code-review Tools

PR-Agent is an open-source AI assistant that helps developers and maintainers streamline code reviews, generate pull request descriptions, and catch potential issues early. By running directly from PR comments, CI pipelines, or the terminal, it reduces the manual effort spent on code evaluation. It is designed for development teams looking to accelerate their review cycles and improve overall code quality across platforms like GitHub, GitLab, and Bitbucket.

pstack-claude provides rigorous, multi-agent workflow implementations of Poteto's pstack methodology, translated for Claude, Codex, Pi, and other major AI coding assistants. It solves the problem of vendor lock-in and inconsistent agent behavior by offering standardized, high-quality workflows across different AI harnesses. This repository is for developers and teams who want reliable, reproducible AI-assisted coding patterns that work seamlessly whether they're using Claude, Gemini, GitHub Copilot, or other AI coding tools.

Code Review Graph is a local-first code intelligence graph for MCP and CLI. It builds a persistent, semantic map of your codebase, enabling AI coding assistants to understand context and dependencies without reading every file. This dramatically reduces context overhead in code reviews and large-repository workflows, making AI tools faster and more accurate. It's built for developers and teams working in complex codebases who want to leverage AI assistance without the performance and cost penalties of massive context windows.

tuicr is a terminal user interface (TUI) for code review that brings GitHub-style diffs and PR review workflows directly to your terminal. It solves the problem of context-switching between your editor and a web browser for code reviews, offering vim keybindings for navigation, line-level commenting, and the ability to push reviews directly to GitHub. It's built for developers who live in the terminal, use vim, and want a faster, more integrated review process for Git, jj, or Mercurial repositories.

Open-source & free — Battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in fine-tuned ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.

See infra costs in code reviews, not on your bill.