agentdock vs deepagents
TypeScript library giving a backend one agent runtime: session-scoped runs with streaming, approvals and cancel, a tool registry, injectable stores and a factory over nine AI SDK providers. — 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.
Same 'library, not product' position, opposite scope. DeepAgents ships planning, sub-agents with isolated context and a virtual filesystem on LangGraph; AgentDock ships a loop and expects the consuming app to own tools, prompts, auth and persistence.
| agentdock | deepagents | |
|---|---|---|
| Stars | 6 | 29k |
| Forks | 2 | 4.0k |
| Language | TypeScript | Python |
| License | MIT | MIT |
| Last activity | 3 days ago | today |
| Topics | agents | agents, orchestration |
| Curated connections | 5 | 11 |
agentdock — the curator's take
A deliberately thin agent loop for Node backends. The one decision worth copying is that sessions own their message history through an injected store, so a multi-tenant app stops threading transcripts through every call site. Set expectations accordingly: v0.1.0, single-digit stars, in-memory defaults, and it is a wrapper over the Vercel AI SDK, so anything the SDK cannot do it cannot do either. Use it if you want a runtime small enough to read end to end; use a real harness if you want planning, sub-agents, sandboxes or memory.
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.