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
AIDC-AI
An AI-powered fully automated short video engine by AIDC-AI that generates complete videos from a single topic input, handling script, visuals, TTS, and BGM via ComfyUI-based pipeline.
microsoft
Microsoft's open-source framework for training and optimizing AI agents via reinforcement learning and prompt optimization, compatible with LangChain, OpenAI SDK, AutoGen, and CrewAI.
virattt
An open-source educational multi-agent AI framework simulating a hedge fund team with 13 investor personas and 5 specialist agents for stock analysis and trading decisions.
vectorize-io
Agent memory system that organizes memories biomimetically into world facts, experiences, and mental models, with multi-strategy retrieval achieving SOTA on the LongMemEval benchmark.
massgen
Open-source multi-agent scaling system that runs in your terminal, orchestrating Claude, GPT-5, Gemini, and Grok to collaborate and vote on the best solution to complex problems.
vllm-project
Unified omni-modality serving framework extending vLLM to support text, image, video, and audio inference with OpenAI-compatible APIs and disaggregated pipeline architecture.
NousResearch
Nous Research's self-improving AI agent with built-in learning loops, persistent memory, and multi-platform deployment across 200+ LLM providers.
google-ai-edge
Google's production-ready open-source inference framework for deploying LLMs on edge devices — Android, iOS, Web, Desktop, and IoT — with GPU and NPU acceleration.
HKUDS
HKUDS's agent-native personalized learning platform combining five AI modes—chat, deep solve, quiz, research, and math animation—in a unified open-source system.
SJTU-IPADS
High-speed LLM inference engine for consumer GPUs using neuron activation sparsity, achieving up to 11.69x speedup over llama.cpp.
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.