Koog is a JVM framework for building predictable, fault-tolerant and enterprise-ready AI agents across all platforms – from backend services to Android and iOS, JVM, and even in-browser environments. Koog is based on our AI products expertise and provides proven solutions for complex LLM and AI problems

An event-driven framework designed to build and orchestrate multi-agent AI systems. It enables seamless integration of AI agents with real-world data sources and systems, facilitating complex, multi-step workflows.

All-in-one command center for OpenClaw agents

The next-generation AI Agent framework driven by Intent Engineering. Move beyond turn-based Function Calling to embrace code-level intent expression and embedded execution. An AI-Native, Intent-Oriented Programming Language built on Python.

Lucia is your whole home assistant that you always wanted

With just one line of code, your MCP or agent can record and manage user preferences with the user profile MCP, without requiring any database dependencies.

A continually maintained guide that helps you match the right AI agent framework for your specific customer-facing use case

How Microsoft Agent Framework can orchestrate multiple specialised agents locally using Foundry Local How a coding agent can generate and execute a standalone Python application as part of an agent workflow How you can use tool calling with model which support tooling How planner and reviewer agents can be composed

how to use agentic coding like an engineer

Build your next great project with typescript, agentframework, agentstack and vue

TaskForce is a modular, open-source, production-ready TypeScript agent framework for orchestrating AI agents, LLM-powered autonomous agents, task pipelines, dynamic toolchains, RAG workflows and memory/retrieval systems.

公开类似langchain，crewai，phidata这类agent framework的搭建思路，还原从0到1，从1到100的agentic framework构建过程

The first of a kind "AGENT AS A BACKEND" : Advanced AI/ML Agent Framework with TypeScript support, multi-model capabilities, vision controls, and comprehensive AI/ML model support including LLM, SLM, MLM, Vision, ASR, TTS, RL, GNN, RNN, CNN, GAN, Diffusion, Transformer, MLP, Autoencoder, BERT, RAG, Hybrid, Foundation, and fine-tuning

opustest is an agentic AI system that automatically analyzes Python codebases and produces a detailed quality report. It uses multiple specialized AI agents — built with Microsoft Agent Framework that collaborate in a pipeline to score your code across four areas and flag every issue found.

为用户打造实用好用的Agent

GenAI prototypes for Microsoft Agent Framework and Semantic Kernel: chat completions, tool calling, document ingestion, vector search, MCP, Azure Open AI, GitHub Models, Ollama and AWS Bedrock

AgentPin agent pinning protocol, part of the Symbiont Agent Trust Stack

The first and only Python package for universal capability discovery across all major agent frameworks

sample/demo application to showcase Microsoft Agent Framework with Group Chat pattern

Microsoft Agent Framework samples and gamma api workflow example