Skip to main content

​
Memory Stores

Each memory subsystem is a separate store class that handles a specific type of information.

​
Summaries

Long-term conversation memory. When session history overflows, the overflow messages are summarized by an LLM and stored. 
memory: {
  storage,
  summaries: {
    maxCount: 10,     // max summaries per session (default: 10)
    maxTokens: 2000,  // token budget for context injection (default: 2000)
  },
}

​
User Facts

Extracts and stores discrete facts about users: preferences, background, interests. 
memory: {
  storage,
  userFacts: {
    maxFacts: 100,    // max facts per user (default: 100)
  },
}
Example extracted facts:
  • “Prefers dark mode”
  • “Lives in Mumbai”
  • “Works on logistics software”

​
User Profile

Structured user data — name, role, company, timezone, language, custom fields. 
memory: {
  storage,
  userProfile: {
    customFields: ["department", "subscription_tier"],
  },
}
Injected as structured context: 
About this user:
- Name: Akash Sengar
- Role: Product Manager
- Company: Xhipment
- Timezone: Asia/Kolkata

​
Entity Memory

Tracks companies, people, projects, and products mentioned in conversations. 
memory: {
  storage,
  entities: {
    namespace: "global",  // "global" | "user" | custom string
  },
}
Provides tools: search_entities, create_entity.

​
Decision Log

Audit trail of agent decisions — what was decided, why, and what happened. 
memory: {
  storage,
  decisions: {
    maxContextDecisions: 5,  // recent decisions in context (default: 5)
  },
}
Provides tools: log_decision, record_outcome, search_decisions.

​
Learned Knowledge

Vector-backed insights from conversations. Requires a VectorStore. 
import { QdrantVectorStore, OpenAIEmbedding } from "@radaros/core";

memory: {
  storage,
  learnings: {
    vectorStore: new QdrantVectorStore({
      url: "http://localhost:6333",
      embedding: new OpenAIEmbedding(),
    }),
    collection: "radaros_learnings",  // default
    topK: 3,                          // results injected into context
  },
}
Both auto-injects relevant learnings into context AND exposes save_learning / search_learnings tools.