Blazing-fast LLM inference in pure Rust. No PyTorch and Python runtime.
Archive
Realistic first-contribution target: active project, 29 open issues, small enough for a newcomer PR to land.
Derived from this repo's Cargo dependencies and activity — difficulty is an estimate from codebase size and scope.
Matched by dependency overlap in Cargo manifests — each card notes the most distinctive crates both projects share.
Blazing-fast LLM inference in pure Rust. No PyTorch and Python runtime.
Fast, flexible LLM inference
Rust library for generating vector embeddings, reranking locally!
Extracting paths from assembly graphs
Mock REST APIs from JSON with zero coding within seconds.
Nix Package Tool. A (humble) successor to linux's apt, which makes life easier when using nix as a package manager.
A Pure Rust based LLM, VLM, VLA, TTS, OCR Inference Engine, powering by Candle & Rust. Alternate to your llama.cpp but much more simpler and cleaner..
⚡ Pure-Rust WebGPU inference engine — OpenAI-API compatible, GGUF native, runs on any GPU. No Python. No llama.cpp. Single binary.
Open-Source Platform for Subagents and Agent Teams. Long-running, collaborative, proactive.