Developer Tools / AI Tooling
A local Claude Code plugin and CLI for auditing, searching, and cleaning agent memory across repos. It scans saved memories for contradictions, stale facts, duplicates, and misfiled entries, with reversible changes and a localhost UI.
The page clearly presents a real AI-adjacent developer tool with a specific job: audit Claude Code memory and clean up contradictions across repositories. The README-visible details cover what it does, how it works, installation paths, CLI/plugin usage, and safeguards like local-only operation and reversible changes. That is enough evidence for a useful public listing.
The snapshot does not show the actual UI, example output, or a worked walkthrough of a scan. It also does not make package maturity easy to judge beyond the repo files and README text, so a visitor cannot tell how polished or battle-tested it is.
Last evaluated just now. Current rank #727. 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.
Single-binary CLI that builds an AI agent knowledge base from git repos, Claude Code/Codex sessions, and saved links. It generates a portable markdown wiki, runs on cron, supports local Ollama mode, and exposes the result for agents via CLAUDE.md/AGENTS.md and MCP.
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.
