Repowise

Your AI coding agent reads files. It doesn't know which ones change together, which ones are dead, or why they were built the way they were. It has the source code and no memory of how the codebase got there.

repowise fixes that. It indexes your codebase into five intelligence layers — dependency graph, git history, auto-generated docs, architectural decisions, and code health — and exposes them to Claude Code, Codex, and any MCP-compatible agent through nine task-shaped tools. The result: your agent answers "why does auth work this way?" instead of "here is what auth.ts contains" — with fewer tool calls, fewer file reads, and lower cost per query, at comparable answer quality (benchmarks ↓).

---

The five layers

repowise runs once, builds everything, then keeps it in sync on every commit. Each layer is queryable from the CLI, the MCP tools, and the local dashboard.

Layer	What it gives you	Edge
◈ Graph	tree-sitter dependency graph across 15 languages · two-tier file + symbol nodes · 3-tier call resolution · Leiden communities · PageRank / centrality / execution flows · framework-aware route→handler edges	A real graph most tools never build
◈ Git	hotspots (churn × complexity) · ownership % · co-change pairs (hidden coupling) · bus factor · contributor profiles · module health · reviewer suggestions	Behavioral signals static analysis can't see
◈ Docs	LLM-generated wiki per module/file · incremental on every commit · freshness + confidence scoring · hybrid RAG search (FTS + vector via RRF)	Stays current — rebuilt every commit
◈ Decisions	architectural decisions mined from 8 sources, evidence-backed (verified / fuzzy / unverified), linked to graph nodes, connected by supersedes/refines/conflicts_with edges, tracked for staleness	★ Captured nowhere else
★ Code Health	25 deterministic biomarkers, 1–10 score per file · defect-calibrated weights · coverage ingestion · trend alerts · refactoring targets · zero LLM, <30s	★ Defect-validated — our edge ↓

Full deep-dive on every layer (graph, git, docs, decisions, hooks, auto-sync, dead code, CLAUDE.md generation): docs/INTELLIGENCE_LAYERS.md →

---

★ Code Health — the layer nobody else nails

Code health is repowise's deepest differentiator — the one layer with no real equivalent, and the only one we can prove predicts real bugs.

repowise scores every file 1–10 from 25 deterministic biomarkers — McCabe complexity, deep nesting, brain methods, class cohesion (LCOM4), god classes, native Rabin–Karp clone detection, untested hotspots, function-level churn, code-age volatility, ownership dispersion, change entropy, co-change scatter, prior-defect history, test-quality smells, and more.

Zero LLM calls. Zero cloud requirement. Zero new runtime dependencies. Pure Python over tree-sitter + git data — finishes in under 30 seconds on a 3,000-file repo. The biomarker weights are calibrated against a real defect corpus, not hand-tuned; only the learned constants ship and the runtime stays fully deterministic.

repowise health                       # KPIs + lowest-scoring files
repowise health --coverage cov.lcov   # ingest LCOV/Cobertura/Clover → untested-hotspot
repowise health --refactoring-targets # ranked by impact / effort
repowise health --trend               # snapshots + declining / predicted-decline alerts

And it proves itself on your repo, not just a benchmark: after every index, repowise checks its own flags against your git history and reports the hit rate in the terminal and on the dashboard — "16/20 lowest-health files had a bug fix in the last 6 months, 3.3x the 24% baseline". See Does the score find the bugs?.

Does the score actually find bugs? Yes — and it out-ranks the leading commercial code-health tool. On the same 2,770 files across 9 languages, scored at the same leakage-free commit against the same defect labels:

Axis (head-to-head, paired tests)	repowise	Leading commercial tool
Recall @ 20%-of-lines budget	0.173	0.074
Effort-aware ranking (Popt)	0.607	0.462
Defect density, size-normalized (defects/KLOC, Alert:Healthy)	2.18×	0.56×
Discrimination (ROC AUC)	0.731	0.705

Ranking by repowise health surfaces 2.3× the defects under a fixed review budget (Popt Δ +0.144, recall Δ +0.098, density Δ p = 0.003 — all paired, significant). Full methodology & CIs →

User guide & per-biomarker reference: docs/CODE_HEALTH.md

---

Benchmarks

Reproducible, on public codebases — repowise-bench →

1 · Agent efficiency — repowise does the exploration once, offline

Most of a coding agent's spend goes to exploration — greping for symbols, reading candidate files, re-reading them as context grows. repowise does that work once so the agent skips it on every query. Paired SWE-QA runs on real repositories (same model, same harness, with vs without repowise's MCP tools):

The win is context: repowise hands the agent a curated answer instead of a pile of files to read. Loading a commit's context via get_context costs 2,391 tokens vs 64,039 raw — ~27× fewer (−96%). Across the two benchmarks, agents read −69% to −89% fewer files and make −49% to −70% fewer tool calls at answer quality on par with raw exploration; on a long, multi-step investigation that compounds to −41% of the context re-read across the whole session. Saved tokens are tokens you don't pay for — dollar cost drops too, though agent-side prompt caching now mutes the cost delta. Reports: flask48 · flask v3 · sklearn48

2 · Distill — index-aware output distillation

Most of what an agent reads from a shell command is noise: 300 lines of passing tests around 4 failures, full commit bodies for "what changed recently". repowise distill <cmd> compresses command output before the agent reads it — errors-first, exit code preserved, and every omission reversible via an inline [repowise#<ref>] marker (repowise expand <ref>). Paired runs on a public OSS repo, per command:

Command	Raw → distilled tokens	Saved
pytest -q (11 failures)	3,374 → 1,317	61% — all 11 failure lines preserved
git log -50	3,064 → 331	89%
git diff (30 commits)	62,833 → 8,635	86%

Small outputs pass through untouched (net-positive guard), and in an end-to-end spot-check the agent reached the identical root-cause diagnosis from distilled output as from raw. Opt-in Claude Code hook rewrites noisy commands automatically (shown for approval); repowise saved tracks tokens and dollars saved. Full guide: docs/DISTILL.md →

3 · Code health predicts real defects

Health scores are collected at a historical commit (T0); bug-fixing commits are counted over the following 6 months; the two are correlated — strictly no leakage. Across 21 open-source repositories spanning all 9 Full-tier languages:

• Cross-project mean ROC AUC 0.74 [95% CI 0.68–0.79] at identifying the files that go on to receive bug-fixes — up to 0.90 on individual repos.
• Survives controlling for file size (partial Spearman ρ = −0.16) — it is not just "flag the big files."
• Significantly out-discriminates recent churn (+0.10 AUC) and prior-defect history (+0.12 AUC), DeLong p < 1e-9.
• Holds up on an external published dataset it has never seen (PROMISE/jEdit CK-metrics: AUC 0.76–0.78, within ~0.03 of the dataset's own tuned model).

Full report: health-defect/BENCHMARK_REPORT.md →

---

Local dashboard

repowise serve starts a full web UI alongside the MCP server — no separate setup.

Highlights: Chat (natural-language Q&A) · Docs (wiki with Mermaid + graph sidebar) · Graph (interactive, 2,000+ nodes, community coloring, path finder) · C4 Architecture (Context → Containers → Components) · Risk (hotspots, ownership heatmap, module health, dead code, blast radius) · Contributors (per-author profiles) · Decisions (evidence drawer, evolution timeline, decision-graph) · Health (biomarker scores, coverage, trends) · Security (local pattern scan) · Costs · Workspace (cross-repo contracts & co-changes). Full view-by-view list in docs/USER_GUIDE.md.

---

Supported languages

15 languages parsed to AST · 9 at the Full tier · framework-aware across all of them.

Full tier  

Good tier    · Partial  

Tier	Languages	What works
Full	Python · TypeScript · JavaScript · Java · Kotlin · Go · Rust · C++ · C#	AST parsing, import resolution, named bindings, call resolution, heritage extraction, docstrings; multi-project workspace resolvers; framework-aware edges; per-language dynamic-hint extractors; code-health biomarkers
Good	C · Ruby · Swift · Scala · PHP	AST parsing, import resolution, named bindings, call resolution, heritage (mixins / derive / extensions / traits), docstrings; dedicated workspace-aware resolvers; Rails / Laravel / TYPO3 framework edges; dynamic-hint extractors
Config / data	OpenAPI · Protobuf · GraphQL · Dockerfile · Makefile · YAML · JSON · TOML · SQL · Terraform · Markdown · Shell	Included in the file tree; special handlers extract endpoints / targets where applicable
Git-blame only	Objective-C · Elixir · Erlang · Dart · Zig · Julia · Clojure · Haskell · OCaml · F# · …	Tracked in git history (blame, hotspots, co-change); no AST parsing yet

Adding a language needs one .scm query file and one config entry — no changes to the parser core. Full per-language matrix, code-health checklist, and the contributor recipe: docs/LANGUAGE_SUPPORT.md →

---

Who it's for

	Start here
Individual developers	pip install repowise → repowise init → query from Claude Code in minutes. 100% local, BYO API key, free under AGPL-3.0.
Teams	repowise.dev hosted — zero ops, hosted MCP endpoint, auto re-index on every commit, plus the free Repowise PR Bot that comments on hotspots, hidden coupling, and declining health per PR.
Enterprises	On-prem topology, SSO/SCIM, RBAC, CVE-aware security layer, workflow integrations, and commercial licensing (no AGPL obligation) — see docs/COMMERCIAL.md.

---

Quickstart

pip install repowise          # or: uv tool install repowise

Single repo

cd your-project
repowise init        # builds all five intelligence layers (one-time)
repowise serve       # starts MCP server + local dashboard

Multi-repo workspace

cd my-workspace/     # parent dir containing backend/, frontend/, shared-libs/
repowise init .      # scans for git repos, indexes each, runs cross-repo analysis
repowise serve       # workspace dashboard + per-repo pages

repowise init automatically registers the MCP server, installs a PostToolUse hook in ~/.claude/settings.json, generates .mcp.json at the project root, and offers a post-commit hook that keeps everything in sync. If the Codex CLI is installed and logged in, interactive runs also offer to write project-local .codex/config.toml, .codex/hooks.json, and a managed AGENTS.md; non-interactive runs require --codex. Skip Codex setup with --no-codex; force or skip AGENTS.md with --agents / --no-agents.

Claude Code plugin. Prefer a one-command setup? Install the plugin from the marketplace — it registers the MCP server and hook and adds /repowise:* slash commands (init, health, risk, dead-code, decision, …):

/plugin marketplace add repowise-dev/repowise
/plugin install repowise@repowise

To add the MCP server to another editor manually:

{
  "mcpServers": {
    "repowise": { "command": "repowise", "args": ["mcp", "/path/to/your/project"] }
  }
}

Init time: the graph, git, dead-code, and code-health layers build in minutes with zero LLM calls — run repowise init --index-only for a queryable index almost immediately. The one-time cost is the documentation layer (LLM-generated wiki pages, can run in the background). After that, every commit-triggered update takes under 30 seconds and only regenerates the pages your change touched.

Docs: Quickstart · User Guide · CLI Reference · Codex · MCP Tools · Distill · Workspaces · Auto-Sync · Config

---

Nine MCP tools

Most tools are designed around data entities — one module, one file, one symbol — forcing agents into long chains of sequential calls. repowise tools are designed around tasks: pass multiple targets in one call, get complete context back. Every response carries an _meta envelope with index_age_days, indexed_commit, and a stale_warning that fires only when the indexed HEAD diverges from live .git/HEAD.

Tool	What only this tool answers
get_overview()	Architecture summary, module map, entry points, git health, community summary. First call on any unfamiliar codebase.
get_answer(question)	Hybrid retrieval (FTS + vector via RRF) + PageRank bias + 1-hop graph expansion → a cited answer with calibrated retrieval_quality. Returns structured best_guesses on low confidence. Collapses search → read → reason into one round-trip.
get_context(targets, include?)	Triage card for files / modules / symbols: title, summary, signatures, hotspot bit, governing_decisions, and symbol_ids. include opens callers/callees, ownership, metrics, decisions, full_doc. Batch many targets.
get_symbol("file.py::Name")	Raw source bytes for one indexed symbol with exact line bounds — cheaper and safer than Read + offset math.
search_codebase(query, kind?)	Semantic search over the wiki, filterable by kind (implementation / test / config / doc), tagging each result's search_method.
get_risk(targets, changed_files?)	Hotspot scores, dependents, co-change partners, ownership, test gaps, security signals. Pass changed_files for PR mode → a directive block (will_break, missing_cochanges, missing_tests, governance_risk).
get_why(query?, targets?)	Architectural decision records, status, evidence spans, and the supersession lineage chain. Falls back to git archaeology when no ADRs exist.
get_dead_code(...)	Unreachable code by confidence tier with cleanup-impact estimates; cross-repo consumer detection in workspace mode.
get_health(targets?, include?)	25-biomarker scores per file. Dashboard mode → KPIs + lowest-scoring files + module rollup; targeted mode → per-file findings. include: coverage, refactoring, trend.

Worked example ("Add rate limiting to all API endpoints" in 5 calls instead of ~30 greps+reads) and the full reference: docs/MCP_TOOLS.md →

---

How it compares

	repowise	Google Code Wiki	DeepWiki	Swimm	CodeScene
Self-hostable, open source	✅ AGPL-3.0	❌ cloud only	❌ cloud only	❌ Enterprise only	✅ Docker
Private repo — no cloud	✅	❌ in development	❌ OSS forks only	✅ Enterprise tier	✅
Auto-generated documentation	✅	✅ Gemini	✅	✅ PR2Doc	❌
MCP server for AI agents	✅ 9 tools	❌	✅ 3 tools	✅	✅
Proactive agent hooks	✅ Claude + Codex hooks	❌	❌	❌	❌
Auto-generated AI instructions (CLAUDE.md, AGENTS.md)	✅	❌	❌	❌	❌
Code health score (1–10)	✅ 25 biomarkers	❌	❌	❌	✅ 25–30
Brain Method / LCOM4 / god class	✅	❌	❌	❌	✅
Test-coverage intelligence	✅ LCOV/Cobertura/Clover	❌	❌	❌	❌
Untested-hotspot detection	✅ coverage × hotspot	❌	❌	❌	❌
Health trend + declining alerts	✅ rolling snapshots	❌	❌	❌	✅
Refactoring recommendations	✅ deterministic	❌	❌	❌	✅
Git intelligence (hotspots, ownership, co-change)	✅	❌	❌	❌	✅
Bus factor analysis	✅	❌	❌	❌	✅
Dead code detection	✅	❌	❌	❌	❌
Architectural decision records	✅	❌	❌	❌	❌
Multi-repo workspace intelligence	✅ co-changes, contracts, federated MCP	❌	❌	❌	❌
Local dashboard	✅	❌	❌	❌ IDE only	✅

repowise is the intersection: behavioral git intelligence + a defect-validated code-health score + auto-generated docs + agent-native MCP + architectural decisions + multi-repo workspace intelligence — self-hostable and open source. Detailed breakdown: docs/COMPETITIVE_ANALYSIS.md.

---

For teams & enterprises

repowise.dev is the same engine, fully managed — at feature parity with self-hosted: every CLI command, every MCP tool, the full dashboard. We dogfood it on our own codebase: live snapshot → · explore public repos →.

On top of self-hosting:

• Zero ops — managed deploys & webhooks, auto re-index on every commit.
• Hosted MCP endpoint — point any MCP client at one URL, no local server.
• Repowise PR Bot — free GitHub App, one deterministic comment per PR (hotspot touches, hidden coupling, declining health, dead code), zero LLM calls. Install → · Learn more →
• CVE-aware security layer, cross-repo intelligence at scale, and integrations (Slack, Jira/Linear, Confluence/Notion, PagerDuty) (rolling out).

What's GA / in development / planned, on-prem topology, SSO/SCIM/RBAC, and pricing: docs/COMMERCIAL.md · Get in touch →

---

Privacy

• Self-hosted: your code never leaves your infrastructure. No telemetry. No analytics.
• BYOK: bring your own Anthropic / OpenAI key. We never see your LLM calls. Zero data retention via Anthropic's API policy.
• What's stored: the NetworkX graph, LanceDB embeddings (non-reversible vectors), generated wiki pages, git metadata. Raw source is processed transiently and never persisted.
• Fully offline: Ollama + a local embedding model = zero external API calls.

---

CLI & configuration

repowise init [PATH]      # index codebase (one-time; --index-only skips LLM)
repowise serve [PATH]     # MCP server + local dashboard
repowise update [PATH]    # incremental update (<30s; --workspace for all repos)
repowise query "<q>"      # ask anything from the terminal
repowise health           # code-health KPIs + lowest-scoring files
repowise risk main..HEAD  # score a branch / PR range for defect risk
repowise dead-code        # unreachable-code report
repowise distill pytest   # compact errors-first output (reversible) — saves 60–90% tokens
repowise saved            # tokens & dollars saved by distillation
repowise doctor           # check setup, API keys, store drift

repowise init generates .repowise/config.yaml (provider, model, embedder, reasoning mode, exclude patterns, git commit depth). Full command set: docs/CLI_REFERENCE.md · config reference: docs/CONFIG.md.

---

Contributing

git clone https://github.com/repowise-dev/repowise
cd repowise
uv sync --all-packages
uv run repowise --version
uv run pytest tests/unit/

Full guide, including how to add languages and LLM providers: CONTRIBUTING.md.

---

License

AGPL-3.0. Free for individuals, teams, and companies using repowise internally.

For commercial licensing — the enterprise security & compliance layer, SSO/SCIM, RBAC, workflow integrations, priority support and SLA, or embedding repowise in a product without AGPL obligations — see docs/COMMERCIAL.md or contact hello@repowise.dev.

---