Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
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.
| Date | Stars |
|---|---|
| 2026-07-24 | 3386 |
| 2026-07-25 | 3399 |
| 2026-07-28 | 3399 |
| 2026-07-30 | 3399 |
| 2026-07-31 | 3387 |
| 2026-08-01 | 3391 |
| 2026-08-02 | 3391 |
| 2026-08-03 | 3391 |
| 2026-08-04 | 3396 |
| 2026-08-05 | 3405 |
| 2026-08-06 | 3406 |
Today
+1 stars today
This week
+7 stars this week
This month
— stars this month
Momentum
46.0
growth rate 0.21%/day
<img width="1600" height="800" alt="banner" src="https://github.com/user-attachments/assets/f3743bb7-7287-4b24-ac97-a7037974396f" />
<p align="center">
<strong>The fastest local AI engine for Apple Silicon.</strong>
<br>
<em>Drop-in OpenAI / Anthropic API · 2–4× faster than Ollama · Runs on any M-series Mac.</em>
</p>
<p align="center">
<a href="https://pypi.org/project/rapid-mlx/"><img src="https://img.shields.io/pypi/v/rapid-mlx?color=blue&label=PyPI" alt="PyPI"></a>
<a href="https://formulae.brew.sh/formula/rapid-mlx"><img src="https://img.shields.io/badge/Homebrew-core-orange?logo=homebrew" alt="Homebrew core"></a>
<a href="https://www.python.org/downloads/"><img src="https://img.shields.io/badge/python-3.10+-blue.svg" alt="Python 3.10+"></a>
<a href="https://support.apple.com/en-us/HT211814"><img src="https://img.shields.io/badge/Apple_Silicon-M1%20|%20M2%20|%20M3%20|%20M4-black.svg?logo=apple" alt="Apple Silicon"></a>
<a href="LICENSE"><img src="https://img.shields.io/badge/License-Apache_2.0-blue.svg" alt="License"></a>
</p>
<p align="center">
<a href="https://github.com/raullenchai/Rapid-MLX/actions/workflows/ci.yml"><img src="https://github.com/raullenchai/Rapid-MLX/actions/workflows/ci.yml/badge.svg" alt="CI"></a>
<a href="https://github.com/raullenchai/Rapid-MLX/stargazers"><img src="https://img.shields.io/github/stars/raullenchai/Rapid-MLX?style=social" alt="GitHub stars"></a>
<a href="https://github.com/raullenchai/Rapid-MLX/graphs/contributors"><img src="https://img.shields.io/github/contributors/raullenchai/Rapid-MLX?color=orange" alt="Contributors"></a>
<a href="https://github.com/raullenchai/Rapid-MLX/commits/main"><img src="https://img.shields.io/github/last-commit/raullenchai/Rapid-MLX?color=orange" alt="Last commit"></a>
<a href="https://deepwiki.com/raullenchai/Rapid-MLX"><img src="https://deepwiki.com/badge.svg" alt="Ask DeepWiki"></a>
</p>
<p align="center">
<sub>
<a href="https://rapidmlx.com"><b>rapidmlx.com</b></a> ·
<a href="https://rapidmlx.com/docs/">Docs</a> ·
<a href="https://models.rapidmlx.com/">Model mirror</a> ·
<a href="https://rapidmlx.com/desktop">Desktop app</a>
</sub>
</p>
---
## Quick Start (60 seconds)
**1. Install** — pick one path (run only one of these):
Homebrew — prebuilt bottle straight from homebrew-core (recommended):
```bash
brew install rapid-mlx
```
or the one-liner — detects your RAM, picks a starter model:
```bash
curl -fsSL https://rapidmlx.com/install.sh | bash
```
Both land the same `rapid-mlx` CLI. The curl installer additionally installs Python 3.10+ if missing, creates an isolated venv at `~/.rapid-mlx/`, symlinks the `rapid-mlx` CLI into `~/.local/bin/`, and prints a serve command sized to your Mac (8–23 GB → `qwen3.5-4b-4bit`; 24–47 GB → `gpt-oss-20b-mxfp4-q8`; 48–95 GB → `qwen3.6-35b-8bit`; 96 GB+ → `gpt-oss-120b-mxfp4-q8`).
> **Install security.** `install.sh` is served over HTTPS (HSTS-preload) from `rapidmlx.com` and is a byte-identical mirror of [`install.sh`](install.sh) at the release commit — read it before running if you like. If you want a cryptographically verified installer rather than trusting the website pipe, don't `curl | bash` the URL above: instead download the release's `install.sh` asset, verify it against the cosign-signed `SHA256SUMS.txt` shipped alongside it, and run that verified copy — full recipe in [SECURITY.md](SECURITY.md). PyPI artifacts additionally carry Sigstore attestations (PEP 740). Two more low-trust paths:
> - **Pin to a commit hash** — `curl -fsSL https://raw.githubusercontent.com/raullenchai/Rapid-MLX/<commit>/install.sh -o install.sh && shasum -a 256 install.sh && bash install.sh`
> - **Skip the shell script entirely** — use Homebrew, `uv`, or `pip` below.
See [Alternative install methods](#alternative-install-methods) for the non-curl paths.
**2. Chat with a model right now:**
```bash
rapid-mlx chat
```
Defaults to `qwen3.5-4b-4bit`. First run downloads the weigExcerpt of 15,040 characters
Read on GitHub
891
98
Jan Hilgard · Czech Republic
12
Mason James · Mason James, LLC · United States
5
3
3
3
corruptbytes · Twilio · United States
2
Willow Lopez
2
2
2
2
Ton Sharp · @Oracle · Ukraine
2
2
1
Kushida
1
1
1
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:7d4c57c2547a53df, topic:llm, topic:qwen
matched fp:7d4c57c2547a53df, topic:inference
matched fp:7d4c57c2547a53df, topic:tool-calling