repowiseWelcome to repowise
Repowise turns any git repository into a queryable knowledge graph that AI coding agents — Claude Code, Cursor, Windsurf, Claude Desktop, VS Code — can reason over through seven MCP tools. Self-hosted or hosted, same engine.
Your AI coding agent reads files. It doesn't know who owns them, which ones change together, which ones are dead, or why they were built the way they were. Repowise indexes your codebase into four intelligence layers and exposes them to your editor through seven precisely designed MCP tools — so your agent answers "why does auth work this way?" instead of "here is what auth.ts contains."
The four intelligence layers
Graph intelligence
Tree-sitter across 14 languages, three-tier call resolution, heritage extraction, Leiden community detection, PageRank, and execution flow tracing.
Git intelligence
500 commits of history turned into hotspot scores, ownership %, co-change pairs, bus factor, and significant commit messages.
Documentation intelligence
LLM-authored wiki for every module and notable file, refreshed incrementally on every commit. Citations, freshness, confidence.
Decision intelligence
First-class decision records mined from git, captured by hand, or extracted from inline markers. Linked to the files they govern.
Jump in
Quickstart
Install repowise, index your first repo, and connect Claude Code in under a minute.
What is repowise
The four layers, who it's for, and how it compares to plain LLM coding.
The seven MCP tools
get_overview, get_answer, get_context, search_codebase, get_risk, get_why, get_dead_code — what they do and when to call them.
CLI reference
Every repowise command grouped by purpose, verified against source.
Hosted vs self-hosted
Same engine. Pick the deployment model that fits your team.
Benchmarked, not hand-waved
On 48 paired SWE-QA tasks from pallets/flask, repowise-augmented
Claude Code matches baseline answer quality while being dramatically
leaner:
| Metric (per task, mean) | Baseline | + repowise | Δ |
|---|---|---|---|
| Cost | $0.1396 | $0.0890 | −36% |
| Wall time | 41.7 s | 33.9 s | −19% |
| Tool calls | 7.4 | 3.8 | −49% |
| Files read | 1.9 | 0.2 | −89% |
32 / 48 (67%) tasks are cheaper with repowise — at parity quality. Methodology and per-task tables: repowise-bench.
Two ways to run it
# Self-hosted — runs entirely on your machine
pip install repowise
cd your-project
repowise init# Hosted — sign in at repowise.dev, click "+ Index a new repo"
# No install, push-sync via webhookEither way, your editor connects through the same MCP protocol and sees the same seven tools.
New here? Start with the Quickstart and you'll be querying your codebase from Claude Code in about a minute. New to MCP? The seven-tool overview explains what your agent can ask for.
Where to find help
- Discord — discord.gg/cQVpuDB6rh
- GitHub — github.com/repowise-dev/repowise
- Email — hello@repowise.dev
- Stuck on install? — Troubleshooting
or just run
repowise doctor.