Rust
Best Way to Run 31B Models on a Laptop? Treat Them Like Databases
LARQL decompiles transformer weights into a queryable graph called a vindex. The project pitches a new shape for local inference: walk a subgraph, patch facts, stream from disk. Here's what's real, what's claimed, and what's still research.
Crane + Qwen3-TTS: Run Voice Cloning Locally with Rust
Clone any voice with 3 seconds of audio using Qwen3-TTS through Crane's pure Rust inference engine. ~4GB VRAM, faster than real-time, Apache 2.0.
LocalAgent: A Local-First Agent Runtime That Actually Cares About Safety
Rust CLI for AI agents with deny-by-default permissions, approval workflows, and deterministic replay. Works with LM Studio, Ollama, and llama.cpp.