Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.

拼好RAG：手搓并融合了GraphRAG、LightRAG、Neo4j-llm-graph-builder进行知识图谱构建以及搜索；整合DeepSearch技术实现私域RAG的推理；自制针对GraphRAG的评估框架| Integrate GraphRAG, LightRAG, and Neo4j-llm-graph-builder for knowledge graph construct…

一键将飞书文档转换为精美的公众号文章，基于 极简美学排版神器 www.md2wechat.cn 强大的 API 服务，支持六大主题风格，让您的内容发布更简单、更美观。

结巴中文分词

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…

🎯 告别信息过载，只看真正关心的新闻 - 多平台热点聚合工具，趋势分析工具，一键监控抖音、知乎、哔哩哔哩、今日头条、百度热搜、贴吧、微博、华尔街见闻、财联社等35个平台，智能关键词筛选，自动生成热点分析报告。支持企业微信、飞书、钉钉、Telegram、邮件、ntfy推送，30秒网页部署，1分钟手机通知，无需编程基础。也支持docker私人部署⭐ 让算法为你服务，而非被算法绑架

A simple yet powerful agent framework that delivers with open-source models

🐙 Guides, papers, lecture, notebooks and resources for prompt engineering

https://github.com/mizuhokaga/jsplumb-dataLineage 数据血缘前端 jsplumb-dataLineage的Vue版本（Vue2、Vue3均实现）

Open Source DeepWiki: AI-Powered Wiki Generator for GitHub/Gitlab/Bitbucket Repositories. Join the discord: https://discord.gg/gMwThUMeme

A highly customizable Flowchart component for Vue 3. Features seamless zoom & pan 🔎, additional components like a Minimap 🗺 and utilities to interact with state and graph.

React Flow | Svelte Flow - Powerful open source libraries for building node-based UIs with React (https://reactflow.dev) or Svelte (https://svelteflow.dev). Ready out-of-the-box and infinitely cust…

ReActAgentsTest

Dify 1.0 Plugin Support MCP Tools Agent strategies

Agent Zero AI framework

开源的端到端产品级通用智能体

🤖 Chat with your SQL database 📊. Accurate Text-to-SQL Generation via LLMs using RAG 🔄.

中文分词 词性标注 命名实体识别 依存句法分析 成分句法分析 语义依存分析 语义角色标注 指代消解 风格转换 语义相似度 新词发现 关键词短语提取 自动摘要 文本分类聚类 拼音简繁转换 自然语言处理

Web UI for Milvus Vector Database

SuperSonic is the next-generation AI+BI platform that unifies Chat BI (powered by LLM) and Headless BI (powered by semantic layer) paradigms.

an open high-performance Optical Character Recognition (OCR) toolkit

A cross-platform QUIC AI-boost fluent-design multi-threaded downloader built with Python.

GPT-VIS-API 是一个轻量级图表生成服务，旨在解决 [antv/mcp-server-chart](https://github.com/antvis/mcp-server-chart) 在私有化部署方面的局限性。该服务接收数据请求，生成图表图像，上传到 MinIO 对象存储，并返回带有效期的预签名访问链接。

Advanced Multi-Turn QA System with LLM and Intent Recognition. 基于LLM大语言模型意图识别、参数抽取结合slot词槽技术实现多轮问答、NL2API. 打造Function Call多轮问答最佳实践

Turn any webpage/Vue/React and so on into desktop and mobile app with easy in few minutes. 轻松将任意网站/Vue/React等项目构建为轻量级(小于5M)多端桌面应用和手机应用仅需几分钟. https://ppofficial.netlify.app/

Turn any webpage/Vue/React and so on into desktop and mobile app under 5M with easy in few minutes. 轻松将任意网站/Vue/React等项目构建为轻量级(小于5M)多端桌面应用和手机应用仅需几分钟. https://ppofficial.netlify.app