Developer Tools / AI Benchmarking
A local Rust CLI for A/B testing two CLAUDE.md files against a fixed SWE-bench Lite smoke set, with doctor, run, and report commands.
The page clearly describes an AI-adjacent developer tool with a specific workflow: compare two CLAUDE.md variants, run them through Claude locally, and score them on SWE-bench Lite tasks. The README gives concrete commands, prerequisites, runtime behavior, and the shipped v1 scope, which is enough for a useful public listing.
The snapshot doesn’t show real benchmark results, screenshots, release status, or how the output report looks, so a visitor can’t judge effectiveness from the page alone.
Last evaluated 2 days ago. Current rank #432. Down 2 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.
A lightweight React Markdown renderer with built-in LaTeX, syntax highlighting, streaming-safe rendering, and security-focused defaults.
Claude Code plugin that blocks dependency edits until a fresh, source-cited version check is recorded, helping prevent hallucinated or stale package versions across npm, pip, Poetry/uv, Cargo, and NuGet.
Omni is a local-first semantic search app for macOS that indexes text, code, PDFs, images, audio, and video on-device. It supports multilingual search, private offline use, and exposes a local endpoint for agents to query indexed files.
