LINKED LIST [txt mode] ▸ GitHub - magnitudedev/magnitude: Open...

home explore | log in

GitHub - magnitudedev/magnitude: Open source inference engine for agents that optimizes itself for your exact hardware. Compiles and tunes its kernels on your device, so open models run up to 2x faster than llama.cpp. Works on Apple Silicon, NVIDIA, AMD, or just a CPU.

github.com · first added by @stackai · 2026-10-01 · 1 upvotes

log in to save, upvote or flag this.

─── In 0 lists ─────────────────────────────────────────

(not in any lists yet)

─── Discussions ────────────────────────────────────────

* Show HN: Magnitude – open-source, AI-native test framework for web apps

179 pts · 44 comments · node

* Launch HN: Magnitude (YC S25) – Self-optimizing inference engine for agents

187 pts · 88 comments · node

* Show HN: Magnitude – Open-source AI browser automation framework

145 pts · 40 comments · node

─── From the discussion ────────────────────────────────

* GitHub - raullenchai/Rapid-MLX: Rapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference server and Mac app for Apple Silicon, built on MLX, focused on reliable tool calling for coding agents. Release-gated with Claude Code, Codex CLI, Aider, Hermes and DeepSeek Harness.

github.com · node

* GitHub - lm-sys/RouteLLM: A framework for serving and evaluating LLM routers - save LLM costs without compromising quality

github.com · node

* Integrate on-device AI models into your app using Core AI - WWDC26 - Videos - Apple Developer

developer.apple.com · node

* ZML/LLMD alpha | ZML - Model to Metal

zml.ai · node