一个轻量级、支持全链路且易于二次开发的大模型应用项目(Large Model Data Assistant) 支持DeepSeek/Qwen3等大模型 基于 Dify 、LangChain/LangGraph、Ollama&Vllm、Sanic 和 Text2SQL 📊 等技术构建的一站式大模型应用开发项目，采用 Vue3、TypeScript 和 Vite 5 打造现代UI。它支持通过 E…

Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthr…

整理目前开源的最优表格识别模型，完善前后处理，模型转换为ONNX | Organize the currently open-source optimal table recognition models, improve pre-processing and post-processing, and convert the models to ONNX.

开源的端到端产品级通用智能体

🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)

🙌 OpenHands: AI-Driven Development

企业级RAG系统从入门到精通

Supercharge Your LLM Application Evaluations 🚀

Kortix – build, manage and train AI Agents.

Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.

No fortress, purely open ground. OpenManus is Coming.

Keep searching, reading webpages, reasoning until it finds the answer (or exceeding the token budget)

EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

Kolors Team

🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!

A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations

Grounded search engine (i.e. with source reference) based on LLM / ChatGPT / OpenAI API. It supports web search, file content search etc.

An Open Large Reasoning Model for Real-World Solutions

The Tavily Python wrapper allows for easy interaction with the Tavily API, offering the full range of our search, extract, crawl, map, and research functionalities directly from your Python program…

GPT Enhanced with Real-Time Web Browsing 🔗

一个超轻量级、可以在移动端实时运行的数字人模型

Digital Avatar Conversational System - Linly-Talker. 😄✨ Linly-Talker is an intelligent AI system that combines large language models (LLMs) with visual models to create a novel human-AI interaction…

这是一个完整的数字人项目，包含Python内核及UE数字人模型，可以用于做数字助理及抖音自动直播，又或者作为你的应用入口也很帅.

Dataset and Code for our ACL 2024 paper: "Multimodal Table Understanding". We propose the first large-scale Multimodal IFT and Pre-Train Dataset for table understanding and develop a generalist tab…

Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型

Submission to https://pytorch.org/hub/

MiniCPM-V 4.5: A GPT-4o Level MLLM for Single Image, Multi Image and High-FPS Video Understanding on Your Phone

MiniCPM on Android platform.