AI Agents Registry

Interactive coding agent that runs code locally with human confirmation.

_(EXPERIMENTAL, RESEARCH IN PROGRESS)_ <p align="right"> <img src="../../packages/autogen-ext/imgs/task_centric_memory.png" alt="Description" width="300" align=

This sample demonstrates how to create a Python agent that interacts with a .NET agent. To run the sample, check out the autogen repository. Then do the followi

This example runs a gRPC server using GrpcWorkerAgentRuntimeHost and instantiates three distributed runtimes using GrpcWorkerAgentRuntime. These runtimes connec

This sample demonstrates how to create a simple chat application using AgentChat and FastAPI. You will be using the following features of AgentChat: 1. Agent: -

This sample demonstrates how to build a streaming chat API featuring multi-agent handoffs and persistent conversation history using autogen-core and FastAPI. Fo

This is an AutoGen powered CLI that generates draft replies for issues and pull requests to reduce maintenance overhead for open source projects. Simple install

This sample demonstrates how to build a streaming chat API with multi-turn conversation history using autogen-core and FastAPI.

This repository is an example of how to run a distributed agent runtime. The system is composed of three main components: 1. The agent host runtime, which is re

An example with two chess player agents that executes its own tools to demonstrate tool use and reflection on tool use.

In this sample, we will demonstrate how to build simple chat interface that interacts with a Core agent or a team, using Chainlit, and support streaming message

An example showing human-in-the-loop which waits for human input before making the tool call.

In this sample, we will build a chat interface that interacts with an intelligent agent built using the AutoGen AgentChat API and the GraphRAG framework.

In this sample, we will demonstrate how to build simple chat interface that interacts with an AgentChat agent or a team, using Chainlit, and support streaming m

<div align="center"> <img src="https://github.com/mehrsa/MultiAgent_Azure_PostgreSQL_AutoGen0.4/blob/main/misc/Drawing%203.png" alt="Architecture"> </div> Go to

Microsoft multi-agent framework with built-in agent patterns and Docker sandbox.

Code-generation agent that builds applications from a natural-language spec.

Reference implementations for running Claude Managed Agents sessions against **self-hosted execution sandboxes**. Each variant implements the same contract on a

This directory deploys the research agent from 00_The_one_liner_research_agent.ipynb through three tiers: local Docker, Modal, and Kubernetes. The agent, the co

@mention a Claude Managed Agent in Slack and get the reply in-thread. `` Slack @mention ──▶ /slack/events ──▶ sessions.create (+ metadata) ──▶ 200 │ Claude runs

@mention a Claude Managed Agent in a Linear issue and get the reply as a comment. `` Linear @mention ──▶ /linear-webhook ──▶ sessions.create (+ metadata) ──▶ 20

A thin MCP server that wraps the Claude Managed Agents Sessions API — so Claude Desktop **or** claude.ai web can start and chat with your org's hosted agents as