rapid-mlx
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.
- Latest release
- 9h ago
- Releases
- 105
- Known CVEs
- 0
- First release
- Mar 21, 2026
- License
- Apache-2.0
Repository
Source
- Stars
- 2.7k
- Forks
- 335
- Open issues
- 26
- Language
- Python
- apple-silicon
- fastapi
- inference
- llm
- local-llm
- macos
- mlx
- openai-api
Security score
No OpenSSF Scorecard available for this repository.
Packages from this repo
No other tracked packages from this repository.
Insights
Activity
- Total releases
- 105
- Last 12 months
- 105
- Cadence
- ~daily
- Dependencies
- 49
Releases per month
last 12 monthsRelease mix
- minor 4
- patch 100
105
releases
Dependencies
Depends on
0.7.0-
argcomplete
>=3.6
-
black
>=23.0.0
-
cn2an
>=0.5.0
-
fastapi
>=0.100.0
-
fugashi
>=1.3.0
-
gradio
>=4.0.0
-
huggingface-hub
>=0.23.0
-
jieba
>=0.42.0
-
jsonschema
>=4.0.0
-
loguru
>=0.7.0
1–10 of 49
Used by
Nothing tracked depends on this yet.
Releases
| Version | Released | |
|---|---|---|
0.7.0
minor
| ||
0.6.83
patch
| ||
0.6.82
patch
| ||
0.6.81
patch
| ||
0.6.80
patch
| ||
0.6.79
patch
| ||
0.6.78
patch
| ||
0.6.77
patch
| ||
0.6.76
patch
| ||
0.6.75
patch
| ||
0.6.74
patch
| ||
0.6.73
patch
| ||
0.6.72
patch
| ||
0.6.71
patch
| ||
0.6.70
patch
| ||
0.6.69
patch
| ||
0.6.68
patch
| ||
0.6.66
patch
| ||
0.6.65
patch
| ||
0.6.64
patch
|
1–20 of 105