Open Source
Explore the latest AI open-source projects from GitHub and HuggingFace.
Explore the latest AI open-source projects from GitHub and HuggingFace.
MiniCPM-o is an open-source omnimodal large language model from OpenBMB, designed to run on-device with Gemini 2.5 Flash-level performance. Built on 8B parameters with SigLip-400M, Whisper-medium-300M, ChatTTS-200M, and Qwen2.5-7B components, it supports full-duplex multimodal live streaming, real-time vision, speech, and video understanding. It achieves 70.2 on OpenCompass and outperforms GPT-4o on multiple benchmarks while targeting mobile deployment.
hacksider
Real-time AI face swap and one-click video deepfake with only a single image
harry0703
AI-powered short video generator that automates scripting, footage sourcing, subtitles, and composition — supporting 10+ LLM providers and batch production.
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.
bytedance
ByteDance's open-source multimodal AI agent stack for GUI automation with vision-language model integration