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
chroma-core
Open-source AI data infrastructure providing vector, hybrid, and full-text search with automatic embedding, metadata filtering, and both self-hosted and cloud deployment options.
elizaOS
Open-source multi-agent AI framework for building and deploying autonomous agents with Discord, Telegram, Farcaster connectors and support for all major LLM providers.
pytorch
PyTorch's on-device AI inference engine for mobile, embedded, and edge deployment with a 50KB runtime footprint and 12+ hardware backends.
MemPalace
Local-first AI memory system with 96.6% LongMemEval recall, storing conversations verbatim in a structured palace architecture with zero cloud dependency.
jundot
LLM inference server optimized for Apple Silicon with continuous batching, tiered SSD KV caching, and native macOS menu bar management.
SJTU-IPADS
High-speed LLM inference engine for consumer GPUs using neuron activation sparsity, achieving up to 11.69x speedup over llama.cpp.
axolotl-ai-cloud
Open-source LLM fine-tuning framework supporting 100+ models with YAML config, PEFT, LoRA, DPO, and multi-GPU training.
Comfy-Org
The most powerful and modular visual AI engine with node-based graph interface supporting SD, Flux, video, 3D, and audio generation.
microsoft
Microsoft's CVPR 2025 foundation model for multimodal AI agents, unifying visual understanding with action generation across digital and physical worlds.
KoljaB
Low-latency text-to-speech library with 20+ engine support, real-time LLM output streaming, and automatic fallback for production applications.
k2-fsa
Offline speech-to-text, TTS, speaker diarization, and VAD toolkit supporting 12 programming languages and deployment on everything from Raspberry Pi to NPUs.
antirez
Pure C inference engine for Mistral's Voxtral Realtime 4B speech-to-text model with zero external dependencies and live mic support.