Context Compression

Use Astreus's auto context compression system to automatically manage long conversations by summarizing older messages while preserving important context.

Quick Start#

Clone the Complete Example#

The easiest way to get started is to clone the complete example repository:

bash

git clone https://github.com/astreus-ai/examples
cd examples/context-compression
npm install

Or Install Package Only#

If you prefer to build from scratch:

bash

npm install @astreus-ai/astreus

Environment Setup#

bash

# .env
OPENAI_API_KEY=sk-your-openai-api-key-here
DB_URL=sqlite://./astreus.db

Auto Context Compression#

The autoContextCompression feature automatically summarizes older messages when the conversation gets too long, maintaining context while reducing token usage:

typescript

import { Agent } from '@astreus-ai/astreus';

const agent = await Agent.create({
  name: 'ContextAgent',
  model: 'gpt-4o',
  memory: true,
  autoContextCompression: true,
  systemPrompt: 'You can handle very long conversations efficiently.'
});

// Have a long conversation
for (let i = 1; i <= 20; i++) {
  await agent.ask(`Tell me an interesting fact about space. This is message #${i}.`);
}

// Test memory - agent should remember early facts despite context compression
const response = await agent.ask("What was the first space fact you told me?");
console.log(response);

Running the Example#

If you cloned the repository:

bash

npm run dev

Repository#

The complete example is available on GitHub: examples/context-compression