Codebase intelligence layer for AI coding agents: code health, git analytics, dead code detection, and architectural decisions via MCP.
repowise is worth checking the docs before setup with strong trust signals. Check agent compatibility and use-case fit before adding it to your workflow.
Repository setup guidance
gh repo view repowise-dev/repowise --webOpen the official README and confirm the supported install method.
Add the server entry to your MCP client config.
Restart your agent and verify that the server tools appear.
repowise gives your AI coding agent deep understanding of your codebase. It analyzes dependencies, git history, code health, and architecture, then exposes this intelligence through MCP tools so your agent can answer complex questions like 'why does auth work this way?' instead of just reading files. It helps reduce tool calls, file reads, and costs while improving answer quality.
repowise is an open-source codebase intelligence platform designed for AI-assisted engineering teams. It indexes your codebase into five intelligence layers: dependency graph (tree-sitter across 15 languages), git history (hotspots, ownership, co-change coupling), auto-generated documentation, architectural decisions, and code health scores. These layers are exposed via nine MCP (Model Context Protocol) tools to agents like Claude Code and Codex. Key features include: multi-repo workspace support, dead code detection, code health scoring proven to predict real bugs, and a local dashboard for visualization. repowise runs once, builds everything, then keeps in sync on every commit. It supports 15 programming languages and provides benchmarks showing reduced tool calls and costs at comparable answer quality.
Strong trust signals; still review the README and permissions before production use.
Last commit was about 51 days ago.
2203 GitHub stars indicate community interest.
25 open issues signal maintenance load.
NOASSERTION license detected.
Give AI coding agents deep codebase context to answer architectural and design questions accurately.
Detect dead code and technical debt across large multi-language repositories.
Automate code review with health scores and git analytics to identify risky changes.
Generate and maintain auto-updated documentation from code structure and git history.
Enable AI agents to understand module ownership, coupling, and bus factor for better refactoring decisions.
repowise indexes your entire codebase locally; ensure sensitive files are excluded via configuration.
MCP tools expose codebase data to AI agents; review agent permissions and data handling policies.
2,203
Stars
285
Forks
25
Issues
NOASSERTION
License
Optimize markdown documentation for LLMs and RAG systems, reducing token consumption by 67-95%.
Up-to-date code documentation for LLMs and AI code editors, eliminating outdated or hallucinated API references.
Turn OpenAPI, MCP, Doxygen, godoc, rustdoc, and Markdown into static documentation sites you own.
Codebase intelligence layer for AI coding agents: code health, git analytics, dead code detection, and architectural decisions via MCP.
AI-assisted engineering teams using Claude Code, Codex, or other MCP-compatible agents., Tech leads and architects who need to manage technical debt and code quality across repos., DevOps and platform engineers integrating code intelligence into CI/CD pipelines.
The setup section provides repository-level starting guidance, not a guarantee of an independently verified installation. Check the official README and release notes.
repowise indexes your entire codebase locally; ensure sensitive files are excluded via configuration. MCP tools expose codebase data to AI agents; review agent permissions and data handling policies.
Similar or complementary options to evaluate include llm-docs-builder, context7, sourcey.
Jun 7, 2026
2 security/trust notes recorded.
Setup difficulty is 3/5.