tanavc1 / local-llm-autotune
Zero-config local LLM optimization for Ollama, LM Studio, and Apple Silicon MLX. Reduces TTFT by 40%, wall time for local agents by 46%, and RAM usage by 3x.
Code health
tanavc1/local-llm-autotune scores 5.7 out of 10 on defect risk, which Repowise rates Fair. Maintainability scores 5.9 out of 10. Static performance risk scores 9.3 out of 10. The three are scored separately and never blended into a single number. 12 of 168 files are git hotspots, the places where changes and bug fixes concentrate.
Full health report- Files
- 168
- Symbols
- 3.1k
- Modules
- 33
- Doc pages
- 572
- Dead exports
- 3
Where the risk concentrates
All 12 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 |
|---|---|---|---|---|
| cli.pyautotune | 99.3th %ile | 14bug magnet | 1bus factor 1 | 15 |
| server.pyautotune/api | 98.6th %ile | 8bug magnet | 1bus factor 1 | 8 |
Read more about tanavc1/local-llm-autotune
- 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 docsProModule-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 keeps the index refreshing weekly.
[](https://repowise.dev/repo/tanavc1/local-llm-autotune)Code health badge
Average health across every file, straight from the latest index.
[](https://repowise.dev/repo/tanavc1/local-llm-autotune)How tanavc1/local-llm-autotune works
Zero-config local LLM optimization for Ollama, LM Studio, and Apple Silicon MLX. Reduces TTFT by 40%, wall time for local agents by 46%, and RAM usage by 3x. This page is an auto-generated, always-fresh map of the tanavc1/local-llm-autotune repository, written primarily in Python. 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 168 source files, 3,064 symbols, and 11 languages, organised into 33 modules, led by python, yaml, markdown. Static analysis leaves 1,314 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.