A Go-based LLM/AI application development framework open-sourced by CloudWeGo (ByteDance), providing component abstractions, agent orchestration, graph/chain workflows, and streaming capabilities.

Model & Inference FrameworkSDKRAG

VIEW DETAILS →

Java AI application development framework supporting LLM-tool/skill, RAG, MCP, Agent-ReAct, Team-Agent, compatible with Java 8-25, embeddable in SpringBoot, jFinal, Vert.x, Quarkus.

Model & Inference FrameworkSDKMulti-Agent System

VIEW DETAILS →

An open-source Go-based application engine integrating autonomous agent framework, GraphRAG knowledge retrieval, and full-stack runtime in a single binary for building web apps, REST APIs, and edge intelligence services.

Model Context ProtocolRAGAI Agents

VIEW DETAILS →

A modular Python toolkit developed by the University of Innsbruck that integrates information retrieval, re-ranking, and RAG generation, featuring 40+ pre-processed datasets and single-line pipeline construction.

Model & Inference FrameworkNatural Language ProcessingSDK

VIEW DETAILS →

An all-in-one AI agent development platform with visual tools that simplify the creation, debugging, and deployment of AI agents, allowing developers to focus on creating core AI value.

AI Agents大语言模型SDK

VIEW DETAILS →

FastGPT is a knowledge-based platform built on LLMs that offers comprehensive capabilities including data processing, RAG retrieval, and visual AI workflow orchestration, enabling easy development and deployment of complex question-answering systems.

Agent & ToolingNext.jsTypeScript

VIEW DETAILS →

UltraRAG is a low-code RAG development framework based on the Model Context Protocol (MCP) architecture, enabling developers to orchestrate complex workflows through simple YAML configuration. It offers a visual IDE for building RAG pipelines with debugging capabilities and can convert pipeline logic into interactive conversational UIs with a single click.

Agent & ToolingPythonRAG

VIEW DETAILS →

The official Claude Code compound engineering plugin that makes each unit of engineering work easier than the last. It implements a workflow of Plan → Work → Review → Compound to accumulate engineering knowledge and reduce technical debt over time.

Agent & ToolingBunTypeScript

VIEW DETAILS →

The world's first universal agent operating system that enables easy building and deployment of private Agentic AI solutions without coding, featuring complete workflow, plugins, and RAG knowledge库 capabilities。

Agent & ToolingDockerTypeScript

VIEW DETAILS →

AdalFlow is a PyTorch-like library for building and auto-optimizing any LLM workflows, from chatbots and RAG to agents, featuring auto-differentiation for prompt optimization and model-agnostic building blocks.

Agent & ToolingPythonPyTorch

VIEW DETAILS →