Rapid-MLX
piclaw
| Rapid-MLX | piclaw | |
|---|---|---|
| 6 | 35 | |
| 2,756 | 725 | |
| 90.1% | 16.7% | |
| 9.8 | 5.8 | |
| 4 days ago | 5 days ago | |
| Python | TypeScript | |
| Apache License 2.0 | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Rapid-MLX
-
Chrome's Gemini Nano Prompt API: A Step-by-Step Guide
💡 💡 Make the fallback cheap to operate. The whole point of using Nano on the supported path is reduced cost. If your fallback is GPT-5.5 at $5/M tokens, you've moved the bill, not deleted it. Two patterns work well: (1) route the fallback to a smaller hosted model (Haiku, Gemini Flash, Mistral Small) that matches Nano's "short summarization" sweet spot; (2) for Mac users specifically, run Rapid-MLX as your /api/llm endpoint — Apple Silicon owners get on-device performance via your server's Mac, not theirs. Same thesis as our DeepClaude guide: the harness is one product, the model is another, and you can swap them.
-
Anthropic is allowing the Claude CLI to run OpenClaw again
> Large-context requests auto-route to a cloud LLM (GPT-5, Claude, etc.) when local prefill would be slow. Routing based on new tokens after cache hit. --cloud-model openai/gpt-5 --cloud-threshold 20000
https://github.com/raullenchai/Rapid-MLX
- Show HN: Rapid-MLX – Run local LLMs on Mac, 2-3x faster than alternatives
-
Gemma 4 on Apple Silicon: 85 tok/s with a pip install
I've verified this end-to-end with structured output (output_type=BaseModel), streaming, multi-turn conversations, and multi-tool workflows. Test suite here.
-
vLLM-mlx – 65 tok/s LLM inference on Mac with tool calling and prompt caching
pip install git+https://github.com/raullenchai/vllm-mlx.git
piclaw
- Paseo – Beautiful open-source coding agent interface (desktop, mobile, CLI)
- Claude Code and Codex Can Have Real-Time Conversation via Git
- Release PiClaw v2.4.0 – The Infosphere · rcarmo/piclaw
- Piclaw – pi in a Technicolor web trenchcoat
-
Ask HN: What Are You Working On? (May 2026)
I’m stabilizing piclaw (https://rcarmo.github.io/projects/piclaw) - it is now my main IDE for all my personal projects, and I run several instances with different plugins. This is _not_ an OpenClaw clone, it is pi in a web trenchcoat, with (I hope) most of the philosophy in place.
I am also working on various other things (a Go Clojure interpreter with IR/WASM, my own inference library, etc.). All are linked from the page above to a degree.
- Release PiClaw v2.3.0 – Tirion upon Túna · rcarmo/piclaw
- Release PiClaw v2.2.2 – Lothlórien · rcarmo/piclaw
- Release PiClaw v2.1.0 – Coruscant · rcarmo/piclaw
- Release PiClaw v2.0.4 – Chapek 9 · rcarmo/piclaw
- Release PiClaw v2.0.3 – Wormulon · rcarmo/piclaw
What are some alternatives?
Sacred - Sacred is a tool to help you configure, organize, log and reproduce experiments developed at IDSIA.
oh-my-pi - ⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and more
MindsDB - General-purpose AI designed for knowledge workers — creators, strategists, and operators — and individuals seeking AI systems they can truly control to help them get work done, with full flexibility to extend and deploy anywhere (VPC, on-prem, or cloud).
pi_agent_rust - High-performance AI coding agent CLI written in Rust with zero unsafe code
gym - A toolkit for developing and comparing reinforcement learning algorithms.
openclaw-stack - Deploy a secure OpenClaw to any VPS using Claude Code.