Onboarding: CrewAI

Add persistent memory to your CrewAI crews. The adapter captures task completions and injects past experience into agent backstories.

Best path: Gateway (for LLM calls) or Python SDK adapter (for task-level capture) Time: 2–5 minutes Reliability: ~99% (Gateway) / ~80% (adapter)

---

Option A: Gateway (Recommended for LLM calls)

If your CrewAI agents use OpenAI or another provider for LLM calls, the Gateway is the simplest integration:

from openai import OpenAI

client = OpenAI(
    base_url="https://api.hippocortex.dev/v1",
    api_key="hx_live_...",
    default_headers={"X-LLM-API-Key": "sk-..."},
)

Every LLM call gets memory automatically. ~99% reliability with graceful fallback.

---

Option B: SDK Adapter (For task-level capture)

Step 1: Install

pip install hippocortex[crewai]

Step 2: Set your API key

export HIPPOCORTEX_API_KEY=hx_live_...

Get a key at dashboard.hippocortex.dev if you do not have one.

Step 3: Wrap your crew

from crewai import Agent, Task, Crew
from hippocortex.adapters import crewai as hx_crewai

# Build your crew normally
researcher = Agent(role="Researcher", ...)
writer = Agent(role="Writer", ...)
crew = Crew(agents=[researcher, writer], tasks=[...])

# Add memory with one line
crew = hx_crewai.wrap(crew, api_key="hx_live_...")

# Use exactly as before
result = crew.kickoff()

Step 4: Verify

Check dashboard.hippocortex.dev to see captured task completions, agent interactions, and crew outcomes.

---

What gets captured

• Task descriptions and completions
• Agent interactions during kickoff
• Tool usage within tasks
• Final crew results

Auto-compile

Knowledge compilation runs automatically after every 10 captures. You do not need to call learn() manually.