Connect Any Agent to Confidential Hardware

The viral open-source AI agent. Connects to Telegram, Signal, Discord — reads files, sends emails, browses the web, calls APIs. Point it at our TDX API and every LLM call is hardware-encrypted.

Best for: Personal AI assistant for lawyers, consultants, analysts who handle confidential documents daily.

# ~/.openclaw/config.yaml
providers:
  - name: voltagegpu-confidential
    type: openai
    base_url: https://api.voltagegpu.com/v1/confidential
    api_key: vgpu_YOUR_API_KEY
    model: contract-analyst  # or any of the 8 agents

# That's it. Every LLM call now runs in a TDX enclave.

Multi-agent orchestration framework. Build pipelines where multiple AI agents collaborate on complex tasks. Swap the LLM backend to our TDX API — zero code change in your agents.

Best for: Dev teams building document processing pipelines for finance, legal, healthcare — where data must stay confidential.

from crewai import Agent, Task, Crew
from langchain_openai import ChatOpenAI

# One line change: point to VoltageGPU TDX
llm = ChatOpenAI(
    base_url="https://api.voltagegpu.com/v1/confidential",
    api_key="vgpu_YOUR_API_KEY",
    model="financial-analyst",  # or any of the 8 agents
)

analyst = Agent(role="Senior Financial Analyst", llm=llm, ...)
crew = Crew(agents=[analyst], tasks=[...])
crew.kickoff()  # All inference is now TDX-encrypted

The most popular LLM framework. RAG pipelines, chains, agents, tool-use — everything works with our OpenAI-compatible API. Same SDK, same code, confidential inference.

Best for: Any LangChain app that processes sensitive data: legal search, medical Q&A, financial analysis, compliance automation.

from langchain_openai import ChatOpenAI

# Drop-in replacement — same OpenAI SDK, TDX-encrypted
llm = ChatOpenAI(
    base_url="https://api.voltagegpu.com/v1/confidential",
    api_key="vgpu_YOUR_API_KEY",
    model="compliance-officer",
)

# Use in any chain, agent, or RAG pipeline
from langchain.chains import RetrievalQA
qa = RetrievalQA.from_chain_type(llm=llm, retriever=retriever)
result = qa.invoke("Does this policy comply with GDPR Art. 25?")

If your code uses the OpenAI SDK (or any OpenAI-compatible client), it works with us. Change the base URL, keep everything else. curl, Python, Node.js, Go — all supported.

Best for: Any existing AI application that needs to become GDPR-compliant or handle sensitive documents.

# Python
from openai import OpenAI
client = OpenAI(
    base_url="https://api.voltagegpu.com/v1/confidential",
    api_key="vgpu_YOUR_API_KEY",
)
response = client.chat.completions.create(
    model="contract-analyst",
    messages=[{"role": "user", "content": "Review this NDA..."}],
)

# Node.js — identical pattern
# import OpenAI from 'openai';
# const client = new OpenAI({ baseURL: "https://api.voltagegpu.com/v1/confidential", apiKey: "vgpu_..." });