Skip to main content
Drop a repoSign up
NEWssmmtt/Xpassjust droppedNEWvicrodh/qbzjust droppedNEWkowalski-ptr/compass-before-compactjust droppedREPOdocker-desktop-windows/docker-desktop+93 stars 24hREPOcslol-manager/ltk-manager+83 stars 24hREPOV0id-v2/Void-Tools-v2.0+50 stars 24hREPOjackwener/wx-cli+42 stars 24hREPOalistaitsacle/free-llm-api-keys+27 stars 24hNEWssmmtt/Xpassjust droppedNEWvicrodh/qbzjust droppedNEWkowalski-ptr/compass-before-compactjust droppedREPOdocker-desktop-windows/docker-desktop+93 stars 24hREPOcslol-manager/ltk-manager+83 stars 24hREPOV0id-v2/Void-Tools-v2.0+50 stars 24hREPOjackwener/wx-cli+42 stars 24hREPOalistaitsacle/free-llm-api-keys+27 stars 24h
raullenchai/Rapid-MLXpublicPythongithub.com/raullenchai/Rapid-MLX
raullenchai avatar

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.

AGENT SKILLSCLAUDE CODELLM INFRALOCAL LLMAPPLE SILICONFASTAPITRENDING #387

// OWNER · raullenchai · REPO SNAPSHOT

github.com/raullenchai

raullenchai

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.

STARS3,447+125 · 7d
FORKS399+0 · 7d
CONTRIBUTORS0maintainer graph thin
OPEN ISSUES · PRS20· 0 
LICENSEno license file
LANGUAGEPython 
FOUNDED
LOCATION
MEMBERS
PUBLIC REPOS
TOTAL STARS
FOCUS
FUNDING

//STAR HISTORY · 12M

+3,193 all-time-window
Stars · cumulative3,444 · today
//WHY IT'S TRENDING· narrative synthesis · medium confidence

raullenchai/Rapid-MLX is sitting at #387 on the trending leaderboard with a pulse of 21/100 with no cross-source channels firing yet — GitHub-stars-only signal so far.

The 7-day star delta is +125 (+3.8%) against a base of 3,447, a meaningful uptick on its own base. What's actually moving is the AI agent / LLM tooling stack.

Watch-outs: no tagged release on record (treat as pre-stable).

↻ refreshed 11m ago· next sync in 54m· sourced from 0 channels · 0 mentions / 24h

FAQ · answers from the data spine

What is raullenchai/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.
Who maintains Rapid-MLX?
Maintained by raullenchai (the owner) on GitHub.
What language is Rapid-MLX written in?
Primarily Python.
When was Rapid-MLX created? When was the last update?
Created February 25, 2026 · last commit July 29, 2026.
How do I install Rapid-MLX?
Clone the repo:
git clone https://github.com/raullenchai/Rapid-MLX.git
Then follow the README in the cloned directory.
Is Rapid-MLX actively maintained?
yes — actively maintained (recent commits)

//COMMENTS · 0

live thread · operators only

Sign in to join the discussion

Be the first to comment.
Created
Updated
Last commit
Repositoryraullenchai/Rapid-MLX