OLLM

OLLM is the world's first enterprise router aggregating high-security, zero-knowledge LLM providers. It provides a unified API gateway to access AI models with guaranteed military-grade encryption at every layer. The OLLM provider for the AI SDK enables seamless integration with all these models while offering unique advantages:

  • Verifiable Privacy: All models run with confidential computing for maximum security
  • Universal Model Access: One API key for models from multiple providers
  • Confidential Computing: Hardware-level encryption with TEE (Trusted Execution Environment) on all models
  • Military-Grade Security: End-to-end encryption at every layer of the stack
  • Simple Integration: OpenAI-compatible API across all models

Learn more about OLLM's capabilities in the OLLM Website.

Setup

The OLLM provider is available in the @ofoundation/ollm module. You can install it with:

pnpm add @ofoundation/ollm

Provider Instance

To create an OLLM provider instance, use the createOLLM function:

import { createOLLM } from '@ofoundation/ollm';


const ollm = createOLLM({
  apiKey: 'YOUR_OLLM_API_KEY',
});

You can obtain your OLLM API key from the OLLM Dashboard.

Language Models

All OLLM models run with confidential computing by default. Use ollm.chatModel() for chat models:

// Confidential computing chat models
const confidentialModel = ollm.chatModel('near/GLM-4.7');

You can find the full list of available models in the OLLM Models.

Examples

Here are examples of using OLLM with the AI SDK:

generateText 

import { createOLLM } from '@ofoundation/ollm';
import { generateText } from 'ai';


const ollm = createOLLM({
  apiKey: 'YOUR_OLLM_API_KEY',
});


const { text } = await generateText({
  model: ollm.chatModel('near/GLM-4.6'),
  prompt: 'What is OLLM?',
});


console.log(text);

streamText 

import { createOLLM } from '@ofoundation/ollm';
import { streamText } from 'ai';


const ollm = createOLLM({
  apiKey: 'YOUR_OLLM_API_KEY',
});


const result = streamText({
  model: ollm.chatModel('near/GLM-4.6'),
  prompt: 'Write a short story about secure AI.',
});


for await (const chunk of result.textStream) {
  console.log(chunk);
}

Using System Messages 

import { createOLLM } from '@ofoundation/ollm';
import { generateText } from 'ai';


const ollm = createOLLM({
  apiKey: 'YOUR_OLLM_API_KEY',
});


const { text } = await generateText({
  model: ollm.chatModel('near/GLM-4.6'),
  system: 'You are a helpful assistant that responds concisely.',
  prompt: 'What is TypeScript in one sentence?',
});


console.log(text);

Advanced Features

OLLM offers several advanced features to enhance your AI applications with enterprise-grade security:

  1. Zero Data Retention (ZDR): Your prompts and completions are never stored or logged by providers.

  2. Confidential Computing: Hardware-level encryption using TEE technology ensures your data is protected even during processing.

  3. Verifiable Privacy: Cryptographic proofs that your data was processed securely.

  4. Model Flexibility: Switch between hundreds of models without changing your code or managing multiple API keys.

  5. Cost Management: Track usage and costs per model in real-time through the dashboard.

  6. Enterprise Support: Available for high-volume users with custom SLAs and dedicated support.

  7. Tool Integrations: Seamlessly works with popular AI development tools including:

    • Cursor
    • Windsurf
    • VS Code
    • Cline
    • Roo Code
    • Replit

For more information about these features and advanced configuration options, visit the OLLM Documentation.

Additional Resources