Multi‑Agent Systems

/perspective/frameworks/deep-agents-sdk/

Frameworks · ReferenceHarness

Deep Agents SDK

Opinionated, batteries-included harness on LangGraph: planning, subagents and a virtual file system out of the box.

Scenario Long-horizon research & multi-step autonomous tasksLicense Open source (MIT)
01

Suitability

Best for

Autonomous, long-horizon agents that plan, spawn subagents and manage context without wiring it yourself.

Watch out

Opinionated by design; you inherit LangGraph and its conventions.

02

Pattern support

SupervisorReActCheckpointing
NativeComposable / supportingColor = ladder level L1–L4
Read on

Related frameworks

Closest options — by shared native patterns and same stack layer.

Harness

Claude Agent SDK

Anthropic's agentic harness — the gather-context / act / verify loop behind Claude Code, with tools, subagents and MCP.

Shares ReAct · SupervisorView →Runtime

LangGraph

Graph-based, state-driven runtime; explicit nodes and edges, checkpointer-backed.

Shares Supervisor · CheckpointingView →Framework

AWS Strands SDK

Model-driven minimal SDK; the LLM weaves the graph from a 'bundle of threads' of tools.

Shares ReActView →

Keep exploring

Compare the field.

ReferenceFrameworksSeventeen platforms across the stack, compared side by side.Compare the field ReferenceProtocolsHow agents interoperate — MCP, A2A and AG-UI on the wire.Compare protocols PatternsThe Six Coordination PatternsThe six patterns every architecture is built from.Browse the catalog

Search

Search patterns, frameworks, and pages.