#125 · Primary category: AI Coding Assistants

repowise

ai code-complexity code-health code-intelligence code-quality dead-code developer-tools documentation git-analytics mcp open-source python refactoring static-analysis technical-debt

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