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.
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
Ranks #82 among AI repositories tracked this week, and #82 over the last 30 days; #102 of 2,845 repositories GStars tracks this week (top 4%).
5 releases in the last 90 days, the latest 1 day ago, with 165 contributors on GitHub.
Use Cases & Benefits
- Provides comprehensive codebase intelligence by indexing code, call graphs, git history, tests, docs, and architectural decisions into a unified local index.
- Delivers precise, evidence-backed insights and risk assessments without any cloud or LLM calls, enabling self-hosted, privacy-preserving, and cost-effective analysis.
- Use for enabling AI coding agents to understand complex repositories deeply, reducing redundant file reads and improving task efficiency.
- Use for integrating deterministic change risk and test impact analysis into CI pipelines to prevent regressions and optimize test runs.
- Use for continuous code health monitoring with detailed defect, maintainability, and performance scores plus actionable refactoring plans to reduce technical debt.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
AGPL 3.0
Network copyleft: like the GPL, and also triggered by offering the software over a network.
Community files
- README: present
- Contributing guide: present
Watch-outs
- AGPL-style copyleft also applies when the software is offered over a network.
General guidance from repository metadata, not legal advice. How we score
From the README
Repowise indexes your code, call graph, git history, tests, docs and design
decisions once, on your machine. Then you and your coding agent ask it things:
what calls this, what breaks if I change it, what is dead, what to fix first, and why it was built this way.
Call graph checked against the compiler: 0.976 to 0.995 precision on Go and TypeScript,
and no tool that finds as much of the graph gets more of it right, in 7 of 7 comparisons.
5 tools · 37,853 compiler edges · every losing row published
Graph, risk, health, tests and dead code make zero LLM calls · no API key needed · free and self-hosted · AGPL-3.0 or commercial
Repowise is an ambitious project. We want every engineer, and every agent working beside them, to understand a codebase the way the person who has maintained it for five years does: what calls what, what tends to break, what nobody uses anymore, and why it was built this way. Cutting tokens was never the goal. It happens anyway, because an agent that can ask the index stops searching, opening and re-reading files to find out. Measured against the other context tools on the same agent tasks, it is also the largest saving.
Everything in this README runs free on your own machine. repowise.dev runs it for you, private repos included, and is where Foresight arrives first.
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
+304 stars over 6 days across 5 snapshot days; best day +81 on Oct 16.
Forks
898+57
Open issues
335+30
Compared with peers in AI
Fastest-growing repositories GStars tracks in this cohort for the week of Oct 11, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| storytold/artcraft | 35.6K | +20.3K | 75 | 26 days ago |
| ifixai-ai/iFixAi | 30.7K | +6.9K | 75 | 5 days ago |
| heygen-com/hyperframes | 70.0K | +5.6K | 45 | today |
| vxcontrol/pentagi | 32.0K | +5.4K | 75 | 17 days ago |
| calesthio/OpenMontage | 70.9K | +3.2K | 75 | — |
| repowise-dev/repowise | 7.8K | +454 | 60 | 1 day ago |
| Category median | 35.6K | +5.6K | 75 | — |
Discover Repositories
Search across tracked repositories by name or description