StackMap
Subscribe

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.

The curated verdict

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.

AutoGendeepagents
Stars60k26k
Forks9.0k3.7k
LanguagePythonPython
LicenseCC-BY-4.0MIT
Last activity3 months agotoday
Topicsagents, evalsagents, orchestration
Curated connections96

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.