Loading...
CrewAI makes it easy to build multi-agent systems. Jarvis SDK gives each agent in your crew access to 700+ executable tools — so your researcher, writer, and reviewer agents all have the capabilities they need.
pip install crewai requests
Sign up at jarvissdk.com and create an API key.
Wrap the execute endpoint as CrewAI BaseTool classes.
Each agent in your crew gets the tools they need.
Copy this into your project to get started immediately.
from crewai import Agent, Task, Crew
from crewai.tools import BaseTool
from pydantic import Field
import requests, json
JARVIS_API_KEY = "jsk_your_api_key_here"
class JarvisExecuteTool(BaseTool):
name: str = "jarvis_execute"
description: str = "Execute any Jarvis SDK module. Format: module|action|{json_params}"
def _run(self, command: str) -> str:
parts = command.split("|", 2)
module, action = parts[0], parts[1]
params = json.loads(parts[2]) if len(parts) > 2 else {}
resp = requests.post(
f"https://jarvissdk.com/api/v1/modules/{module}/execute",
headers={"x-api-key": JARVIS_API_KEY, "Content-Type": "application/json"},
json={"action": action, "params": params},
)
return str(resp.json().get("result", resp.text))
class JarvisSearchTool(BaseTool):
name: str = "jarvis_search"
description: str = "Search for tools in the Jarvis SDK marketplace"
def _run(self, query: str) -> str:
resp = requests.get(
f"https://jarvissdk.com/api/v1/catalog/search?q={query}",
headers={"x-api-key": JARVIS_API_KEY},
)
modules = resp.json().get("modules", [])[:5]
return "\n".join(f"- {m['name']}: {m.get('description','')}" for m in modules)
# Create a crew with Jarvis SDK tools
researcher = Agent(
role="Research Analyst",
goal="Find and summarize relevant data",
tools=[JarvisExecuteTool(), JarvisSearchTool()],
verbose=True,
)
task = Task(
description="Use Jarvis SDK tools to analyze and summarize this text: 'AI agents need tools'",
expected_output="A brief analysis with tool-assisted insights",
agent=researcher,
)
crew = Crew(agents=[researcher], tasks=[task], verbose=True)
result = crew.kickoff()Each CrewAI agent gets exactly the tools it needs. The researcher gets search tools, the writer gets text tools, the reviewer gets validation tools.
Agents can search the marketplace at runtime to find new tools they need — no pre-configuration required.
Via A2A protocol, Jarvis SDK agents can coordinate with your CrewAI crew as peers — not just tool providers.
Jarvis SDK tracks which agent uses which tools, giving you per-agent cost visibility for your crew.
Yes. Create different tool instances or use the self-equip API to give each agent a tailored toolkit based on their role.
Absolutely. Jarvis SDK tools are standard BaseTool subclasses — they work alongside @tool decorators, SerperDevTool, etc.
Yes — crew members pass context between tasks naturally. Tool outputs flow through CrewAI's standard delegation mechanism.
Free tier includes 1,000 executions/month. No credit card required.