CrewAI Integration

CortexDB provides persistent long-term memory for CrewAI agents, enabling crews to learn and remember across task executions.

Installation

pip install cortexdb[crewai]

Setup

from crewai import Agent, Task, Crew
from cortexdb.integrations.crewai import CortexMemory

memory = CortexMemory(
    api_key="your-cortex-api-key",
    tenant_id="my-app",
    namespace="engineering-crew",
)

researcher = Agent(
    role="Senior Researcher",
    goal="Find relevant technical context",
    backstory="You are a senior engineer with deep institutional knowledge.",
    memory=memory,
)

writer = Agent(
    role="Technical Writer",
    goal="Write clear technical documentation",
    backstory="You produce excellent technical docs.",
    memory=memory,  # Shared memory across agents
)

task = Task(
    description="Write a summary of our database migration decisions.",
    agent=writer,
)

crew = Crew(
    agents=[researcher, writer],
    tasks=[task],
)

result = crew.kickoff()

Shared vs Per-Agent Memory

# Shared memory (all agents see the same memories)
shared_memory = CortexMemory(tenant_id="my-app", namespace="shared")

# Per-agent memory (isolated)
researcher_memory = CortexMemory(tenant_id="my-app", namespace="researcher")
writer_memory = CortexMemory(tenant_id="my-app", namespace="writer")

Configuration

| Parameter | Default | Description | |---|---|---| | api_key | $CORTEX_API_KEY | CortexDB API key | | tenant_id | Required | Tenant identifier | | namespace | None | Memory namespace | | top_k | 10 | Results per recall |