Skip to main content

​
Unified Memory

RadarOS provides a single unified memory config that works identically across Agent, VoiceAgent, and BrowserAgent. All memory subsystems share one storage backend.

​
Quick Start

import { Agent, MongoDBStorage, openai } from "@radaros/core";

const agent = new Agent({
  name: "assistant",
  model: openai("gpt-4o"),
  memory: {
    storage: new MongoDBStorage({ uri: "mongodb://localhost/radaros" }),
  },
});
With just storage, you get:
  • Session persistence — message history saved across runs
  • Summaries — overflow messages automatically summarized

​
Full Configuration

const agent = new Agent({
  name: "assistant",
  model: openai("gpt-4o"),
  memory: {
    storage: new MongoDBStorage({ uri: "mongodb://localhost/radaros" }),
    maxMessages: 20,          // messages in session history (default: 50)
    maxTokens: 128_000,       // auto-trim history to fit context window

    summaries: true,          // ON by default — long-term conversation context
    userFacts: true,          // OFF by default — "prefers dark mode", "lives in Mumbai"
    userProfile: true,        // OFF by default — structured: name, role, timezone
    entities: true,           // OFF by default — companies, people, projects
    decisions: true,          // OFF by default — audit trail of agent choices

    learnings: {              // OFF by default — needs a vector store
      vectorStore: qdrant(...),
    },

    model: openai("gpt-4o-mini"), // cheaper model for background extraction
  },
});

​
How It Works

  1. Before each run — MemoryManager.buildContext() assembles a context string from all enabled stores and injects it into the system prompt.
  2. After each run — MemoryManager.afterRun() fires background extraction for all enabled stores. This is non-blocking (fire-and-forget) so it never adds latency.
  3. Session overflow — When the session exceeds maxMessages, overflow messages are automatically summarized.

​
Works Everywhere

The same memory config works across all agent types: 
// Text Agent
new Agent({ model, memory: { storage } });

// Voice Agent
new VoiceAgent({ provider, memory: { storage } });

// Browser Agent
new BrowserAgent({ model, memory: { storage } });

​
Default Feature States

FeatureDefaultRequires
SessionsONstorage
SummariesONstorage
User FactsOFFuserFacts: true
User ProfileOFFuserProfile: true
EntitiesOFFentities: true
DecisionsOFFdecisions: true
LearningsOFFlearnings: { vectorStore }

​
Accessing Stores Directly

You can access individual stores via the MemoryManager: 
const mm = agent.memory; // MemoryManager | null

const facts = await mm?.getUserFacts()?.getFacts("user-123");
const profile = await mm?.getUserProfile()?.getProfile("user-123");
const entities = await mm?.getEntityMemory()?.listEntities();