AutoGen

Name: AutoGen
Author: Microsoft

Deprecated

by Microsoft · Framework · also known as Microsoft AutoGen, pyautogen, autogen-agentchat

Microsoft's multi-agent framework (Core, AgentChat, Extensions, Studio) for Python and .NET, now archived with users directed to Microsoft Agent Framework

MIT licenseOpen sourceFreeLocalSelf-hostedSelf-hostable

Visit official site Compare

Link verified Nov 2, 2026

Overview

AutoGen is Microsoft Research's framework for building multi-agent AI applications. Its 0.4 redesign split it into layers: Core, an event-driven runtime for scalable and distributed agents across languages; AgentChat, a higher-level Python API for conversational single- and multi-agent apps; Extensions, which connect to services such as MCP servers, OpenAI Assistants and Docker code executors; and AutoGen Studio, a web UI for prototyping without code. A .NET implementation accompanied the Python packages, and code is MIT-licensed with documentation under CC-BY-4.0.

The repository README now carries an archived notice: Microsoft no longer maintains the project, provides no bug or security fixes, and advises against production use. New users are directed to Microsoft Agent Framework, described as the enterprise-ready successor with a migration guide from AutoGen, and a community fork (AG2) continues separately. AutoGen remains relevant as reference material for its research lineage and for existing deployments, but new work should start elsewhere.

Editorial note on uncertainty. Microsoft Agent Framework, the designated successor, is not part of this encyclopedia's slug list, so it is not linked as an alternative.

Capabilities

Event-driven Core runtime for distributed multi-agent systems
AgentChat API for conversational agents and teams
Extensions for MCP, OpenAI Assistants, Docker code execution and gRPC runtimes
AutoGen Studio no-code prototyping UI
Python and .NET implementations

Typical workflows

Study the original multi-agent conversation patterns from the research papers
Maintain an existing AgentChat deployment while planning migration

Strengths

Well-documented research lineage
MIT-licensed code remains available

Limitations

Archived; no maintenance or security fixes from Microsoft
Successor framework requires migration
Not recommended for production

Prerequisites

Python 3.10+ or .NET

Who it is for

Researchers studying multi-agent patterns
Teams with legacy AutoGen deployments

Alternatives & comparison

CrewAI
Open-source Python framework for role-based multi-agent crews and event-driven flows, with a commercial enterprise console for deploying, monitoring and triggering automations
MixedOpen source
LangGraph
Low-level orchestration framework and runtime for stateful, long-running agents expressed as graphs, with durable execution, checkpointing, human-in-the-loop and streaming
Open sourceOpen source
OpenAI Agents SDK
Lightweight open-source Python and TypeScript framework for agents, handoffs, guardrails, sessions and tracing, defaulting to OpenAI's Responses API with adapters for other providers
Open sourceOpen source
Pydantic AI
Type-safe Python agent framework from the Pydantic team with validated structured outputs, dependency injection, swappable model providers, MCP, durable execution and evals
Open sourceOpen source

Compare AutoGen with its alternatives →

Sources & verification

Primary sources consulted for this record. Claims are tied to the fields each source supports; the automated link checker re-verifies every URL on a schedule.

License
https://github.com/microsoft/autogen/blob/main/LICENSE-CODE
Supports: license_spdx, source_model
Code MIT; LICENSE file is CC-BY-4.0 for documentation
checked Nov 1, 2026
Official site
AutoGen documentation
https://microsoft.github.io/autogen/stable
Supports: name, capabilities, languages
checked Nov 1, 2026
Repository
https://github.com/microsoft/autogen
Supports: product_status, license_spdx
README states the project is archived and no longer maintained; points to Microsoft Agent Framework
checked Nov 1, 2026

Confidence: High
Reviewed: Nov 1, 2026
Links: Verified · Nov 2, 2026

Spotted an error?

Apify

Apify Technologies s.r.o. · Data collection & crawling

Cloud platform and marketplace for running web-scraping and automation programs (Actors), with storages, proxies, scheduling, an API and an MCP server for agents

Apache-2.0FreemiumUsage-basedNov 2, 2026

Claude Code

Anthropic · Coding agents & AI IDEs

Anthropic's agentic coding tool that reads a codebase, edits files and runs commands from the terminal, IDEs, a desktop app, the web and CI, with MCP, hooks, skills and subagents

ProprietaryPaidUsage-basedLocalNov 2, 2026

Claude Platform

Anthropic · Model providers & APIs

Anthropic's developer platform for the Claude models: Messages API, tool use, structured outputs, prompt caching, batch processing and Managed Agents, plus cloud availability

ProprietaryUsage-basedEnterpriseNov 2, 2026

OpenAI API

OpenAI · Model providers & APIs

OpenAI's hosted developer platform: Responses and Chat Completions APIs, Realtime voice, embeddings, images, audio, fine-tuning, evals and managed agents

ProprietaryUsage-basedEnterpriseNov 2, 2026

Model Context Protocol

Model Context Protocol, a Series of LF Projects, LLC (originated by Anthropic) · Agent frameworks & orchestration

Open JSON-RPC standard for connecting AI applications to tools, data and prompts through servers, now stewarded under the Linux Foundation with SDKs in many languages

Open sourceOpen sourceFreeLocalSelf-hostedNov 2, 2026

LangChain

LangChain, Inc. · Agent frameworks & orchestration

Open-source Python and JavaScript framework whose create_agent harness builds tool-using agents on the LangGraph runtime with swappable model providers and middleware

MITOpen sourceFreeLocalSelf-hostedNov 2, 2026