raullenchai-Rapid-MLX SantoshSrinivas79 · PARTIAL
The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.
github.com/SantoshSrinivas79/raullenchai-Rapid-MLX · ★ 0 · Forks 0 · Size 20.0 MB
SUMMARY
Technologies 19
Scored 16
Observed 16
Practices 6
Evidence 20
Skips 3
COVERAGE
Analyzed 681 files · 590 commits · 0 API calls
TECHNOLOGIES & DEPTH
Shell LANGUAGE Depth 70
9 files · PRODUCTION
JSON LANGUAGE Depth 70
182 files · PRODUCTION
Markdown LANGUAGE Depth 70
48 files · PRODUCTION
TOML LANGUAGE Depth 70
2 files · PRODUCTION
YAML LANGUAGE Depth 70
28 files · PRODUCTION
Python LANGUAGE Depth 70
388 files · PRODUCTION
Poetry BUILD_TOOL Depth 80
1 files · CONFIGURATION
Black QUALITY Depth —
0 files · config only
FastAPI FRAMEWORK Depth 78
30 files · PRODUCTION, TEST
MongoDB DATABASE Depth 65
1 files · CONFIGURATION
NumPy LIBRARY Depth 81
22 files · PRODUCTION, TEST
Pydantic LIBRARY Depth 78
10 files · PRODUCTION, TEST
Requests LIBRARY Depth 85
18 files · PRODUCTION, TEST
Ruff QUALITY Depth —
0 files · config only
Starlette FRAMEWORK Depth 74
4 files · PRODUCTION, TEST
TypeScript LANGUAGE Depth 78
12 files · PRODUCTION, TEST
Uvicorn LIBRARY Depth 74
4 files · PRODUCTION, TEST
mypy QUALITY Depth —
0 files · config only
pytest TESTING Depth 74
104 files · PRODUCTION, TEST
PRACTICES
documentation · observedautomated_tests · observedcontinuous_integration · observedcontainerization · absentlinting · observedformatting · absent
ACTIVITY & OWNERSHIP
First commit 2025-12-06
Last commit 2026-05-29
Active months 6
Commits 590