Documentation Index
Fetch the complete documentation index at: https://docs.xhipai.com/llms.txt
Use this file to discover all available pages before exploring further.
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)
},
}
- “Prefers dark mode”
- “Lives in Mumbai”
- “Works on logistics software”
The memory system automatically extracts facts from conversations:
// Conversation:
// User: "I'm based in Mumbai and usually work late, so schedule meetings after 6 PM IST."
// Extracted facts:
// - "Based in Mumbai"
// - "Prefers meetings after 6 PM IST"
// - "Works late hours"
// The agent sees in its next run:
// "User Facts:
// - Based in Mumbai
// - Prefers meetings after 6 PM IST
// - Works late hours"
User Profile
Structured user data — name, role, company, timezone, language, custom fields.
memory: {
storage,
userProfile: {
customFields: ["department", "subscription_tier"],
},
}
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
},
}
search_entities, create_entity.
Entities are automatically extracted from conversations:
// Conversation:
// User: "We need to update the Xhipment dashboard. Talk to Raj from the frontend team."
// Extracted entities:
// - Xhipment (type: "product", attributes: { category: "dashboard" })
// - Raj (type: "person", attributes: { team: "frontend" })
// Agent can search entities using the auto-exposed tool:
// search_entities({ query: "frontend" })
// → [{ name: "Raj", type: "person", attributes: { team: "frontend" } }]
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)
},
}
log_decision, record_outcome, search_decisions.
Decisions are logged with context for audit trails:
// The agent automatically logs decisions using the log_decision tool:
// log_decision({
// decision: "Approved refund of $45.99 for order #12345",
// reasoning: "Order was delayed by 7 days, exceeding the 5-day SLA",
// context: "Customer reported non-delivery on Dec 22",
// })
// Later, search past decisions:
// search_decisions({ query: "refund policy" })
// → [{ decision: "Approved refund of $45.99...", reasoning: "..." }]
// Record outcomes to track decision quality:
// record_outcome({
// decisionId: "dec-abc123",
// outcome: "success",
// notes: "Customer confirmed receipt of refund",
// })
Learned Knowledge
Vector-backed insights from conversations. Requires a VectorStore.
import { QdrantVectorStore, OpenAIEmbedding } from "@agentium/core";
memory: {
storage,
learnings: {
vectorStore: new QdrantVectorStore({
url: "http://localhost:6333",
embedding: new OpenAIEmbedding(),
}),
collection: "agentium_learnings", // default
topK: 3, // results injected into context
},
}
save_learning / search_learnings tools.
How Learnings Work
// Setup with vector store
const agent = new Agent({
name: "support-agent",
model: openai("gpt-4o"),
memory: {
storage,
learnings: {
vectorStore: new QdrantVectorStore({
url: "http://localhost:6333",
embedding: new OpenAIEmbedding(),
}),
topK: 3, // Inject top 3 most relevant learnings
},
},
});
// During a conversation, the agent discovers a useful pattern:
// Agent uses save_learning tool:
// save_learning({
// content: "For delayed international shipments, check customs hold status
// before issuing refunds. 80% of 'lost' packages are stuck in customs.",
// tags: ["shipping", "customs", "refund"],
// })
// In a FUTURE conversation about a different delayed shipment:
// The vector store finds this learning is relevant
// and injects it into the system prompt:
// "Relevant Learnings:
// - For delayed international shipments, check customs hold status
// before issuing refunds. 80% of 'lost' packages are stuck in customs."
Graph Memory
Knowledge graph with entity-relationship tracking. Unlike flat entity memory, graph memory builds a traversable graph of nodes and edges with temporal metadata.
import { InMemoryGraphStore } from "@agentium/core";
memory: {
storage,
graph: {
store: new InMemoryGraphStore(),
autoExtract: true, // extract entities + relationships from conversations
maxContextNodes: 10, // max nodes in context string
},
}
Procedure Memory
Records and reuses successful multi-step tool-call workflows.
memory: {
storage,
procedures: true, // or { maxProcedures: 100 }
}
Temporal Awareness
All fact-based stores (User Facts, Entity Memory) now support temporal fields:
validFrom — when the fact became validinvalidatedAt — when a newer fact superseded it
The LLM extraction prompts detect contradictions and mark old facts as superseded rather than keeping duplicates.
See Temporal Awareness for full documentation.
When memory stores are enabled, these tools become available to the agent:
| Store | Tools | Description |
|---|
| Entity Memory | search_entities, create_entity | Search and create entity records |
| Decision Log | log_decision, record_outcome, search_decisions | Log decisions and track outcomes |
| Learnings | save_learning, search_learnings | Save and retrieve vector-backed insights |
| Graph Memory | query_graph, traverse_entity, add_relationship | Query and traverse the knowledge graph |
| Procedures | recall_procedure | Find matching multi-step workflows |
