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
facebookresearch
Meta's self-supervised video learning framework achieving state-of-the-art motion understanding and zero-shot robotics transfer.
simular-ai
Open-source GUI agent enabling AI to autonomously use computers with 72.6% accuracy on OSWorld, surpassing human-level performance.
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.
ace-step
Open-source music generation foundation model combining diffusion and linear transformers, generating 4 minutes of music in 20 seconds.
QwenLM
Alibaba's most powerful open-source vision-language model with 256K context, spatial reasoning, and visual agent capabilities.
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.
NVIDIA
Python framework for GPU-accelerated simulation, spatial computing, and differentiable 3D physics.
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.
canopyai
State-of-the-art open-source TTS built on Llama-3b with zero-shot voice cloning, emotional control, and sub-200ms streaming latency.