Open Source
Explore the latest AI open-source projects from GitHub and HuggingFace.
Explore the latest AI open-source projects from GitHub and HuggingFace.
Explore the latest AI open-source projects from GitHub and HuggingFace. Discover projects across categories like LLM, Vision, Audio, and more.
625 projects
deepseek-ai
An open-weight 671B-parameter Mixture-of-Experts LLM (37B active per token) that matches leading closed models, notable for FP8 training and a detailed efficiency report.
open-webui
A feature-rich, self-hosted AI platform that puts a ChatGPT-style interface over local and API-based models, with built-in RAG, web search, voice, and team controls.
sgl-project
A high-performance, Apache-2.0 serving framework for LLMs and multimodal models, featuring RadixAttention prefix caching and day-0 support for major open models.
CAMEL-AI
A research-driven, open-source multi-agent framework for building scalable, stateful agent societies — built to find the "scaling laws of agents." Apache-2.0 licensed.
Tripo AI & Stability AI
A state-of-the-art open-source model from Tripo AI and Stability AI that reconstructs a 3D mesh from a single image in under 0.5 seconds on an A100 — MIT licensed.
Stability AI
Stability AI's open-source toolkit for training, fine-tuning, and running generative audio models — the codebase behind the openly licensed Stable Audio Open.
CJ Pais
A free, open-source, cross-platform speech-to-text app that transcribes your voice entirely offline — press a shortcut, speak, and have the text pasted into any app.
OpenBMB
OpenBMB's pocket-sized multimodal LLM series delivering GPT-4V-class image and video understanding that runs efficiently on phones and edge devices — no cloud required.
ByteDance
ByteDance's open-source TTS system delivering high-quality zero-shot voice cloning from a lightweight 0.45B-parameter diffusion transformer, with bilingual Chinese/English support.
DeusData
A single-binary code intelligence engine that indexes repositories into a persistent knowledge graph across 158 languages, cutting agent token use by up to 120x via 14 MCP tools.
Jamie Pine
A local-first, open-source AI voice studio that clones voices, generates speech across 23 languages and 7 TTS engines, dictates into any app, and gives MCP agents a voice you own.
Palmier
An open-source, Swift-native macOS video editor where you and an AI agent generate and edit video together in the timeline, with SOTA generation and MCP agent integration.