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 ten 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 five intelligence layers and exposes them to your editor through ten precisely designed MCP tools, so your agent answers "why does auth work this way?" instead of "here is what auth.ts contains."
Let your agent set it up
Paste this into Claude Code, Cursor, Codex, or whatever you use. No API key needed, and nothing in the flow stops to ask for one.
Set up Repowise in this repository so you can query it instead of grepping.
1. Check for the CLI with `repowise --version`. If missing: `pip install repowise`.
2. If `.repowise/` already exists, run `repowise status` and stop.
3. Otherwise run `repowise init --yes` from the repo root. This needs NO API
key and exits 0 without one. Do not stop to ask me for a key.
4. It registers the MCP server itself. Then call get_overview and tell me the
architecture, the top hotspots, and anything in the health report worth acting on.More prompts, plugin installs, and the machine-readable llms.txt endpoints are on Set up with your agent.
The five intelligence layers
Graph intelligence
Tree-sitter across 16 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
A wiki for every module and notable file, refreshed incrementally on every commit. Written by a model, or rendered from your code's structure with no API key at all.
Decision intelligence
First-class decision records mined from git, captured by hand, or extracted from inline markers. Linked to the files they govern.
Code health
A 1 to 10 score per file from deterministic markers across three signals (defect risk, maintainability, performance), with defect-calibrated weights, benchmarked to out-rank the leading commercial tool at predicting real bugs. Zero LLM.
The hosted platform
The fastest way to run Repowise: sign in at repowise.dev, index a repo, done: managed indexing, push-sync, private repos via a GitHub App, and everything the managed service adds on top of the engine.
Hosted platform overview
Zero-ops indexing, AI docs and chat, the plan ladder from free to enterprise. Start here.
Security suite
CVE scanning with usage and reachability triage, secrets across full git history, SBOM/VEX, nightly refresh, compliance, audit trail.
Teams & leader dashboard
Pooled repos and credits, portfolio health and ownership, engineering signals with nightly drift detection.
Alerts & notifications
Signed Slack-compatible webhooks, the notification bell, and per-kind email, built to never spam.
Jump in
Quickstart
Install repowise, index your first repo, and connect Claude Code in under a minute.
Set up with your agent
Copy-pasteable prompts your agent can follow start to finish, plus the machine-readable llms.txt endpoints.
Agent plugins
The Claude Code and Codex plugins: MCP server, hooks, six skills, and ten slash commands in one install.
What is repowise
The five layers, who it's for, and how it compares to plain LLM coding.
The ten MCP tools
get_overview, get_answer, get_context, get_symbol, search_codebase, get_risk, get_change_risk, get_why, get_dead_code, get_health: 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.
VS Code extension
Editor-native health signals, refactoring CodeLens, branch risk, and in-editor dashboards, plus one-install MCP for your agent.
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 ten 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 ten-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? See Troubleshooting
or just run
repowise doctor.
