Private CrewAI Deployment,
Sovereign Multi-Agent Workflows.

# Install CrewAI and the OpenAI SDK that backs the LLM wrapper
pip install crewai crewai-tools openai

# Sovereign legal crew, contract analyst + clause drafter
from crewai import Agent, Crew, Task, LLM, Process

# One LLM, every agent in the crew uses the confidential endpoint.
# Requests pass through our relay, which sees them in clear (TLS ends at our host).
# To keep plaintext off our servers, run your own inference server in a
# Confidential VM and terminate TLS inside its trust domain.
confidential_llm = LLM(
    model="openai/Qwen/Qwen3.5-397B-A17B-TEE",
    base_url="https://api.voltagegpu.com/v1",
    api_key="vgpu_...",  # https://voltagegpu.com/api-keys
    temperature=0.2,
    max_tokens=4096,
)

analyst = Agent(
    role="Senior Contract Analyst",
    goal="Identify regulatory and commercial risks in vendor contracts.",
    backstory="EU-trained counsel specialized in DORA / RGPD / NIS2.",
    llm=confidential_llm,
    verbose=False,
)

drafter = Agent(
    role="Clause Drafter",
    goal="Propose redlines that address each finding.",
    backstory="Has drafted MSAs for 200+ regulated SaaS rollouts.",
    llm=confidential_llm,
    verbose=False,
)

review = Task(
    description="Review {contract} and list every Article 28 RGPD gap.",
    expected_output="A bulleted list of clause-level findings with severity.",
    agent=analyst,
)

redline = Task(
    description="Draft a redline for each finding produced by the analyst.",
    expected_output="Markdown redlines grouped by clause section.",
    agent=drafter,
    context=[review],
)

crew = Crew(
    agents=[analyst, drafter],
    tasks=[review, redline],
    process=Process.sequential,
    verbose=False,
)

result = crew.kickoff(inputs={"contract": open("msa.txt").read()})
print(result)

# Finance deal-screening crew, three agents, hierarchical process
from crewai import Agent, Crew, Task, LLM, Process

reasoning_llm = LLM(
    model="openai/deepseek-ai/DeepSeek-V3.2-TEE",
    base_url="https://api.voltagegpu.com/v1",
    api_key="vgpu_...",
    temperature=0.0,
)

fast_llm = LLM(
    model="openai/google/gemma-4-31B-turbo-TEE",
    base_url="https://api.voltagegpu.com/v1",
    api_key="vgpu_...",
    temperature=0.1,
)

screener = Agent(role="Deal Screener", goal="Filter opportunities", llm=fast_llm, backstory="MD-led screening discipline.")
modeler  = Agent(role="Model Builder",  goal="Build base+stress cases", llm=reasoning_llm, backstory="Sector-specialist analyst.")
ic_writer = Agent(role="IC Memo Writer", goal="Produce IC-ready memos", llm=reasoning_llm, backstory="Investment committee veteran.")

crew = Crew(
    agents=[screener, modeler, ic_writer],
    tasks=[
        Task(description="Screen {opportunity}", expected_output="GO / NO-GO with rationale", agent=screener),
        Task(description="Build base+stress model", expected_output="Model JSON + key drivers", agent=modeler),
        Task(description="Draft IC memo", expected_output="2-page memo", agent=ic_writer),
    ],
    process=Process.hierarchical,
    manager_llm=reasoning_llm,
)

memo = crew.kickoff(inputs={"opportunity": open("teaser.pdf", "rb").read()})

Per million tokens, from our live pricing (/pricing).

Ship a sovereign crew this afternoon

Generate an API key, swap base_url, kick off your first confidential crew. Requests pass through our relay, which sees them in clear (TLS ends at our host). To keep plaintext off our servers, run your own inference server in a Confidential VM and terminate TLS inside its trust domain.