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.
492 projects
facebookresearch
Meta's self-supervised video learning framework achieving state-of-the-art motion understanding and zero-shot robotics transfer.
QwenLM
Alibaba's most powerful open-source vision-language model with 256K context, spatial reasoning, and visual agent capabilities.
ace-step
Open-source music generation foundation model combining diffusion and linear transformers, generating 4 minutes of music in 20 seconds.
OpenBMB
Tokenizer-free TTS system with context-aware prosody generation and true-to-life zero-shot voice cloning, trained on 1.8M hours of audio.
XiaomiMiMo
Xiaomi's open-source 309B MoE model with 15B active params, ranking #1 on SWE-bench among open-source models.
InsForge
Open-source backend platform built for AI coding agents with semantic layer for databases, auth, storage, and edge functions.
opendataloader-project
Benchmark-leading open-source PDF parser producing AI-ready structured data with hybrid AI engine and LangChain integration.
state-spaces
Linear-time state space model architecture for efficient sequence modeling, rivaling Transformers.
UbiquitousLearning
Fast, lightweight multimodal LLM inference engine for mobile and edge devices with NPU support.
NVIDIA
Python framework for GPU-accelerated simulation, spatial computing, and differentiable 3D physics.
canopyai
State-of-the-art open-source TTS built on Llama-3b with zero-shot voice cloning, emotional control, and sub-200ms streaming latency.
alibaba
Unified framework for audio processing and generation that handles speech restoration, separation, voice conversion, and more in a single model.