dust-tt / dust
Custom AI agent platform to speed up your work.
Code health
dust-tt/dust scores 7.0 out of 10 on defect risk, which Repowise rates Good. Maintainability scores 8.6 out of 10. Static performance risk scores 9.9 out of 10. The three are scored separately and never blended into a single number. 1,749 of 12,105 files are git hotspots, the places where changes and bug fixes concentrate.
Full health report- Files
- 12k
- Symbols
- 58k
- Modules
- 49
- Doc pages
- 7.7k
- Dead exports
- 2.6k
Where the risk concentrates
All 1,749 hotspotsRanked by prior bug fixes and change frequency, mined from the full git history rather than from the code alone.
| File | Churn | Prior fixes | Maintainers | Commits 90d |
|---|---|---|---|---|
| conversation.tsfront/lib/api/assistant | 100.0th %ile | 28bug magnet | 25 | 62 |
| skill_resource.tsfront/lib/resources/skill | 100.0th %ile | 23bug magnet | 19 | 76 |
Read more about dust-tt/dust
- OverviewFiles, symbols, languages, packages, git intelligence
- ArchitectureDependency graph, layered architecture, symbol index, and third-party dependencies
- Code healthPer-file health scores, hotspots, test coverage, dead code, and refactoring targets
- AI explanationsProModule-by-module documentation generated from source
Add a badge to your README
Both badges are public, cached, and update on their own after every index. Nothing to install.
Repowise badge
Links to this page. Adding it also re-indexes the repo every week.
[](https://repowise.dev/repo/dust-tt/dust)Code health badge
Average health across every file, straight from the latest index.
[](https://repowise.dev/repo/dust-tt/dust)How dust-tt/dust works
Custom AI agent platform to speed up your work. This page is an auto-generated, always-fresh map of the dust-tt/dust repository, written primarily in TypeScript. 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 12,105 source files, 57,562 symbols, and 16 languages, organised into 49 modules, led by typescript, json, rust. Static analysis leaves 26,100 open findings across the three health dimensions.
Use the links 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.