deepagents vs OpenRath
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 — PyTorch-shaped multi-agent framework: Session is the tensor, Agent the layer, Workflow the module — plus a v2 durable runtime with checkpoints, leases, an effect ledger and human interrupts.
Both are composable Python agent libraries with sub-agents and durable state. DeepAgents rides LangGraph and its ecosystem; OpenRath rebuilds the primitives around Session and ships its own durable runtime, which is more to learn but fewer layers to fight.
| deepagents | OpenRath | |
|---|---|---|
| Stars | 29k | 1.1k |
| Forks | 4.0k | 59 |
| Language | Python | Python |
| License | MIT | BSD-3-Clause |
| Last activity | today | 1 months ago |
| Topics | agents, orchestration | agents, orchestration |
| Curated connections | 11 | 7 |
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.
OpenRath — the curator's take
The abstraction is the pitch. Starting from Session rather than the agent loop is what lets you branch, trace and compose many agents across many sessions without hand-rolling a state machine — and v2's effect ledger (idempotency keys, ambiguous effects parked in NEEDS_REVIEW instead of blindly replayed) is the part most 'production-ready' agent frameworks quietly skip. The cost is conceptual weight plus Postgres, Redis and S3 for anything durable. For one agent with five tools this is far more machinery than the job needs, and the Agent Server HTTP surface is still Beta.