CrewAI - RedPill AI

CrewAI uses LiteLLM internally. Prefix the RedPill model ID with openai/ so LiteLLM selects its OpenAI-compatible adapter.

Install

pip install crewai
export REDPILL_AI_API_KEY="YOUR_API_KEY"

Build a crew

import os

from crewai import Agent, Crew, LLM, Process, Task


llm = LLM(
    model="openai/z-ai/glm-5.2",
    base_url="https://api.redpill.ai/v1",
    api_key=os.environ["REDPILL_AI_API_KEY"],
    temperature=0,
)

reviewer = Agent(
    role="Code reviewer",
    goal="Identify correctness and security risks",
    backstory="A senior engineer who reports concrete findings.",
    llm=llm,
    max_iter=3,
)

review = Task(
    description="Review the supplied change summary: {change_summary}",
    expected_output="A prioritized list of findings with suggested fixes.",
    agent=reviewer,
)

crew = Crew(agents=[reviewer], tasks=[review], process=Process.sequential)
result = crew.kickoff(inputs={"change_summary": "Adds token refresh without retry limits."})
print(result)

The first openai/ segment selects the LiteLLM provider. RedPill receives z-ai/glm-5.2 as the model ID.

Production checks

Keep max_iter bounded and set timeouts around the crew run. Select a model that declares tool support before adding tools. For confidential-only calls, change base_url to https://tee.redpill.ai/v1 and use an is_tee: true model.

Troubleshooting

Symptom	Check
LiteLLM cannot select a provider	Keep the `openai/` prefix before the RedPill model ID.
Authentication fails	Confirm `REDPILL_AI_API_KEY` is available to the Python process.
Crew loops too long	Reduce `max_iter` and add task-level execution limits.

References