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.
760 projects
2noise
A dialogue-optimized open TTS model trained on 100,000+ hours that adds fine-grained prosody — laughter, pauses, interjections — with multi-speaker, English/Chinese support.
Plachtaa
A zero-shot voice and singing voice conversion model that clones a voice from a 1–30s reference clip with no training, including a real-time (~300ms) conversion mode.
IDEA-Research
An open-set object detector that locates objects from arbitrary natural-language prompts, marrying the DINO detector with grounded pre-training for strong zero-shot detection.
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.
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.
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.
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.
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.