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.
310 projects
pipecat-ai
Open-source Python framework for real-time voice and multimodal conversational AI with 20+ STT/TTS/LLM providers and 10.6K+ GitHub stars.
open-webui
Self-hosted AI platform with 127K+ stars supporting Ollama, OpenAI APIs, built-in RAG with 9 vector databases, and enterprise access controls.
dora-rs
A Rust-based AI robotics middleware claiming 10-17x faster performance than ROS2, with zero-copy Apache Arrow data transfer and multimodal AI model integration.
huggingface
Hugging Face's open-source robotics framework providing standardized models, datasets, and DIY robot tools for accessible end-to-end robot learning. ICLR 2026 accepted.
Genesis-Embodied-AI
A GPU-accelerated generative physics engine for robotics and embodied AI, achieving 43M+ FPS on a single RTX 4090 with unified multi-material simulation.
microsoft
Microsoft's official 1-bit LLM inference framework achieving 1.37x-6.17x speedup and up to 82% energy reduction, enabling 100B parameter models to run on consumer CPUs.
isaac-sim
NVIDIA's GPU-accelerated open-source framework for robot learning, offering photorealistic sim-to-real training with 4,096+ parallel environments on Isaac Sim.
fishaudio
A 4B+ parameter SOTA open-source TTS system trained on 10M+ hours of audio across 50 languages, featuring dual-autoregressive architecture and fine-grained inline emotion control.
langflow-ai
Open-source visual platform for building AI agents and workflows with 145k+ stars, drag-and-drop interface, and full Python customization
vllm-project
High-throughput, memory-efficient LLM inference engine with PagedAttention, 72.8k stars, powering production LLM deployment worldwide
ultralytics
Definitive real-time computer vision framework with 54k+ stars, YOLO26 NMS-free inference, and multi-task support for detection, segmentation, and pose estimation
nari-labs
A 1.6B parameter TTS model by Nari Labs that generates ultra-realistic multi-speaker dialogue in a single pass, supporting voice cloning and non-verbal expressions.