Repowise · Codebase intelligence
jegernoutt / refact
AI Agent that handles engineering tasks end-to-end: integrates with developers’ tools, plans, executes, and iterates until it achieves a successful result.
Does the health score find the bugs?
Repowise ranks every file by predicted defect risk. Of the 20 files it flags as riskiest, 19 (95%) actually needed a bug fix in the last 6 months — 2.7× better than picking files at random.
Languages
- typescript48.4%
- rust33.9%
- yaml5.1%
- kotlin4.5%
- python2.7%
- toml1.4%
- json1.1%
Key modules3
- typescript
vscode
plugins/vscode
- rust
engine
refact-agent/engine
- typescript
gui
refact-agent/gui
Code health
Full reportHow jegernoutt/refact works
AI Agent that handles engineering tasks end-to-end: integrates with developers’ tools, plans, executes, and iterates until it achieves a successful result. This page is an auto-generated, always-fresh map of the jegernoutt/refact repository, written primarily in Rust. Repowise indexes the source, parses every symbol, computes a dependency graph, scores per-file code health from complexity, duplication, test coverage and churn, mines git history for hotspots and ownership, and lifts the resulting architectural decisions into a wiki you can read or query through MCP.
The codebase has 2,567 source files, 47,440 symbols, and 13 languages, structured as a monorepo with 3 packages. Git churn analysis flags 463 high-frequency files as hotspots — places where bugs, rewrites, and code review tend to concentrate. The dependency graph clusters into 344 tightly-coupled module communities.
Use the panels above to open the interactive dashboards, or connect this repo to your editor via the Repowise MCP server for grounded answers inside Claude, Cursor, or VS Code.