Stars
Memory Sparse Attention - A scalable, end-to-end trainable latent-memory framework for 100M-token contexts.
A verified tool that works on any potato computer that will let you bypass discord verification
Performant, batteries-included completion plugin for Neovim
JavaScript/TypeScript-native, low-boilerplate, object-capability RPC system
Haptic input knob with software-defined endstops and virtual detents
AppCUI is a fast, cross-platform console and text-based user interface (CUI/TUI) framework for Rust. It combines a low-level console engine for input (mouse, keyboard, clipboard, etc.), colors, and…
Development environments for coding agents. Enable multiple agents to work safely and independently with your preferred stack.
Cross-platform AirDrop. File transfer between Android, iOS, Linux, macOS, and Windows over ad hoc WiFi. No network infrastructure required, just two devices with WiFi chips (and optionally Bluetoot…
A Flipper Zero clone, but cheapest, DIY and simply Open Source, made with Arduino IDE
Monorepo for Javascript WebAssembly packages by Wasmer
EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine
Comfortably monitor your network traffic 🕵️♂️
media streaming framework and teleconferencing system written in rust
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
SoTA LLM for converting natural language questions to SQL queries
Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable…
JAX implementation of OpenAI's Whisper model for up to 70x speed-up on TPU.
StableLM: Stability AI Language Models
Turbopilot is an open source large-language-model based code completion engine that runs locally on CPU
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
A markup-based typesetting system that is powerful and easy to learn.
antimatter15 / alpaca.cpp
Forked from ggml-org/llama.cppLocally run an Instruction-Tuned Chat-Style LLM
Port of OpenAI's Whisper model in C/C++