ainetcafe provider for pi: Kimi K3 served from ainetcafe's own cluster at native MXFP4 ($2.10 / $10.50 per M tokens), OpenAI-compatible, with thinking-level mapping and live model discovery.

Local Qwen3-ASR transcription and realtime meeting capture on Apple Silicon.

Node.js bindings for llama.cpp with QBNN architecture support

Run your favorite LLMs (Qwen, Gemma4, NemotronH, DharaAR, ...) at blazing-fast speeds on Apple Silicon, with multi-modal (image/audio/video) support, from JavaScript/TypeScript.

Route your test suite through every AI provider hosting your model; compare cost-per-passing-outcome and trajectory quality locally.

Check what a quantized tensor actually means: GRIT descriptors carry the full numeric contract (element format, group sizes, scale formats, zero points, sparsity, rounding) as 64 bytes with a 64-bit id, verifiable against the bytes in O(1). Spec v1, zero

OpenClaw provider plugin for ainetcafe (Kimi K3 at native MXFP4, OpenAI-compatible, https://microquickjs.com/v1).