repowise-dev/

repowise

GitHub Website

Repowise provides codebase intelligence with health scoring, generated docs, git analytics, dead code detection, and architectural decisions via MCP tools. It runs locally, offering a ten-tool MCP suite and a local dashboard.

4.7kstars

516forks

100issues

AGPL-3.0license

2026since

Star historydaily snapshots by VibeCrowd

Collecting history — the radar snapshots this repo daily. The trend line appears after 3 days of data (1 so far).

Alternatives & relatedmatched by topic overlap

DeusData/

codebase-memory-mcp

▲ 1.2k/wk

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

37k3.0kC

Graphify-Labs/

graphify

▲ 4.6k/wk

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.

102k9.9kPython

ComposioHQ/

awesome-claude-skills

▲ 585/wk

A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows

72k8.1kPython

sickn33/

agentic-awesome-skills

▲ 328/wk

AAS Core is the local, agent-first control plane for complete catalog discovery, agent-owned selection, stack validation, and planning, backed by 2,000+ agentic skills. Includes CLI, local MCP, catalog, plugins, and Workbench.

44k6.5kPython

wshobson/

agents

▲ 148/wk

Multi-harness agentic plugin marketplace for Claude Code, Codex CLI, Cursor, OpenCode, GitHub Copilot, and Gemini CLI

38k4.1kPython

affaan-m/

ECC

▲ 2.9k/wk

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

238k36kJavaScript

Comparerepowise vs codebase-memory-mcp repowise vs graphify repowise vs awesome-claude-skills

Reviewgenerated from repository data · Aug 5, 2026

What it is

repowise is a codebase intelligence tool that indexes a repository to provide a defect-validated health score, change-risk scoring on PRs, and a local dashboard. It exposes ten MCP tools to integrate with various agents and editors, enabling tasks over files or symbols without requiring API keys or cloud services.

How it works

The index computes five layers (Graph, Git, Docs, Decisions, Code health) from the repository in a single pass and keeps them synchronized on every commit. It supports generating a wiki per module/file, incremental rebuilds, and a hybrid search. The Code health layer uses 25 deterministic markers across three lenses (defect risk, maintainability, performance) to score files from 1-10 and suggest concrete refactoring like Extract Class or Move Method. The system emphasizes local operation (no API key, all local) and zero LLM usage in indexing.

Getting started

From README:

repowise init --no-prose

repowise distill <cmd>

repowise health

repowise health --refactoring-targets

There are instructions for viewing the local dashboard at localhost:3000 and generating wiki pages from the index.

Recent releases

Latest releases:

v0.38.0 (2026-08-04): features measuring vocabulary overlap across orientation pages; retired page ids keep resolv
v0.37.0 (2026-07-29): add --no-editor-setup to skip global MCP/hook registration; scope Stats page
v0.36.0 (2026-07-25): cleaner docs nav; data-driven TOML output filters
v0.35.0 (2026-07-24): UI bug-fix rendering improvements; restore numbers emphasis
v0.34.0 (2026-07-20): vscode release; overlap knowledge-graph enrichment

Traction

GitHub stars: 4655 (as provided). Other numbers: forks 516, open_issues 100. Language Python. License AGPL-3.0.

Behind the repo

Not provided in the excerpt beyond project hosting and MCP tooling references. No company-specific details are included.

Caveats

License: AGPL-3.0. Created 2026-03-23; last_push 2026-08-04. Open issues: 100.

SharePost on X LinkedIn