CrewAI

Skytale integrates with CrewAI as standard BaseTool instances. Your agents get encrypted send/receive capabilities without any infrastructure changes.

Installation

pip install skytale-sdk[crewai]

This installs skytale-sdk and crewai.

Quick start

from crewai import Agent, Task, Crew
from skytale_sdk.integrations import crewai as skytale_crew

# 1. Create a channel manager
mgr = skytale_crew.create_manager(identity=b"analyst")

# 2. Create or join a channel (see Invite Flow below)
mgr.create("acme/analysis/pipeline")

# 3. Create an agent with Skytale tools
analyst = Agent(
    role="Analyst",
    goal="Read and analyze data from the encrypted channel",
    backstory="You analyze data received via encrypted channels.",
    tools=skytale_crew.tools(mgr),
)

# 4. Run a task
task = Task(
    description="Check acme/analysis/pipeline for new data and summarize it.",
    expected_output="A summary of the data received.",
    agent=analyst,
)

crew = Crew(agents=[analyst], tasks=[task])
crew.kickoff()

Invite flow

One agent creates the channel and generates a token; the joining agent uses it. MLS key exchange happens automatically.

Same-process setup (demos)

from skytale_sdk.integrations import crewai as skytale_crew

researcher = skytale_crew.create_manager(identity=b"researcher")
analyst = skytale_crew.create_manager(identity=b"analyst")

researcher.create("acme/demo/findings")
token = researcher.invite("acme/demo/findings")
analyst.join_with_token("acme/demo/findings", token)

# Both managers are ready — create Agents with tools and run a Crew

Pre-provisioned setup (production)

Run a setup script before starting your crew:

# setup.py — run once
from skytale_sdk import SkytaleChannelManager

creator = SkytaleChannelManager(identity=b"creator", data_dir="/var/lib/creator")
creator.create("acme/prod/pipeline")

# Generate a token and share it (env var, config file, etc.)
token = creator.invite("acme/prod/pipeline")

# Joiner uses the token — no key package exchange needed
joiner = SkytaleChannelManager(identity=b"joiner", data_dir="/var/lib/joiner")
joiner.join_with_token("acme/prod/pipeline", token)

Tools reference

Tool	Args	Description
skytale_send	channel, message	Send an encrypted message to a channel
skytale_receive	channel, timeout (default 5s)	Receive buffered messages from a channel
skytale_channels	—	List all active channels

Tip

CrewAI automatically discovers tool descriptions from the BaseTool classes. The LLM knows when and how to use each tool.

Environment variables

Variable	Default	Description
SKYTALE_RELAY	https://relay.skytale.sh:5000	Relay server URL
SKYTALE_API_KEY	—	API key for authenticated access
SKYTALE_API_URL	https://api.skytale.sh	API server URL

Full example

See sdk/examples/crewai_encrypted.py for a complete multi-agent crew demo.

Cross-framework communication

CrewAI agents and LangGraph agents on the same channel communicate automatically — Skytale is the pipe, not the framework. A CrewAI agent sends data and a LangGraph agent receives it, because both use the same SkytaleChannelManager under the hood.

For structured cross-protocol messaging, see the Envelope and Protocol Adapters documentation.