Hosted for teams → · Docs · Discord · Contact
For your agent · The five layers · Distill · Change risk · Code health · Dashboard · Workspaces · Quickstart · MCP tools · Comparison · Teams
Your AI agent burns most of its budget rediscovering your codebase. Index it once, and it never has to again.
Paired runs, same model, same harness, with and without repowise (the numbers, and what they do not show →).
Free and self-hosted, runs on your machine, and the first index needs no API key.
Every question your agent asks about your repo has an answer that could have been computed ahead of time. Who calls this function? What breaks if I change it? Why is it written this way? Which of these files is actually dangerous? Instead, agents rediscover it from scratch on every task: grep, read, re-read, forget.
repowise computes those answers once and keeps them current on every commit. Your
agent reads the answer instead of the codebase, and the same index gives your team a
defect-validated health score, change-risk scoring on every PR, and a local dashboard
for all of it. One pip install, no cloud, your code never leaves your machine.
repowise exposes ten task-shaped MCP tools to Claude Code, Codex, Cursor, VS Code and anything else that speaks MCP. Most tools are built around data entities (one file, one symbol), which forces agents into long chains of sequential calls. These are built around tasks: pass several targets in one call, get complete context back.
Because the exploration work is already done, that phase mostly disappears. Loading
one commit's context through get_context costs 2,391 tokens instead of 64,039
raw. On a long multi-step investigation that compounds to −41% of the context
re-read across the whole session.
And it arrives without being asked. Optional hooks push
context into the session at the moment it matters: the governing architectural
decision when your agent edits a file that decision covers, a warning when it touches
a file with a run of recent bug fixes, a compact briefing at session start. repowise
also generates your CLAUDE.md and AGENTS.md from the real index, so even an agent
with no MCP support starts informed.
It learns from how you actually work. repowise reads your own agent transcripts for the corrections you keep making ("use the shared HTTP client, not raw requests") and turns the durable ones into tracked decisions it delivers back later. The wiki generation budget tilts toward the modules you and your agent ask about most. All local, all deterministic, no extra LLM calls.
Five layers, built in a single pass and kept in sync on every commit. Each one is queryable from the CLI, the MCP tools, and the local dashboard.
| Layer | What it gives you | Edge |
|---|---|---|
| ◈ Graph | Dependency graph across 16 languages · file + symbol nodes · 3-tier call resolution · Leiden communities · PageRank and 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 · which files actually get bug-fixed, and how recently | Behavioural signals static analysis cannot see |
| ◈ Docs | A generated wiki page per module and file · rebuilt incrementally every commit · freshness and confidence scoring · hybrid search (full-text + vector) · selectable style and output language | Stays current instead of rotting |
| ◈ Decisions | Architectural decisions mined from eight sources, evidence-backed, linked to the graph nodes they govern, connected by supersedes / refines / conflicts_with, tracked for staleness | ★ Captured nowhere else |
| ★ Code health | 25 deterministic markers, 1 to 10 per file · three signals: defect risk · maintainability · performance · coverage ingestion · concrete refactoring plans (Extract Class / Helper, Move Method, Break Cycle, Split File) · zero LLM, under 30s | ★ Defect-validated, with the fix attached |
Only the Docs layer needs an LLM. repowise init --index-only builds the graph,
git, decision, and health layers with no API key and no spend (seven of the eight
decision sources are deterministic; only the one harvested during doc generation
needs a provider).
Full detail on every layer: docs/layers/INTELLIGENCE_LAYERS.md →
Most of what an agent reads back from a shell command is noise: 300 lines of passing
tests wrapped around 4 failures, full commit bodies when it asked "what changed
recently". repowise distill <cmd> compresses command output before the agent reads
it, errors first, exit code preserved.
repowise distill pytest # 61% fewer tokens, all 11 failure lines kept
repowise distill git log -50 # 89% fewer tokens
repowise saved # what distillation saved you, in tokens and dollarsNothing is lost. Every omission leaves an inline [repowise#<ref>] marker that
repowise expand <ref> reverses in full, so the agent can always pull the detail back
without re-running the command. Small outputs pass through untouched. An opt-in hook
rewrites noisy commands automatically, shown to you for approval first.
The Costs dashboard tallies both savings surfaces, priced at your own agent's model. Example from a week of heavy local use.
Full guide: docs/agent/DISTILL.md →
Three deterministic signals, all computed from the graph and git history, no LLM:
- Change risk. Score any commit or
base..HEADrange 0-10 from the shape of the diff, ranked against your repo's own recent commits. PR mode returns directives rather than vibes:will_break,missing_cochanges,missing_tests,tests_to_run. One command:repowise risk main..HEAD. (reference →) - Bug history. Which files and symbols actually get bug-fixed, and how recently. Doc, test and config commits are filtered out so the count means what it says, and a file with a run of recent fixes gets flagged as a bug magnet while you edit it. (reference →)
- Test intelligence. Ingest coverage, find untested hotspots, and run only the
tests a diff actually exercises with
repowise impacted-tests HEAD~1. (reference →)
Plus the free Repowise PR Bot: one deterministic comment per pull request covering hotspot touches, hidden coupling, declining health and dead code. Zero LLM calls.
A score that says "this file is risky" is where most tools stop. repowise scores every file, locates where the risk concentrates, and then names the specific fix.
Every file is scored 1-10 from 25 deterministic markers (McCabe complexity, brain methods, LCOM4 cohesion, god classes, native Rabin-Karp clone detection, untested hotspots, change entropy, prior-defect history and more), split into three lenses: defect risk, maintainability, and performance (static N+1 and I/O-in-loop risk traced across files through the call graph, where file-local linters found 0 of the cross-function cases repowise surfaced 557 of).
Zero LLM calls, zero cloud, zero new runtime dependencies. Pure Python over tree-sitter and git data, under 30 seconds on a 3,000-file repo, with marker weights calibrated against a real defect corpus, not hand-tuned.
It proves itself on your repo, not just on a benchmark. After every index, repowise checks its own flags against your git history and reports what it found: "17 of the 20 lowest-health files had a bug fix in the last 6 months, 3.6x the 23% baseline." If that number is bad on your codebase, you will see it.
Then it names the fix. Not "this class is too big", but Extract Class, Extract Helper, Move Method, Break Cycle, Split File, or Extract Method, with the exact methods, edges and symbols that move, the blast radius of callers and co-changing files that have to move with them, and a graph-aware ranking so a fix on a central hub outranks the same fix on a leaf. Extract Method goes down to an intra-procedural dataflow pass that lifts the exact span and infers a behavior-preserving signature.
repowise health # KPIs and lowest-scoring files
repowise health --refactoring-targets # ranked, concrete plans
repowise health --trend # snapshots plus declining-health alertsThe dashboard renders each plan as a card with a copy-to-agent button. An optional LLM step, never in the indexing path and only on request, expands any plan into generated code and a unified diff.
Against CodeScene, the leading commercial code-health tool, on the same 2,770 files and the same defect labels, ranking by repowise health surfaces 2.3x the defects under a fixed review budget (paired, p = 0.003). Full head-to-head, methodology and limitations →
Guides: code health · refactoring
repowise serve starts the full web dashboard next to the MCP server. No separate
setup, all local.
 Code Health · every file as a bubble, hover any one to inspect its score, size, coverage and findings |
 Commits · change-risk distribution, size-versus-diffusion scatter, and a review-priority queue |
 Refactoring · plans grouped by type, ranked on a priority-versus-effort quadrant |
 Files · a treemap of the whole repo, sortable by health, churn, size or coverage |
Also in there: Chat (ask the codebase in natural language) · Docs (the generated wiki, with Mermaid and a graph sidebar) · Architecture and C4 (Context → Containers → Components) · Knowledge Graph plus a zoomable canvas map · Risk, Hotspots, Coupling and Blast radius · Contributors · Decisions (evidence drawer and evolution timeline) · Symbols · Security · Dead code · Stats · Costs · Workspace.
Every view and what each one answers: docs/start/DASHBOARD.md →
Real systems are not one repository, and the interesting failures live in the gaps between them.
- Workspaces. Index many repos as one unit and get what only a cross-repo view can show: contracts matched between a producer and its consumers, so a breaking API change is caught before it ships, plus cross-repo co-change pairs, federated MCP that answers across the whole estate, and conformance checks. (docs/scale/WORKSPACES.md →)
- Worktrees just work. Run
repowise initorrepowise updateinside a linked git worktree and it detects the base checkout, seeds that worktree's index from it, and catches up incrementally. No flags, no second full index. (docs/scale/WORKTREES.md →) - Auto-sync. Keep the index current with a post-commit hook, a file watcher
(
repowise watch), a webhook, or polling. An incremental update takes seconds. (docs/scale/AUTO_SYNC.md →)
The Repowise VS Code extension puts the index where code actually gets written: know what your change breaks before you push (riskiest files ranked, what is downstream, forgotten companion files, missing tests, suggested reviewers), health in the gutter and status bar, callers and ownership on hover, refactoring plans as CodeLens, and the full dashboards inside the editor. One install also registers the MCP server with VS Code, so the same local index serves both you and your agent, and exposes six tools to GitHub Copilot. Quiet by default, everything toggleable, nothing leaves your machine.
Install from the Marketplace (search Repowise) or Open VSX, then run Repowise: Set Up This Repository. Guide: docs/agent/VSCODE.md →
16 languages parsed to AST · 11 at the Full tier · framework-aware across all of them.
Full tier
Good tier
SQL and dbt projects get real ref() / source() lineage, shell scripts get
function-level symbols, and OpenAPI, Protobuf, GraphQL, Dockerfile, Terraform and
friends get dedicated handlers. Anything else is still tracked through git history:
blame, hotspots, co-change.
Adding a language takes one .scm query file and one config entry, with no changes
to the parser core. Full matrix and the contributor recipe:
docs/layers/LANGUAGE_SUPPORT.md →
1. Install
pip install repowise # Windows: python -m pip install repowise
repowise --version2. Index your repo, with no LLM and no key
cd /path/to/your/repo
repowise init --index-only -yThat builds the dependency graph, git history, code-health scores and dead-code
findings in seconds. Want the generated wiki and semantic search too? Use repowise init --provider gemini|anthropic|openai with the matching key.
3. Connect your agent. The MCP server is repowise mcp, served from the repo directory.
Claude Code
# Plugin (adds the tools, slash commands and skills):
/plugin marketplace add repowise-dev/repowise
/plugin install repowise@repowise
# ...or wire the MCP server directly:
claude mcp add repowise -- repowise mcpOr commit a project .mcp.json:
{ "mcpServers": { "repowise": { "command": "repowise", "args": ["mcp"] } } }Codex CLI
Add to ~/.codex/config.toml:
[mcp_servers.repowise]
command = "repowise"
args = ["mcp"]Or: codex mcp add repowise -- repowise mcp
4. First real call. Ask your agent: "Use repowise get_overview to summarize this
repo", or "get_context for src/auth.py". You get graph-grounded architecture and
per-file triage instead of a flurry of greps.
get_overviewandget_contextwork in index-only mode with no key, synthesized from the graph, git and health layers.search_codebase,get_answerandget_whyneed full mode (the generated wiki).
Full walkthrough: docs/start/QUICKSTART.md →
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,
so your agent always knows how much to trust what it just read.
| Tool | What only this tool answers |
|---|---|
get_overview() |
Architecture summary, module map, entry points, git health. The first call on any unfamiliar codebase. |
get_answer(question) |
Hybrid retrieval (full-text plus vector via RRF), PageRank bias and 1-hop graph expansion into one cited answer with a calibrated retrieval_quality. Collapses search → read → reason into a single round-trip. |
get_context(targets, include?) |
Triage card for files, modules or symbols: summary, signatures, hotspot bit, governing decisions, symbol_ids. include opens callers, callees, ownership and metrics. Batch many targets in one call. |
get_symbol("file.py::Name") |
Source for one indexed symbol with exact line bounds. Cheaper and safer than Read plus 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?) |
Hotspots, dependents, co-change partners, ownership, test gaps, bug history. Pass changed_files for PR mode and get a directive block back. |
get_change_risk(revspec) |
Pre-merge defect score for a whole commit or range from the shape of the diff, ranked as a percentile against recent commits, plus the tests coverage proves it touches. |
get_why(query?, targets?) |
Architectural decisions, their evidence spans and the supersession lineage. Falls back to git archaeology when no decisions exist. |
get_dead_code(...) |
Unreachable code by confidence tier with cleanup-impact estimates, and cross-repo consumer detection in workspace mode. |
get_health(targets?, include?) |
Per-file marker scores across all three signals. include opens coverage, trends, per-file signals, the accuracy self-check, and structured refactoring plans. |
Ten is a deliberate ceiling rather than a limit we ran into: a small, task-shaped surface is easier for an agent to choose from than a large one. Worked example ("add rate limiting to all API endpoints" in 5 calls instead of ~30 greps and reads), the opt-in tools, and the full reference: docs/agent/MCP_TOOLS.md →
| 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 | ✅ 10 tools | ❌ | ✅ 3 tools | ✅ | ✅ |
| Proactive agent hooks | ✅ Claude + Codex | ❌ | ❌ | ❌ | ❌ |
Auto-generated AI instructions (CLAUDE.md, AGENTS.md) |
✅ | ❌ | ❌ | ❌ | ❌ |
| Command-output distillation | ✅ reversible | ❌ | ❌ | ❌ | ❌ |
| Learns from your usage (session-mined decisions, demand-weighted docs) | ✅ | ❌ | ❌ | ❌ | ❌ |
| Code health score (1-10) | ✅ 25 markers | ❌ | ❌ | ❌ | ✅ 25-30 |
| Brain Method / LCOM4 / god class | ✅ | ❌ | ❌ | ❌ | ✅ |
| Test-coverage intelligence | ✅ LCOV/Cobertura/Clover | ❌ | ❌ | ❌ | ❌ |
| Untested-hotspot detection | ✅ coverage × hotspot | ❌ | ❌ | ❌ | ❌ |
| Health trend + declining alerts | ✅ rolling snapshots | ❌ | ❌ | ❌ | ✅ |
| Concrete cross-file refactoring plans | ✅ graph-aware + blast radius | ❌ | ❌ | ❌ | |
| Dataflow-verified within-function plans | ✅ CFG + reaching definitions | ❌ | ❌ | ❌ | |
| Git intelligence (hotspots, ownership, co-change) | ✅ | ❌ | ❌ | ❌ | ✅ |
| Pre-merge change-risk scoring | ✅ 0-10 + directives | ❌ | ❌ | ❌ | ✅ |
| Bus factor analysis | ✅ | ❌ | ❌ | ❌ | ✅ |
| Dead code detection | ✅ | ❌ | ❌ | ❌ | ❌ |
| Architectural decision records | ✅ | ❌ | ❌ | ❌ | ❌ |
| Multi-repo workspace intelligence | ✅ contracts, co-change, federated MCP | ❌ | ❌ | ❌ | ❌ |
| Local dashboard | ✅ | ❌ | ❌ | ❌ IDE only | ✅ |
repowise is the intersection: an agent-native context layer and behavioral git intelligence and a defect-validated health score with the fix attached, all out of one index, self-hostable and open source. Full side-by-side comparisons: repowise.dev/compare →
| Start here | |
|---|---|
| Individual developers | pip install repowise → repowise init → query from Claude Code, Cursor, or any MCP agent. Fully local, bring your own key, free under AGPL-3.0. For developers → |
| Team leads | Know which PRs to worry about before you merge: change-risk scoring plus the free Repowise PR Bot. For team leads → |
| Engineering leaders | See how much of your code AI wrote and whether it is healthy: agent provenance, health trends and bus factor, straight from git history. For engineering leaders → |
| Security & compliance | Reachability-aware CVE triage, secret detection across full git history, and SBOM, on your real dependency graph. For security → · security review → |
| Enterprises | On-prem and air-gapped, SSO/SCIM, commercial licensing with no AGPL obligation, IP indemnification. For enterprise → · docs/business/COMMERCIAL.md |
repowise.dev is the same engine, fully managed, at feature parity with self-hosted: every CLI command, every MCP tool, the whole dashboard. We run it on our own codebase in the open: live snapshot → · explore public repos →.
On top of self-hosting: managed deploys and webhooks with auto re-index on every commit, a hosted MCP endpoint so any client can point at one URL with no local server, a CVE-aware security layer, cross-repo intelligence at scale, and integrations (Slack, Jira/Linear, Confluence/Notion, PagerDuty) (rolling out).
What is GA versus in development, on-prem topology, SSO/SCIM/RBAC and pricing: docs/business/COMMERCIAL.md · Get in touch →
- Self-hosted: your code never leaves your infrastructure, so no code, file paths
or repo names are ever sent. The CLI does report anonymous, opt-out usage
telemetry (command names and coarse environment only) to help us prioritize; turn it
off with
repowise telemetry disable,DO_NOT_TRACK=1, or by running fully offline. What's collected → - Bring your own key: we never see your LLM calls. Zero data retention via Anthropic's API policy.
- What's stored: the graph, embeddings (non-reversible vectors), generated wiki pages, git metadata. Raw source is processed transiently and never persisted.
- Fully offline: Ollama plus a local embedding model means zero external calls.
Doing a security review? docs/business/SECURITY_COMPLIANCE.md →
repowise init [PATH] # index a codebase (one-time; --index-only skips the LLM)
repowise serve [PATH] # MCP server + local dashboard
repowise update [PATH] # incremental update (seconds; --workspace for every repo)
repowise watch # auto-sync daemon, re-index on file change
repowise search "<q>" # search the wiki (fulltext / semantic / symbol)
repowise health # code-health KPIs and lowest-scoring files
repowise risk main..HEAD # score a branch or PR range for defect risk
repowise impacted-tests # only the tests a diff actually exercises
repowise dead-code # unreachable-code report
repowise decision list # architectural decisions
repowise distill pytest # compact, errors-first, reversible command output
repowise saved # tokens and dollars saved by distillation
repowise workspace add # multi-repo workspace management
repowise doctor # check setup, API keys, index driftEvery command and flag: docs/reference/CLI_REFERENCE.md · config: docs/reference/CONFIG.md
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 · architecture: docs/architecture/
AGPL-3.0. Free for individuals, teams and companies using repowise internally.
For commercial licensing (the enterprise security and compliance layer, SSO/SCIM, RBAC, workflow integrations, priority support and SLA, or embedding repowise in a product without AGPL obligations), see docs/business/COMMERCIAL.md or contact hello@repowise.dev.
Built for engineers who got tired of watching their AI agent cat the same file for the fourth time.
⭐ If repowise earns a place in your workflow, give it a star. It costs you nothing, and it's the signal that keeps a small team building this in the open.
repowise.dev · Explore → · Discord · X · hello@repowise.dev