Multi‑Agent Systems

/perspective/frameworks/autogen-ag2/

Frameworks · ReferenceFramework

AutoGen / AG2

Event-driven conversation between agents; asynchronous messages and group chats.

Scenario Code reviews, collaborative planningLicense Open source (Apache 2.0)
01

Suitability

Best for

Multi-agent debates, negotiations, and code reviews via conversation.

Watch out

Chat histories drive high token consumption; no built-in persistence.

02

Architecture & integrations

Event-driven message passing; very flexible for debates and negotiations. Debates, complex agent negotiations, code reviews.

03

Technical profile

Approach
Event- and conversation-based message passing.
Control & learning curve
Medium learning curve. High modularity; asynchronous architecture.
Performance
Highly parallelizable; potentially high token consumption from chat histories.
04

Pattern support

Group ChatSupervisor
NativeComposable / supportingColor = ladder level L1–L4
Native patterns: GroupChat, Nested Chats, Magentic
Read on

Related frameworks

Closest options — by shared native patterns and same stack layer.

Framework

CrewAI

Role-based 'Crews' of agents; flat abstraction over team-shaped workflows.

Shares SupervisorView →Runtime

LangGraph

Graph-based, state-driven runtime; explicit nodes and edges, checkpointer-backed.

Shares SupervisorView →Harness

Deep Agents SDK

Opinionated, batteries-included harness on LangGraph: planning, subagents and a virtual file system out of the box.

Shares SupervisorView →

Keep exploring

Compare the field.

ReferenceFrameworksSeventeen platforms across the stack, compared side by side.Compare the field ReferenceProtocolsHow agents interoperate — MCP, A2A and AG-UI on the wire.Compare protocols PatternsThe Six Coordination PatternsThe six patterns every architecture is built from.Browse the catalog

Search

Search patterns, frameworks, and pages.