AutoGen is Microsoft Research’s open-source framework for conversation-driven multi-agent systems, agents that talk through a problem instead of calling tools in sequence. Microsoft put it in maintenance mode in October 2025, splitting the project three ways: legacy AutoGen, Microsoft Agent Framework, and the community fork AG2. None of the three, nor CrewAI or LangGraph, governs what agents reason over; Atlan’s context layer connects to all of them through MCP.
Most 2026 coverage of AutoGen is about leaving it. This page covers what still works and how to navigate the split.
| Field | Value |
|---|---|
| What it is | Open-source Microsoft Research framework for conversation-driven multi-agent systems |
| Created by | Qingyun Wu, Chi Wang, and Microsoft Research (arXiv, August 2023) |
| Current status | Maintenance mode since October 2025, bug/security fixes only |
| Official successor | Microsoft Agent Framework (MAF), 1.0 GA April 2026 |
| Community fork | AG2, Apache 2.0, led by Chi Wang and Qingyun Wu |
| Best for | Research, prototyping, debate/critique workflows |
| GitHub stars | 60,020 (July 2026), roughly 5x MAF’s 12,432 |
What is AutoGen?
Permalink to “What is AutoGen?”AutoGen is Microsoft Research’s open-source framework for building multi-agent systems where agents reason together through structured conversation rather than a single model calling tools in a fixed sequence. The original paper, led by Qingyun Wu and Chi Wang (arXiv, August 2023), describes agents defined by role that converse to reach a solution, a framing Microsoft’s project page and IBM Think confirm. See what an agentic framework is for the baseline this cluster builds on.
The ConversableAgent pattern
Permalink to “The ConversableAgent pattern”Every AutoGen agent inherits from one primitive: ConversableAgent. Instances exchange messages, propose actions, and critique each other’s output, closer to colleagues working a problem together than a script executing steps.
User Proxy, Assistant, and Code Executor agents
Permalink to “User Proxy, Assistant, and Code Executor agents”Three named roles handle most AutoGen workflows: User Proxy represents the human, Assistant reasons through the problem and drafts solutions, Code Executor runs generated code and returns real output, errors included. Most deployments use only two or three of these roles.
GroupChat: how AutoGen’s agents talk to each other
Permalink to “GroupChat: how AutoGen’s agents talk to each other”For problems needing more than one specialist, AutoGen’s GroupChat pattern lets User Proxy, Assistant, and Code Executor agents share one conversation thread, with a manager routing turns between them. It carries the sharpest governance trade-off here: rich conversation, no built-in ledger of which agent’s contribution shaped the final answer.
AutoGen proved agents reasoning together produces different results than a controller calling tools in sequence. What it never specified is what those conversations are grounded in: the shared facts and lineage that keep three agents from confidently agreeing on three different numbers.
Is AutoGen deprecated? What maintenance mode means in 2026
Permalink to “Is AutoGen deprecated? What maintenance mode means in 2026”AutoGen is not abandoned, but it’s no longer where new development happens. Microsoft moved it into maintenance mode in October 2025: bug/security fixes only, last feature release September 2025, per a competing framework vendor’s AutoGen comparison. The GitHub README now redirects newcomers to the Microsoft Agent Framework instead of AutoGen’s own quickstart.
Despite that redirect, AutoGen’s star count tells a more nuanced story. As of July 2026, the repository holds just over 60,000 GitHub stars, roughly five times the Microsoft Agent Framework’s own 12,432, both fresher than the 54,534-star figure The Agent Times reported in February 2026. Legacy adoption doesn’t vanish overnight, though teams face a real deadline: per AI DEV DAY’s 2026 analysis, major API providers deprecate legacy callback patterns in Q3 2026.
Maintenance mode answers whether AutoGen is dead, not whether moving off it fixes the underlying problem: neither its freeze nor its retirement addresses what agents built on it were allowed to know, a root cause behind why AI agents fail in production that survives the migration.
The AI Context Stack
A four-layer blueprint for the context infrastructure that sits underneath every agentic framework, AutoGen included, so a migration between frameworks never means rebuilding your business definitions from scratch.
Get the Context Stack BriefAutoGen, Microsoft Agent Framework, or AG2: which path should you take?
Permalink to “AutoGen, Microsoft Agent Framework, or AG2: which path should you take?”Since October 2025, “using AutoGen” means choosing between three paths: the original framework, Microsoft’s official successor, or the community fork. Most 2026 content mentions AG2 without explaining why the split happened.
| Path | Maintainer | License | Status | GitHub stars | Best for |
|---|---|---|---|---|---|
| Legacy AutoGen | Microsoft Research | MIT | Maintenance mode | 60,020 | Existing codebases |
| Microsoft Agent Framework | Microsoft | MIT | GA (April 2026) | 12,432 | New enterprise builds |
| AG2 | Chi Wang, Qingyun Wu | Apache 2.0 | Active | 4,801 | Independent governance |
AG2’s roughly 4,800 stars, per its own repository, reflect credibility, not mass migration. Chi Wang called the motivation “the need to move faster and make decisions more efficiently without corporate constraints, and creating a more neutral space for contributions from various organizations”: project governance, not data governance.
The Microsoft Agent Framework merged AutoGen with Semantic Kernel rather than replacing it, reaching 1.0 GA in April 2026. Shawn Henry, its Principal Group Product Manager, put it simply: “We realized we were building the same thing [AutoGen and Semantic Kernel]. So we decided to team up and build one great thing instead of two good things.”
Which path fits which team
Permalink to “Which path fits which team”Migrating to MAF suits new enterprise builds on Azure or a broader AI agent stack; see the deep dive for mechanics. Adopting AG2 suits teams wanting AutoGen’s model under independent governance. Staying on legacy AutoGen works short-term, provided the team budgets for the Q3 2026 API deprecations.
How does AutoGen compare to CrewAI and LangGraph?
Permalink to “How does AutoGen compare to CrewAI and LangGraph?”AutoGen, CrewAI, and LangGraph each take a different approach to multi-agent system orchestration: conversation, role-based crews, explicit state graphs.
| Framework | Orchestration model | Context handling | Best fit |
|---|---|---|---|
| AutoGen | Conversation-driven (GroupChat, agent debate) | Partial MCP support | Research, debate and critique |
| CrewAI | Role-based crews | Crew-scoped memory | Structured business workflows |
| LangGraph | Explicit state graphs | Mature retriever/MCP abstractions | Complex, stateful pipelines |
Worth flagging: the context-handling row reflects Atlan’s own comparison content, not an independent benchmark, though it doesn’t mean AutoGen can’t connect to an external context layer, only that doing so takes more custom work than some peers.
None is categorically better. AutoGen fits debate and exploratory research; CrewAI’s role-based structure fits defined workflows with clear ownership; LangGraph’s state graphs fit complex pipelines needing checkpointing. Teams weighing all three can go deeper in the full agentic frameworks comparison or the OpenAI Agents SDK, LangChain, and CrewAI comparison.
Whichever model a team picks, what each agent may know still has to be governed somewhere, a gap covered in Atlan’s comparison of agent context layer tools.
When should you still use AutoGen in 2026?
Permalink to “When should you still use AutoGen in 2026?”Despite maintenance mode, AutoGen remains a legitimate, narrow choice, depending on what a team is building and how much production risk it can absorb.
| Criterion | Why it matters | What to look for |
|---|---|---|
| Use case (research vs. production) | Suits exploration, not scale | Debate, critique, research synthesis |
| Tolerance for maintenance-mode risk | No new features; Q3 2026 API deprecations loom | Investment not ready to migrate off |
| Need for audit trails | GroupChat has no built-in audit trail | Regulated use cases look elsewhere |
| MCP and context-layer integration effort | Partial versus LangChain’s more mature abstractions | Teams with in-house capacity |
| Migration cost if choosing legacy | Not gaining features | Budget for an eventual move |
Where it still fits, and where it doesn’t
Permalink to “Where it still fits, and where it doesn’t”Research and prototyping: per Second Talent’s 2026 survey, roughly 60% of production systems use the simplest pattern, one Assistant plus one User Proxy, before gaps compound at multi-agent scale. Debate and critique workflows are the design’s most natural fit: brainstorming, code review, iterative correction. When to choose differently: AutoGen Studio, the no-code UI, caps out per its original research paper at two-agent and GroupChat workflows. Otherwise, evaluate CrewAI, LangGraph, the Microsoft Agent Framework, or the selection guide.
Keeping AutoGen in 2026 is defensible, not a default: it fits debate-style work while the context question stays open, since the two are separate axes. AutoGen answers what an agent does next, not what it’s allowed to know, the gap behind AI agent accuracy failures, and neither does its successor or fork.
Context Gap Calculator
Score how much of your agent stack, AutoGen included, is reasoning over governed context versus definitions that live only in someone's head or a single framework's config.
Calculate Your Context GapAutoGen, Microsoft Agent Framework, AG2: three paths, one enterprise context gap
Permalink to “AutoGen, Microsoft Agent Framework, AG2: three paths, one enterprise context gap”Whichever of the three paths a team chooses, none of them, including the governance-focused successor, solves what Atlan calls the enterprise context gap: what agents may know, and how that’s governed.
GroupChat’s autonomy is AutoGen’s sharpest version of this gap. As AxonFlow’s AutoGen governance documentation puts it, agents “message each other freely,” sensitive data “can flow between agents without filtering,” costs “can spiral through recursive agent conversations,” and there is “no audit trail showing which agent made which decision unless you build one,” left to the implementer, covered in Atlan’s guide to debugging multi-agent systems.
To be fair, transcripts let a reviewer roughly reconstruct one conversation without formal audit tooling, but that doesn’t scale to proving which data an agent was authorized to see across thousands of concurrent sessions. A readable log isn’t a governed one.
The strongest version of this argument isn’t that AutoGen is inferior to what replaced it, but that Microsoft’s own Agent Governance Toolkit, released alongside MAF 1.0, explicitly excludes business definitions, semantic meaning, and data catalog management from its scope. As Atlan’s own agentic frameworks comparison puts it, none of these frameworks knows what “ARR” means in a business, or which table holds the canonical revenue figure, for AutoGen any more than CrewAI or LangGraph.
If the designated successor still leaves this open, the gap isn’t a maintenance-mode problem, it’s what every agentic framework leaves ungoverned by design.
How Atlan approaches the enterprise context gap
Permalink to “How Atlan approaches the enterprise context gap”GroupChat conversations and shared multi-agent memory work convincingly in a demo. In production, they create what Atlan calls multi-agent memory silos: no shared, governed source of truth, so teams rebuild business definitions every time they adopt a new framework or role.
Atlan’s context layer connects to AutoGen by name through its MCP server, alongside LangGraph and CrewAI, so the same certified definitions, lineage, and governance rules reach an agent regardless of which AutoGen path runs the orchestration. The Enterprise Data Graph is queryable by AutoGen agents at runtime, giving a User Proxy or Assistant agent the governed answer a human analyst would get. Teams can review the parallel context layer pattern built for CrewAI or the equivalent for LangGraph; the same architecture applies here.
One enterprise customer’s experience illustrates the pressure: it began a multi-agent build on AutoGen, then evolved its architecture as context requirements grew, consistent with teams “very conscious about not locking into anything including a single agentic framework,” as one put it. Portable context engineering makes that evolution possible without a full rebuild.
The framework decision is reversible: a team can move from AutoGen to AG2, MAF, or elsewhere within months. The context architecture underneath, what agents are allowed to know and who’s accountable for it, determines whether that migration is a rewrite or a redeploy.
AI Agent Context Readiness Checklist
See where an AutoGen, MAF, or AG2 deployment stands before the context gap becomes a production incident.
Check Your ReadinessWhy AutoGen’s fork doesn’t close the enterprise context gap
Permalink to “Why AutoGen’s fork doesn’t close the enterprise context gap”AutoGen proved something real: agents reasoning together through conversation, not just calling tools in sequence, produces genuinely different results, an idea that shaped how the industry thinks about multi-agent design. Its own fork and its own official successor are both evidence of how far that idea traveled.
Neither the fork nor the successor closed the one gap that determines whether an agent works in production: what it is allowed to know, and who governs that knowledge as it changes. AutoGen, MAF, and AG2 orchestrate agents well; none of them governs the context those agents reason over, a separate decision worth making deliberately rather than inheriting by default.
See how Atlan connects governed context to any agentic framework a team chooses, AutoGen included, and how to implement an enterprise context layer for AI end to end.
Sources
Permalink to “Sources”- AutoGen: Multi-Agent Conversation Framework, arXiv
- AutoGen, Microsoft Research
- What Is AutoGen?, IBM Think
- Chi Wang’s clarification on AutoGen and AG2 authorship, X
- LangChain vs. AutoGen in 2026: What the Maintenance Announcement Changed, LangChain
- microsoft/autogen repository, GitHub
- AutoGen Hits 54,534 Stars, The Agent Times
- microsoft/agent-framework repository, GitHub
- Is AutoGen Deprecated?, AI DEV DAY
- ag2ai/ag2 repository, GitHub
- Microsoft Agent Framework 1.0, Azure AI Foundry Devblog
- Shawn Henry on the Microsoft Agent Framework merger, Agent Driven Development
- How Enterprises Are Using AutoGen in 2026, Second Talent
- AutoGen Studio: A No-Code Multi-Agent Tool, arXiv
- AutoGen Integration: Microsoft Multi-Agent AI Governance, AxonFlow
- Microsoft AutoGen: possible plagiarism/academic misconduct?, Hacker News
FAQs about AutoGen
Permalink to “FAQs about AutoGen”1. What is the purpose of AutoGen?
Permalink to “1. What is the purpose of AutoGen?”AutoGen’s purpose is to let multiple AI agents collaborate through conversation, rather than one agent calling tools in sequence, for code generation and research synthesis. It’s built around the ConversableAgent primitive, where a User Proxy, an Assistant, and a Code Executor exchange messages until resolved.
2. Is AutoGen completely free to use?
Permalink to “2. Is AutoGen completely free to use?”Yes. AutoGen is open-source under the MIT license, free to download, run, and modify. Microsoft doesn’t charge for the framework; costs come from the compute and API usage it consumes.
3. What is the difference between AutoGen and AutoGPT?
Permalink to “3. What is the difference between AutoGen and AutoGPT?”AutoGen is Microsoft Research’s structured multi-agent framework with defined agent roles (User Proxy, Assistant, Code Executor). AutoGPT is an earlier, more experimental single-agent project with less structured coordination. AutoGen has a stronger academic pedigree and clearer production patterns.
4. What is the AG2 fork, and should you use it instead of AutoGen?
Permalink to “4. What is the AG2 fork, and should you use it instead of AutoGen?”AG2 is the community-governed fork of AutoGen, created in November 2024 by original creators Chi Wang and Qingyun Wu after leaving Microsoft. Use AG2 for AutoGen’s model under independent, Apache 2.0 governance. Stay on legacy AutoGen only for codebases not yet ready to migrate.
5. Who created AutoGen?
Permalink to “5. Who created AutoGen?”AutoGen was created by Microsoft Research, with Qingyun Wu and Chi Wang as lead authors, published as an arXiv paper in August 2023. Chi Wang later confirmed Wu was a Penn State professor, not a Microsoft employee, when it was written.
6. Does AutoGen support languages other than Python?
Permalink to “6. Does AutoGen support languages other than Python?”AutoGen is primarily a Python framework; its APIs and tooling are built around it. The Microsoft Agent Framework extends this to Python and C#/.NET, but legacy AutoGen remains Python-only.
7. Does Atlan integrate with AutoGen?
Permalink to “7. Does Atlan integrate with AutoGen?”Yes. Atlan’s context layer connects to AutoGen by name through its MCP server, exposing the same governed definitions and lineage LangGraph and CrewAI agents draw from, so AutoGen agents reason over current, audited context instead of duplicated ones.
