repowise-dev/repowise
Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural decisions via MCP. observed · 2026-08-28
Health v2 · maintenance only
77/100
- Activity 99
- Release rhythm 86
- Longevity 11
Flags: young
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.
- gap_med: 1
- age_days: 163
- days_rel: 12
- days_push: 7
- n_releases_24m: 62
Adoption not part of the score
6240 stars · 667 forks observed · 2026-08-28
What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded
Repowise is a Python-based codebase intelligence tool that indexes code structure, call graphs, git history, tests, and architectural decisions into one durable index. It exposes this evidence to humans and AI coding agents via a CLI and MCP server, providing code health scores, change-risk analysis, auto-generated documentation, dead code detection, and git analytics.
Use cases
- give my AI coding agent compact context about my codebase via MCP
- find dead code and technical debt hotspots in my repository
- auto-generate architecture documentation that stays up to date
- score change risk on pull requests before merging
- analyze git history for hotspots, ownership, and file coupling
- triage CVEs by whether my code actually reaches vulnerable dependency code
- detect secrets across full git history and generate an SBOM
- measure how much of my codebase was written by AI agents
When to choose
- you want deterministic, LLM-free static and historical analysis with reproducible results
- you use AI coding agents and want to cut token usage and tool calls with grounded repository context
- you need evidence-backed code health and defect-risk ranking validated against bug-fix history
- you want self-hostable analysis where source code never leaves your infrastructure
- you need C4 architecture views derived from the real dependency graph instead of hand-drawn diagrams
When to avoid
- you need a lightweight linter or formatter for style enforcement rather than repository-level intelligence
- your project is very small and a simple grep or IDE search suffices
- you require IDE-native inline integrations rather than CLI, MCP, or web-based surfaces
- you cannot accept an AGPL-3.0 license in your context
Facets
cli-tool · maturity active
linter developer-tools documentation search-engine mcp security data-visualization developer-tools documentation security version-control python cli self-hosted cross-platform code-health code-intelligence git-analytics dead-code-detection technical-debt change-risk code-review architecture-diagrams mcp-server ai-coding-agents dependency-graph cve-triage static-analysis
10 sources
- readme: https://github.com/repowise-dev/repowise · fetched 2026-08-28 · b1e8b7a30a52
- homepage: https://repowise.dev · fetched 2026-08-29 · dec44bd1ab71
- site_page: https://www.repowise.dev/features/code-health · fetched 2026-08-29 · 30aa955e007e
- site_page: https://www.repowise.dev/features/agent-provenance · fetched 2026-08-29 · c87cf6fd19f9
- site_page: https://www.repowise.dev/features/ai-context · fetched 2026-08-29 · 618928d7242e
- site_page: https://www.repowise.dev/features/change-risk · fetched 2026-08-29 · 5cf618e2b00e
- site_page: https://www.repowise.dev/features/security · fetched 2026-08-29 · e82ae14a36c8
- site_page: https://www.repowise.dev/features/wiki · fetched 2026-08-29 · d6ad083fd39a
- site_page: https://www.repowise.dev/features/git-intelligence · fetched 2026-08-29 · a3918c40e5d8
- site_page: https://www.repowise.dev/features/architecture · fetched 2026-08-29 · c2d022eac388
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| repowise-dev/repowise | main | 77 |
For agents
markdown · JSON · MCP: product_card(name="repowise-dev/repowise")
Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem