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.
352 projects
kvcache-ai
Heterogeneous CPU-GPU LLM inference framework enabling DeepSeek-R1-671B on consumer hardware.
onyx-dot-app
Open-source AI platform with enterprise RAG, deep research, custom agents, and 50+ connectors that works with any LLM.
FunAudioLLM
Multilingual voice understanding model with ASR, emotion, and event detection
google-deepmind
Google's frontier open multimodal model family with 140+ language support
neuphonic
On-device super-realistic TTS with instant voice cloning on a 0.5B LLM backbone
DepthAnything
Foundation model for monocular depth estimation with 7.8k+ GitHub stars, delivering state-of-the-art depth maps from single images across 25M to 1.3B parameter variants.
NVIDIA
Unified model optimization library for LLM inference acceleration
myshell-ai
Instant voice cloning framework by MIT and MyShell with 36k+ GitHub stars, enabling zero-shot cross-lingual voice replication from just seconds of reference audio.
browserbase
AI-powered browser automation framework with natural language control
langchain-ai
The dominant open-source agent engineering platform for building LLM-powered applications with 132k+ GitHub stars, supporting chains, agents, RAG, and multi-provider LLM integration.
github
GitHub's toolkit for Spec-Driven Development with AI coding agents
ggml-org
Pure C/C++ LLM inference engine supporting CPUs, Apple Silicon, CUDA, and Vulkan