deepagents vs OpenManus
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. — versus — Open-source general autonomous agent from the MetaGPT team — the 'Manus without an invite code': browsing, tool use and multi-step task execution from a simple Python core.
Same job — a batteries-included general autonomous agent that plans, browses and executes multi-step tasks. deepagents is the actively maintained, LangGraph-backed harness; OpenManus is the leaner, quieter reference implementation.
| deepagents | OpenManus | |
|---|---|---|
| Stars | 26k | 57k |
| Forks | 3.7k | 10.0k |
| Language | Python | Python |
| License | MIT | MIT |
| Last activity | today | 5 months ago |
| Topics | agents, orchestration | agents |
| Curated connections | 6 | 2 |
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.
OpenManus — the curator's take
The fastest way to feel what a general autonomous agent does: clone, add a model key, hand it a task — the 3-hour-prototype energy that earned 57k stars keeps the codebase small enough to actually read, which makes it a great learning skeleton. But look at the commit graph before betting on it: activity has been quiet for months while the team's focus moved on (OpenManus-RL and beyond), so treat it as a reference implementation, NOT a maintained production framework — for durable agent infrastructure reach for an actively developed harness instead.