "https://wpnews.pro/news/roborev-continuous-code-review-for-coding-agents.txt", "jsonld": "https://wpnews.pro/news/roborev-continuous-code-review-for-coding-agents.jsonld"}}