media streaming framework and teleconferencing system written in rust
- rust
- rust-lang
- zoom
- actix-web
111,085 visible repositories in the index
25–47 of 47 · Most stars
media streaming framework and teleconferencing system written in rust
NobodyWho is an inference engine that lets you run LLMs locally and efficiently on any device.
Translated清风输入法 (Qingfeng Input Method, "gentle breeze input method") | A lightweight, fast, customizable open-source Chinese input method, designed specifically for Wubi and code table input schemes, supporting full Pinyin/double Pinyin (Windows / macOS / Linux)
Import .sql files into TypeScript with full type inference and zero codegen.
Generate Nix packages from URLs with hash prefetching, dependency inference, license detection, and more [maintainer=@figsoda]
Jev-compatible API server for open decision models. Ollama for decision models: pull and serve 29 model families (Laya, pplx-decider, Clef, Winnow, coba...) locally or self-hosted behind /v1/systemone. The TypeSafe SDK works unchanged: set its base URL and pick an open model. CLI, desktop app, Docker, MCP server, public bench.
TranslatedAntigravity in Russia without a VPN and without changing the region of your Google account
Distributed zkML
Highly Performant, Modular, Memory Safe and Production-ready Inference, Ingestion and Indexing built in Rust 🦀
JSTprove - Fast, verifiable AI
ezkl is an engine for doing inference for deep learning models and other computational graphs in a zk-snark (ZKML). Use it from Python, Javascript, or the command line.
Run, serve, query and edit AI models — a Rust model runtime built on VINDEX3, an executable, inspectable model format.
AI-native, cloud-native file system in Rust. Full POSIX on object storage with a multi-tier distributed cache, for AI training, inference, and agents. CNCF Sandbox project.
Minimal LLM inference in Rust
Perplexity open source garden for inference technology
An open-source computer vision framework to build and deploy apps in minutes
A Rust port of parinfer.
[MIRROR] unofficial implementation of Dante protocol (Audio over IP)
Pure-Rust inference engine for Qwen GGUF models (Qwen3 to Qwen3.8, dense and MoE up to 770B+). CUDA and Vulkan (NVIDIA, AMD), hybrid CPU+GPU experts, MTP speculative decoding, OpenAI and Anthropic compatible server. Up to ~1.7x llama.cpp decode on a 12 GB RTX 3060.
TypeQL: Built for systems, not records
Streaming-first load balancer for AI inference gateways
Auto Nix GC Root Retention
Modern desktop application (Rust + Tauri v2 + Svelte 5 + Candle (HF)) for communicating with AI models that runs completely locally on your computer. No subscriptions, no data sent to the internet — just you and your personal AI assistant