← Back to adopters
Adopter quickstart

CrewAI proof path

Private-beta path for adopting Imladri with CrewAI: initialize the adapter, wrap one risky capability, run the scanner or proof command from the repo, and review the same evidence in Profile.

Certification status

Certified

Certified

Certified against CrewAI Python tool execution and CrewAI-shaped TypeScript tool objects, including Tool.run, Tool._run, CrewStructuredTool.invoke, and action-alias mapping.

4/4 CrewAI lanes passed; real-package verification covers crewai with 3 allowed body calls and zero blocked-path body calls.

Runtimemixed
Access modePrivate beta
Approved beta starter
cli
imladri init --framework crewai --ci-provider github
Reference dependencies
dependencies
npm install @imladri/sdk
pip install crewai
Minimal wrapper
mixed
from crewai.tools import tool as crewai_tool
from crewai.tools.base_tool import Tool
from crewai.tools.structured_tool import CrewStructuredTool
from imladri.adapters import wrap_crewai_tools

@crewai_tool("customer_export")
def customer_export(customer_id: str) -> str:
    """Export approved customer data."""
    return f"exported:{customer_id}"

def summarize_ticket(ticket_id: str) -> dict:
    return {"summary": ticket_id}

def lookup_inventory(sku: str) -> dict:
    return {"sku": sku, "available": True}

crew_tools = [
    customer_export,
    Tool(name="ticket_summarize", description="Summarize ticket", func=summarize_ticket),
    CrewStructuredTool.from_function(
        func=lookup_inventory,
        name="inventory_lookup",
        description="Look up inventory",
    ),
]

guarded_tools = wrap_crewai_tools(
    agent,
    crew_tools,
    strict_tools=["customer.data.export"],
    action_aliases={
        "customer_export": "customer.data.export",
        "ticket_summarize": "ticket.summarize",
        "inventory_lookup": "inventory.lookup",
    },
)

# Pass guarded_tools into the CrewAI Agent/Task/Crew path that owns execution.
Terminal proof evidence
terminal evidence
imladri sdk certify --real --target crewai --include-heavy
imladri scan --path . --fail-on new
imladri proof export --format json --output imladri-proof.json