Codebase for Aria - an Open Multimodal Native MoE
- mixture-of-experts
- multimodal
- vision-and-language
142,273 visible repositories in the index
361–384 of 802 · Most stars
Codebase for Aria - an Open Multimodal Native MoE
Any file → clean Markdown for AI agents: PDF, Word, PowerPoint, Excel, EPUB, HTML and web pages, images (OCR), audio and video (metadata, subtitles, transcripts). A fast Rust MCP server and CLI that runs on your machine. No API key.
Unified interface for AI chat, Agentic workflows and more ...
Plan, build and launch products with AI: guided planning prompts, an AI App Starter for Next.js, Supabase and Vercel, and agent configurations.
Agents-flex is A lightweight Java AI agent development framework (positioned as a counterpart to Spring AI). It supports features such as RAG, MCP, Skills, Text2SQL , LLM Wiki, Sub-agents, Web Search, TTS (synchronous and streaming), and STT.
Run MoE models bigger than your RAM. Frontier-size MoE on a phone, laptop, edge. Lossless, on stock llama.cpp. An adaptive streaming optimizer. Any hardware, any OS, any model, any quantization, behind a local OpenAI-compatible server.
On-premises conversational RAG with configurable containers
A FastAPI service for semantic text search using precomputed embeddings and advanced similarity measures, with built-in support for various file types through textract.
Python library for Agentic Document Extraction (ADE).
开源、可私有化部署的 Web Agent 底座,支持多用户、隔离沙箱,以及 Skills 和 MCP 扩展。Open-source, self-hostable Web Agent foundation with multi-user support, isolated sandboxes, and extensibility through Skills and MCP.
An open-source take on ChatGPT's Intelligent UI: answers stream as interactive UI (maps, photos, charts, drawings and working tools). Built with OpenUI.
Own the flow: one open-source AI platform for your knowledge, models and channels – web, WhatsApp, email, Outlook, Nextcloud & ownCloud. Local and cloud models side by side, with the cost on every answer.
Source code/webpage/demos for the What-If Tool
Tutel MoE: Optimized Mixture-of-Experts Library, Support GLM/Kimi/Gpt/DeepSeek/Qwen using FP8/NVFP4/MXFP4
[ICLR 2026 Oral] BIRD-INTERACT: Re-imagines Text-to-SQL evaluation via lens of dynamic interactions.
Next.js frontend for LangChain Chat.
Lite & Super-fast re-ranking for your search & retrieval pipelines. Supports SoTA Listwise and Pairwise reranking based on LLMs and cross-encoders and more. Created by Prithivi Da, open for PRs & Collaborations.
Use Claude Code for free in the terminal, VSCode extension, or via Discord
🔍 LangKit: An open-source toolkit for monitoring Large Language Models (LLMs). 📚 Extracts signals from prompts & responses, ensuring safety & security. 🛡️ Features include text quality, relevance metrics, & sentiment analysis. 📊 A comprehensive tool for LLM observability. 👀
🧸 Lobe Vidol - Making Virtual Idols Accessible for EveryOne
NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment
TextGen: Implementation of Text Generation models, include LLaMA, BLOOM, GPT2, BART, T5, SongNet and so on. 文本生成模型,实现了包括LLaMA,ChatGLM,BLOOM,GPT2,Seq2Seq,BART,T5,UDA等模型的训练和预测,开箱即用。
Open-source LLM gateway in Rust. One endpoint for OpenAI, Anthropic, Gemini and every other vendor. Any SDK, any model, any tool.
Empower Large Language Models (LLM) using Knowledge Graph based Retrieval-Augmented Generation (KG-RAG) for knowledge intensive tasks