AutoGen vs deepagents
Multi-agent conversation framework for building LLM applications with cooperating agents. — versus — LangChain's batteries-included agent harness on LangGraph — planning, sub-agents with isolated context, filesystem, shell, skills, human-in-the-loop and persistent memory out of the box.
Both are batteries-included multi-agent frameworks; AutoGen centers on agent-to-agent conversation, deepagents on a single planner with sub-agents, filesystem and context management.
| AutoGen | deepagents | |
|---|---|---|
| Stars | 61k | 29k |
| Forks | 9.2k | 4.0k |
| Language | Python | Python |
| License | CC-BY-4.0 | MIT |
| Last activity | 4 months ago | yesterday |
| Topics | agents, evals | agents, orchestration |
| Curated connections | 9 | 9 |
AutoGen — the curator's take
Multi-agent conversation framework for building LLM applications with cooperating agents.
deepagents — the curator's take
The fastest route to a serious long-horizon agent if you accept LangChain's stack: planning, sub-agents, context offloading and HITL gates work out of the box, and any LangGraph graph plugs in as a sub-agent, so custom orchestration composes instead of forking. NOT for simple tool-calling loops — LangChain's create_agent is lighter — and the opinions run deep: if you're fighting the harness, you wanted LangGraph directly. Model-agnostic in theory; tuned around frontier tool-callers in practice.