CODEBASE INTELLIGENCE FOR AI AGENTS · OPEN SOURCE · HOSTED

Your AI agent doesn't
understand your codebase.

Index any repo into a documented dependency graph in under 30 seconds — real architecture, ownership, and decisions for your AI agents instead of guesses.

Paste any public GitHub repo URL to instantly explore its architecture, dependencies, and more.

See repowise dogfooded on itself→View all repos→
1.4k
GitHub stars
470
Repos indexed
7
MCP tools
<30s
Incremental update
01HOW IT WORKS

One engine, three interfaces

Install once. Choose the interface that fits your workflow — or use all three. They share the same data, the same intelligence, the same stores.

GETTING STARTED

CLI

For the solo developer

GETTING STARTED
$ pip install repowise
$ repowise init .
$ repowise update
$ repowise serve

MCP Server

For AI-native workflows

GETTING STARTED
$ repowise mcp
$ get_overview()
$ get_context(["src/auth"])
$ get_risk(["payments.py"])

Web UI

For the whole team

GETTING STARTED
$ repowise serve
$ localhost:7337/wiki
$ localhost:7337/graph
$ localhost:7337/hotspots
02INTELLIGENCE LAYERS

Most tools answer one question.
repowise answers five.

Graph structure, git history, generated documentation, architectural decisions, and codebase chat — five layers that compound into genuine understanding.

GRAPH

Every dependency, ranked and traced

  • Tree-sitter ASTs across 10+ languages → directed dependency graph
  • PageRank and betweenness centrality surface critical symbols
  • Edge types: imports, calls, inherits, implements, co-changes
  • Scales to 30K+ nodes with automatic SQLite-backed graph
HOTSPOTCORE MODULE
GIT

History that writes the documentation

  • Hotspot detection — top 25% churn + complexity files flagged
  • Co-change partners: files that change together without imports
  • Ownership from git blame — primary owner + top 3 contributors
  • Significant commits filtered into generation prompts
GIT LOGfeat: add auth flowfix: token refreshrefactor: db layerchore: update depsfeat: graph exportfix: memory leakGIT ANALYSISauth/middleware.pyHOTSPOTCHURN99th %ileOWNERRaghav C.87%CO-CHANGE PARTNERSdb/sessions.py92%tests/test_auth.py78%SIGNIFICANT COMMITS3 of 47 included in docs
DOCS

Wiki pages that stay fresh

  • 9-level hierarchical generation: symbols → files → modules → repo
  • Confidence scoring with git-informed decay — stale pages auto-regenerate
  • RAG context via LanceDB or pgvector — each page knows its imports
  • Resumable, crash-safe, idempotent — checkpoint after every page
✦AUTO-GENERATEDCONFIDENCE0.953 FILES CHANGED
DECISIONS

The why behind your architecture

  • 4 capture sources: inline markers, git archaeology, README mining, CLI
  • Staleness tracking — decisions age when governed files get commits
  • get_why() searches decisions before you change anything
  • Health dashboard: stale decisions, ungoverned hotspots, proposed reviews
PROPOSEDACCEPTEDRATIONALE2025-03-15 · Raghav C.AFFECTED FILESsrc/auth/src/db/tests/STALE ⚠
CHAT

Ask questions. Get grounded answers.

  • Provider-agnostic — works with whichever LLM you configured
  • SSE streaming with real-time tool call visibility
  • Answers grounded in your actual codebase, not hallucinated
  • Artifact panel: diagrams, risk reports, wiki pages

What files handle authentication and who owns them?

⚡get_context(["src/auth"]) · get_risk(["src/auth"])
src/auth/middleware.pyHOTSPOT
defverify_token(request):
token = request.headers...
Owner:Raghav C.· 96th %ile churn
Ask about your codebase...↑
03MCP INTEGRATION

7 tools your AI agent already knows how to call

  • get_overview()— Architecture summary, module map, entry points, tech stack.
  • get_answer()— One-call RAG Q&A. Retrieves over the wiki, gates on confidence, returns a cited 2–5 sentence answer.
  • get_context()— Docs, ownership, history, decisions, freshness for files, modules, or symbols. Pass multiple targets in one call.
  • search_codebase()— Semantic search over the full wiki using LanceDB or pgvector. Natural language queries.
  • get_risk()— Hotspot score, dependents, co-change partners, risk summary. Also returns top 5 global hotspots.
  • get_why()— Three modes: natural language search over decisions, path-based lookup, or health dashboard.
  • get_dead_code()— Unreachable files, unused exports, zombie packages — sorted by confidence and cleanup impact.
SUPPORTED EDITORS
Claude Code|Cursor|Cline|Any MCP client
CLAUDE CODE// Ask repowise about your codebaseget_context({ targets: ["src/auth"]})MCP PROTOCOLrepowise MCPGraphGitWikiADRsRICH CONTEXTRESPONSEfile:src/auth/middleware.pyowner:Raghav C.churn:96th percentileconfidence:0.95 — docs freshdecisions:Use JWT · Async auth
04EDITOR INTELLIGENCE
CLAUDE.MD

CLAUDE.md that writes itself

  • Architecture overview from the real dependency graph
  • Hotspot warnings with churn metrics and owners
  • Key design decisions and architectural constraints
  • Dead code summary with confidence scores
  • Entry points, build commands, and tech stack
  • Also generates cursor.md — same data, different format
CLAUDE.md
repowise update
✦AUTO-GENERATED BY REPOWISE
1# CLAUDE.md
3## Architecture
4Monorepo · Python + Next.js
53 packages · 0 circular deps
7## Hotspots
8graph-flow.tsx 99th %ile
9init_cmd.py 97th %ile
11## Commands
12Build: npm run build
13Test: npm run test
05HOW WE COMPARE

The full picture, side by side

  • Auto-generated docs, git intelligence, decision records, and MCP tools — one package
  • Open-source (AGPL-3.0) and fully self-hostable
  • 14/14 features vs 3–4/14 for any single competitor
FeaturerepowiseGoogle CodeWikiDeepWikiCodeSceneSourcegraph
Self-hostable OSS✓————
Works with private repos✓—✓✓✓
Auto-generated wiki (LLM)✓✓✓——
Git intelligence (hotspots / ownership / co-changes)✓——✓—
Dead code detection✓————
Architectural decision records✓————
MCP server for AI agents✓————
Semantic search✓✓✓—✓
Doc freshness / confidence scoring✓————
CLAUDE.md auto-generation✓————
Codebase chat (agentic)✓✓✓——
Dependency graph visualization✓✓✓✓✓
Provider choice (4 LLM providers)✓————
Privacy (code never leaves your infra)✓——✓✓
repowise: 14/14 · CodeScene: 3/14 · Sourcegraph: 3/14 · DeepWiki: 4/14 · Google CodeWiki: 3/14

Self-assessed against publicly documented features as of May 2026. Vendor capabilities change — please verify before committing to any tool.

06FROM THE BLOG

Guides, comparisons, and deep dives

Security review on a Python monolith with 19 hotspots
use-cases10 min read

Security review on a Python monolith with 19 hotspots

A security review codebase case study on a Python monolith: find 19 hotspots, map ownership gaps, and cut duplicate reads with one review path.

Generate claude.md from a real repo, not a blank page
guides12 min read

Generate claude.md from a real repo, not a blank page

Generate claude.md from repo architecture, ownership, and recent changes with MCP calls. Give Claude Code a day-one brief that cuts guessing.

RAG for code is not embeddings plus a vector store
concepts9 min read

RAG for code is not embeddings plus a vector store

RAG for code fails when it stops at chunks and vectors. See a 4-layer model with symbols, history, ownership, and a 36% cheaper retrieval path.

View all posts→
07GET IN TOUCH

Three paths to codebase intelligence

  • Self-host — free, forever
    • pip install repowise — your machine, your server, your CI
    • AGPL-3.0 · full feature set · code never leaves your infra
  • Hosted SaaS — live now
  • Enterprise
    • On-prem · SSO · role-based access · dedicated support · SLAs
I'm interested in