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
DeusData
A single-binary code intelligence engine that indexes repositories into a persistent knowledge graph across 158 languages, cutting agent token use by up to 120x via 14 MCP tools.
Palmier
An open-source, Swift-native macOS video editor where you and an AI agent generate and edit video together in the timeline, with SOTA generation and MCP agent integration.
Jamie Pine
A local-first, open-source AI voice studio that clones voices, generates speech across 23 languages and 7 TTS engines, dictates into any app, and gives MCP agents a voice you own.
ByteDance
ByteDance's MIT-licensed super agent harness that orchestrates sub-agents, memory, and sandboxes for long-horizon research, coding, and creation.
Tencent Hunyuan
Tencent's open-source diffusion system that turns a single image or text prompt into high-resolution, textured 3D assets.
vLLM Project
A high-throughput, memory-efficient LLM inference and serving engine built around PagedAttention, with an OpenAI-compatible API and 200+ model support.
ByteDance Seed
ByteDance Seed's open-source unified multimodal model that combines image-text understanding with image generation in a single Mixture-of-Transformer-experts architecture.
RVC-Boss
Open-source WebUI for few-shot and zero-shot voice cloning and text-to-speech, producing a usable voice from as little as a 5-second sample.
Collabora
Collabora's near-real-time speech-to-text server built on OpenAI Whisper, with faster-whisper, TensorRT-LLM, and OpenVINO backends.
zai-org
Z.ai's flagship open-source LLM for complex systems engineering and long-horizon agentic tasks, scaling to 744B parameters with sparse attention and a 1M-token context in the latest GLM-5.2.
PaddlePaddle
A global-leading open-source OCR toolkit and Document AI engine that turns PDFs and images into structured, LLM-ready JSON and Markdown, powered by the lightweight PaddleOCR-VL vision-language model.
QwenLM
An open-source TTS series from Alibaba's Qwen team (0.6B/1.7B) delivering human-like speech with voice cloning, voice design, 10-language coverage, and ~97ms streaming latency.