deepagents

library0.7.9pypypi✓ verified 27d ago

Agent harness by LangChain built on LangGraph. Implements planning (write_todos tool), filesystem backends, and subagent delegation — the architecture behind Claude Code, Manus, and Deep Research. Returns a compiled LangGraph StateGraph. Released mid-2025. Current version: 0.4.12 (Mar 2026). Default model is Claude Sonnet (not GPT-4o). Requires LangChain core libraries.

llm-agents ai-ml web-framework

pip install deepagents

github ↗package ↗homepage ↗docs ↗

INSTALL

IMPORT

SIG · DEEPAGENTS

deepagents

llm-agentspythonv0.7.9

Install

14.1s avg

Import

9128ms

Disk

167MB

Pass rate

6/ 10

Env Coverage6 / 10

glibc

3.9–3.13

musl

3.9–3.13

Install & Compatibility

Where this runs

tested against v0.7.9 · pip install

no network on importno background threads

Install × environment matrix

Each cell = how many times install + import succeeded across repeated harness runs. Partial = flaky.
glibc = Debian/Ubuntu slim · musl = Alpine Linux

musl

glibc

py 3.10

✕ build_error

py 3.11

✓ —

✓ 15.75s

py 3.12

✓ —

✓ 13.3s

py 3.13

✓ —

✓ 13.3s

py 3.9

✕ build_error

167MB installed

● package 167MB

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

create_deep_agent

✓ from deepagents import create_deep_agent

✗ from deepagents import create_deep_agent

init_chat_model

✓ from langchain.chat_models import init_chat_model

✗ from langchain.chat_models import init_chat_model

Minimal deepagents agent with OpenAI model.

# pip install deepagents langchain-openai from deepagents import create_deep_agent from langchain.chat_models import init_chat_model model = init_chat_model('openai:gpt-4o') agent = create_deep_agent( model=model, system_prompt='You are a helpful research assistant.' ) result = agent.invoke({ 'messages': [{ 'role': 'user', 'content': 'Write a short summary of what LangGraph is' }] }) print(result['messages'][-1].content)

Debug

Known issues

gotchaDefault model is Claude Sonnet (anthropic), not GPT-4o. Requires ANTHROPIC_API_KEY if no custom model passed. Fails with AuthenticationError if key not set.

fix

Pass model= explicitly: create_deep_agent(model=init_chat_model('openai:gpt-4o')) to use OpenAI.

affects: all

gotchacreate_deep_agent returns a compiled LangGraph StateGraph — not a plain callable. Must invoke with {'messages': [...]} dict, not a plain string.

fix

agent.invoke({'messages': [{'role': 'user', 'content': 'your prompt'}]})

affects: all

gotchaResult is a dict, not a string. Final answer is at result['messages'][-1].content. Agent may also create files accessible at result['files'].

fix

result['messages'][-1].content for text output. result.get('files', {}) for any files created.

affects: all

gotchaBecause it returns a LangGraph graph, it supports streaming, checkpointers, human-in-the-loop, and LangSmith tracing natively — but requires LangGraph-style usage patterns.

fix

Use agent.stream() for streaming. Pass checkpointer= for persistence. Set LANGSMITH_TRACING=true for tracing.

affects: all

gotchaLLMs trained before mid-2025 have no knowledge of deepagents. Will hallucinate LangChain agent patterns or generic ReAct agents instead.

fix

Always use create_deep_agent() from deepagents — not langchain's create_react_agent or create_tool_calling_agent.

affects: all

breakingThe `deepagents` library requires Python 3.11 or higher. Installation will fail with a 'No matching distribution found' error on older Python versions.

fix

Upgrade your Python environment to 3.11 or newer to install `deepagents`.

affects: all

breakingWhen using OpenAI models (e.g., 'openai:gpt-4o'), the OPENAI_API_KEY environment variable or `api_key` parameter must be set. Fails with openai.OpenAIError if not provided.

fix

Set the OPENAI_API_KEY environment variable or pass `api_key` to `init_chat_model` (e.g., `init_chat_model('openai:gpt-4o', api_key='your_key')`).

affects: all

Upgrade

Version history

0.7.9latest on PyPI · released Aug 25, 2026

Audit

Dependencies

langchain-corerequiredRequired. deepagents is built on LangChain/LangGraph.

langgraphrequiredRequired. create_deep_agent returns a compiled LangGraph StateGraph.

langchain-anthropicoptionalRequired for default model (Claude Sonnet). Install if not using custom model.

Agent activity

46 hits · last 30 days

node

Amazon

Bingbot

OpenAI (training)

Resources

githubhttps://github.com/langchain-ai/deepagents ↗

packagehttps://pypi.org/project/deepagents/ ↗

homepagehttps://docs.langchain.com/oss/python/deepagents/overview ↗

docshttps://reference.langchain.com/python/deepagents/ ↗