Developer Tools / Code Review
Self-hosted AI code reviewer for GitHub pull requests that uses multiple narrow reviewer passes and a validator to produce one verified review.
The page clearly describes a real AI-powered developer tool with a specific job: reviewing GitHub pull requests. The README gives a strong explanation of how it works, includes benchmark claims, deployment details, and states that it is self-hosted on the user’s infrastructure. There is enough visible evidence for a useful public listing.
The crawl shows a detailed product story, but not enough concrete setup detail in the snapshot to judge onboarding quality, supported GitHub hosting setups, or how much configuration is needed beyond the shipped defaults. The benchmark section is visible, but the full methodology and reproducibility details are not fully exposed here.
Last evaluated 16 hours ago. Current rank #229. Down 3 spots in the rankings.
CodeGraph is a local code knowledge graph for AI coding agents like Claude Code, Cursor, Codex, OpenCode, and Hermes Agent. It aims to cut token use, tool calls, and runtime by letting agents query pre-indexed code structure instead of scanning files repeatedly.
Mercemur is a store automation platform with three interfaces: a REST API, an MCP server for AI agents, and a CLI for editing storefronts as files. The docs show authentication, scopes, rate limits, error handling, pagination, idempotency, and a large API surface for catalogue, orders, customers, pricing, and money.
Lumae is a free native macOS screen recorder and screenshot tool for polished demos, with automatic zooms, cursor smoothing, motion blur, captions, voiceover, and annotated screenshots. It also exposes editing commands over MCP so agents like Claude Code or Claude Desktop can edit projects directly.
A zero-dependency C++23 CLI and MCP server that gives coding agents a ranked map of a repository, including call context, blast radius, and tests to run.
