Skip to content
HEBBS

TypeScript SDK Quick Start

This guide walks you through connecting to a HEBBS server, storing memories, and recalling them — all in under 30 lines of TypeScript.

Prerequisites

Section titled “Prerequisites”
  • HEBBS TypeScript SDK installed (npm install @hebbs/sdk)
  • A running HEBBS server (default: localhost:6380)
  • Your API key exported: export HEBBS_API_KEY="hb_..."

Full Example

Section titled “Full Example”
import { HebbsClient, MemoryKind } from '@hebbs/sdk';


const client = new HebbsClient('localhost:6380', {
  apiKey: process.env.HEBBS_API_KEY,
});
await client.connect();


// Check server health
const health = await client.health();
console.log(`Server status: ${health.serving ? 'serving' : 'not serving'}`);


// Store some memories
const m1 = await client.remember({
  content: 'Customer mentioned they are expanding to Europe next quarter',
  entityId: 'acme-corp',
  kind: MemoryKind.EPISODIC,
});
console.log(`Stored memory: ${m1.id.toString('hex')}`);


const m2 = await client.remember({
  content: 'GDPR compliance is their top concern for the expansion',
  entityId: 'acme-corp',
  kind: MemoryKind.EPISODIC,
});
console.log(`Stored memory: ${m2.id.toString('hex')}`);


const m3 = await client.remember({
  content: 'European expansion requires GDPR compliance as a prerequisite',
  entityId: 'acme-corp',
  kind: MemoryKind.SEMANTIC,
});
console.log(`Stored memory: ${m3.id.toString('hex')}`);


// Recall by similarity
const results = await client.recall({
  cue: 'What are the customer plans for Europe?',
  entityId: 'acme-corp',
  strategies: ['similarity'],
  topK: 5,
});


console.log(`\nRecall returned ${results.results.length} memories:`);
for (const r of results.results) {
  console.log(`  [${r.score.toFixed(3)}] ${r.memory.content}`);
}


// Recall by temporal proximity
const temporal = await client.recall({
  cue: 'What happened recently with this customer?',
  entityId: 'acme-corp',
  strategies: ['temporal'],
  topK: 5,
});


console.log(`\nTemporal recall returned ${temporal.results.length} memories:`);
for (const r of temporal.results) {
  console.log(`  [${r.memory.createdAt}] ${r.memory.content}`);
}


await client.close();

What Just Happened

Section titled “What Just Happened”
  1. Connect — new HebbsClient() creates the client, and connect() establishes the gRPC channel. Call close() when done.
  2. Remember — each remember() call stores a memory in the engine. HEBBS automatically embeds the content, indexes it across vector, temporal, and graph indexes, and returns the stored memory with its assigned ID.
  3. Recall — recall() queries the engine using one of four strategies: similarity, temporal, causal, or analogical. Results include relevance scores and metadata.

Next Steps

Section titled “Next Steps”