NexaAI / nexa-sdk
Nexa SDK is a comprehensive toolkit for supporting GGML and ONNX models. It supports text generation, image generation, vision-language models (VLM), Audio Language Model, auto-speech-recognition (ASR), and text-to-speech (TTS) capabilities.
☆4,472Updated 3 weeks ago
Alternatives and similar repositories for nexa-sdk:
Users that are interested in nexa-sdk are comparing it to the libraries listed below
- Build multimodal language agents for fast prototype and production☆2,451Updated last week
- A UI-Focused Agent for Windows OS Interaction.☆6,639Updated this week
- The open source platform for AI-native application development.☆5,089Updated 3 months ago
- Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities。☆1,689Updated 2 months ago
- Easiest and laziest way for building multi-agent LLMs applications.☆1,417Updated last week
- Hallo2: Long-Duration and High-Resolution Audio-driven Portrait Image Animation☆3,518Updated last month
- Your Automatic Prompt Engineering Assistant for GenAI Applications☆2,091Updated 11 months ago
- SDG is a specialized framework designed to generate high-quality structured tabular data.☆2,338Updated 3 weeks ago
- Resources of our paper "FilmAgent: A Multi-Agent Framework for End-to-End Film Automation in Virtual 3D Spaces". New versions in the maki…☆938Updated last week
- "LightRAG: Simple and Fast Retrieval-Augmented Generation"☆13,170Updated this week
- The codes about "Uni-MoE: Scaling Unified Multimodal Models with Mixture of Experts"☆705Updated 2 months ago
- "AutoAgent: Fully-Automated and Zero-Code LLM Agent Framework"☆3,315Updated this week
- open-source multimodal large language model that can hear, talk while thinking. Featuring real-time end-to-end speech input and streaming…☆3,239Updated 4 months ago
- "MiniRAG: Making RAG Simpler with Small and Free Language Models"☆901Updated this week
- [ICLR 2025] SOTA discrete acoustic codec models with 40/75 tokens per second for audio language modeling☆1,085Updated 3 weeks ago
- Align Anything: Training All-modality Model with Feedback☆3,063Updated last week
- "Your Fully-Automated Personal AI Assistant, and Open-Source & Cost-Efficient Alternative to OpenAI's Deep Research"☆838Updated last month
- "VideoRAG: Retrieval-Augmented Generation with Extreme Long-Context Videos"☆510Updated this week
- Awesome LLMs on Device: A Comprehensive Survey☆1,037Updated 2 months ago
- CSGHub is a brand-new open-source platform for managing LLMs, developed by the OpenCSG team. It offers both open-source and on-premise/Sa…☆2,599Updated this week
- Large-scale, Informative, and Diverse Multi-round Chat Data (and Models)☆2,521Updated last year
- 🔥 InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity☆1,348Updated last week
- ☆1,380Updated 5 months ago
- csghub-server is the backend server for CSGHub which helps user to manage datasets, modes, and also run Model Inference, Finetune and App…☆602Updated 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，支持sso登录，大数据平台对接，notebook在线开发，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，边缘计算，标注平台，自动化标注，大模型微调，vllm大模型推…☆1,622Updated last week
- Accelerating the development of large multimodal models (LMMs) with one-click evaluation module - lmms-eval.☆2,268Updated this week
- The first open autoregressive foundational video AI model.☆2,880Updated 5 months ago
- Structure your STEM essay in several minutes with Generative AI.☆707Updated 7 months ago
- Pioneering Multimodal Reasoning with CoT☆1,157Updated this week
- Interface for OuteTTS models.☆959Updated last month