DeepAgents
ActiveDescription
Agent harness built with LangChain and LangGraph. Equipped with a planning tool, filesystem backend, and ability to spawn subagents for complex agentic tasks.
Key Features
- Sub-agent delegation — delegate tasks to agents with isolated context windows
- Pluggable filesystem — read, write, edit or search over local, sandboxed or remote backends
- Context management — summarize long threads and offload tool outputs to disk
- Persistent memory — pluggable state and store backends for cross-session recall
- Human-in-the-loop — approve, edit or reject tool calls before they run
- On-demand Skills — agents can dynamically load reusable behavior modules as needed
Use Cases
💡 Build autonomous coding agents capable of complex multi-step tasks
💡 Use sub-agents to process file search, code analysis and other independent subtasks in parallel
💡 Add cross-session persistent memory to agents for long-cycle project development
💡 Control agent behavior in production via Human-in-the-loop approval mechanisms
💡 Leverage LangSmith integration for agent tracing, evaluation and monitoring
Strengths & Limitations
✅ Strengths
- • Actively maintained, recent updates
- • High community interest (28.9k stars)
- • Permissive open-source license (MIT)
- • Responsive to issues, low backlog
Tags
Categories
Quick Start
uv add deepagents
from deepagents import create_deep_agent
agent = create_deep_agent(
model="openai:gpt-5.5",
tools=[my_custom_tool],
system_prompt="You are a research assistant.",
)
result = agent.invoke({"messages": "Research LangGraph and write a summary"})