#125 · Primary category: AI Coding Assistants
repowise
Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural decisions via MCP.
Project last updated:08/29/26
GitHub Stars
6.3K
Forks
672
Contributors
79
License
AGPL-3.0
Why we included this project
An AI coding agent can read the file open in front of it, but it usually has no idea how that file fits into the rest of the repo. Repowise fixes that by building a local index in SQLite plus a vector store and exposing it to your editor through MCP tools the agent can call itself. From that index come per-file health scores, a generated wiki whose pages cite the exact source ranges, git signals like hotspots, ownership and bus factor, dead-code cleanup plans arranged in tiers, and architectural decisions tied to the files they govern. It runs locally with no API key, and adding an LLM provider upgrades the wiki to model-written prose. Teams that lean on Claude Code, Cursor, or Windsurf stop hand-holding their agents around module boundaries, and maintainers see outside contributors land with full context instead of asking the same questions over and over.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
superpowers
An agentic skills framework & software development methodology that works.
ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
skills
Skills for Real Engineers. Straight from my .agents directory.
opencode
The open source coding agent.
andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.