deepcrew-ai: Skill for Claude Code

deepcrew-ai integration skill

deepcrew-ai is an async, LiteLLM-backed multi-agent library. This skill teaches you how to wire it into any Python project correctly on the first try.

Install

pip install deepcrew-ai
# optional extras:
pip install deepcrew-ai[fastapi]   # SSE streaming endpoint
pip install deepcrew-ai[redis]     # Redis-backed memory
pip install deepcrew-ai[otel]      # OpenTelemetry tracing

API keys are read by LiteLLM from standard env vars — set whichever providers you use: OPENAI_API_KEY, ANTHROPIC_API_KEY, GEMINI_API_KEY, etc. The model string on every Agent determines the provider, e.g. "openai/gpt-4o", "anthropic/claude-opus-4-8", "gemini/gemini-2.0-flash", "ollama/llama3.2" (local, no key needed).

Decision table

You need...	Use
One agent, no coordination	Agent + run_agent()
Router picks one agent or fans out to several in parallel	Orchestrator
An explicit, fixed pipeline of steps with dependencies	WorkflowBuilder
An agent that critiques and improves its own answer	Agent(loop_config=LoopConfig(verifier=...))
An agent that can delegate sub-tasks to fresh agents mid-run	Orchestrator(enable_spawn=True)
A simple chatbot UI that should only show the reply text	StreamPolicy.chat()
A technical/debug UI that should show everything	StreamPolicy.verbose()
Approve or block individual tool calls before they run	AgentHooks(approve_tool=...)

Recipes

Single agent + tool

from deepcrew import Agent, run_agent, tool

@tool
def get_weather(city: str) -> str:
    """Look up the current weather for a city."""
    return f"Sunny in {city}"

agent = Agent(name="assistant", model="openai/gpt-4o", tools=[get_weather])
result = await run_agent(agent, [{"role": "user", "content": "Weather in Tokyo?"}])
print(result.text)

Multimodal query (image + PDF)

from deepcrew import Agent, run_agent, image, pdf, user_message

agent = Agent(name="analyst", model="anthropic/claude-opus-4-8")
msg = user_message("Summarize this chart and check it against the report.",
                    image("chart.png"), pdf("report.pdf"))
result = await run_agent(agent, [msg])