NexaAI / nexa-sdkLinks
Run frontier LLMs and VLMs with day-0 model support across GPU, NPU, and CPU, with comprehensive runtime coverage for PC (Python/C++), mobile (Android & iOS), and Linux/IoT (Arm64 & x86 Docker). Supporting OpenAI GPT-OSS, IBM Granite-4, Qwen-3-VL, Gemma-3n, Ministral-3, and more.
☆7,584Updated this week
Alternatives and similar repositories for nexa-sdk
Users that are interested in nexa-sdk are comparing it to the libraries listed below
Sorting:
- The open source platform for AI-native application development.☆5,362Updated last year
- Klavis AI (YC X25): MCP integration platforms that let AI agents use tools reliably at any scale☆5,602Updated last week
- [ICLR 2025] Hallo2: Long-Duration and High-Resolution Audio-driven Portrait Image Animation☆3,669Updated 11 months ago
- UFO³: Weaving the Digital Agent Galaxy☆7,962Updated 3 weeks ago
- Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities。☆1,858Updated last year
- Mirix is a multi-agent personal assistant designed to track on-screen activities and answer user questions intelligently. By capturing re…☆3,374Updated 3 weeks ago
- [EMNLP-2024] Build multimodal language agents for fast prototype and production☆2,624Updated 10 months ago
- open-source multimodal large language model that can hear, talk while thinking. Featuring real-time end-to-end speech input and streaming…☆3,512Updated last year
- SDG is a specialized framework designed to generate high-quality structured tabular data.☆2,404Updated last week
- Open-source framework for conversational voice AI agents☆9,699Updated last week
- 🔥 [ICCV 2025 Highlight] InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity☆2,659Updated 5 months ago
- Your Automatic Prompt Engineering Assistant for GenAI Applications☆2,122Updated last year
- Easiest and laziest way for building multi-agent LLMs applications.☆3,702Updated this week
- MiroFlow is an agent framework that enables tool-use agent tasks, featuring a reproducible GAIA score of 82.4%.☆2,308Updated last week
- Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation☆8,635Updated last year
- A lightweight LMM-based Document Parsing Model☆6,449Updated last month
- SimpleMem: Efficient Lifelong Memory for LLM Agents☆1,774Updated this week
- HunyuanVideo-1.5: A leading lightweight video generation model☆3,702Updated 3 weeks ago
- System Level Intelligent Router for Mixture-of-Models at Cloud, Data Center and Edge☆2,878Updated this week
- cube studio开源云原生一站式机器学习/深度学习/大模型AI平台/MaaS/mlops/人工智能平台/训推平台，算法全链路流程，算力租赁平台，拖拉拽任务流pipeline编排，多机多卡分布式训练，超参搜索，推理服务，VGPU虚拟化，云边端协同，边缘计算，自动化标注平…☆1,886Updated last week
- Resources of our paper "FilmAgent: A Multi-Agent Framework for End-to-End Film Automation in Virtual 3D Spaces". New versions in the maki…☆1,093Updated 10 months ago
- [EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"☆27,541Updated last week
- [KDD'2026] "VideoRAG: Chat with Your Videos"☆2,552Updated 2 weeks ago
- UltraRAG v3: A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines☆3,539Updated this week
- "AutoAgent: Fully-Automated and Zero-Code LLM Agent Framework"☆8,480Updated 3 months ago
- LAYRA—an enterprise-ready, out-of-the-box solution—unlocks next-generation intelligent systems powered by visual RAG and limitless visual…☆897Updated 3 months ago
- The first open autoregressive foundational video AI model.☆2,891Updated last year
- MiroThinker is an open source deep research agent optimized for research and prediction. It achieves a 80.8% Avg@8 score on the challengi…☆5,749Updated this week
- Eko (Eko Keeps Operating) - Build Production-ready Agentic Workflow with Natural Language - eko.fellou.ai☆4,845Updated last week
- Fulling is an AI-powered Full-stack Engineer Agent. Built with Next.js, Claude, shadcn/ui, and PostgreSQL. Use kubernetes as infra.☆2,236Updated this week