Quick Start - Nebula

You’ll need a Nebula API key before starting. Get one at zeroset.com.

Using Claude Code, Cursor, or Codex? Run npx skills add zeroset-inc/skills to integrate Nebula automatically.

Prerequisites

Python 3.10+ or Node.js 18+
A Nebula API key from the dashboard

1. Install

# Python
pip install nebula-sdk

# Node.js
npm install @nebula-ai/sdk

2. Initialize Client

from nebula import Nebula

# Uses NEBULA_API_KEY environment variable
nebula = Nebula()

import Nebula from '@nebula-ai/sdk';

const client = new Nebula({
  apiKey: process.env.NEBULA_API_KEY,
});

# Verify your API key by listing collections
curl -X GET "https://api.zeroset.com/v1/collections?limit=5" \
  -H "Authorization: Bearer YOUR_API_KEY"

3. Store & Search

from nebula import Nebula

nebula = Nebula()

# Create a collection
collection = nebula.collections.create(
    name="my_notes",
    description="Personal notes",
).results

# Store a memory
created = nebula.memories.create(
    collection_id=collection.id,
    raw_text="Machine learning is transforming healthcare",
    metadata={"topic": "AI", "importance": "high"},
).results
memory_id = created.id

# Search memories
results = nebula.memories.search(
    query="machine learning healthcare",
    collection_ids=[collection.id],
    include_sources=True,
).results

# Results contain semantic, procedural, episodic, and sources
for fact in results.semantic or []:
    print(f"[{fact['category']}] {fact['description']}")
for source in results.sources or []:
    print(source['text'])

import Nebula from '@nebula-ai/sdk';

const client = new Nebula({
  apiKey: process.env.NEBULA_API_KEY,
});

async function storeAndSearch() {
  // Create a collection
  const { results: collection } = await client.collections.create({
    name: 'my_notes',
    description: 'Personal notes',
  });

  // Store a memory
  const { results: created } = await client.memories.create({
    collection_id: collection.id,
    raw_text: 'Machine learning is transforming healthcare',
    metadata: { topic: 'AI', importance: 'high' },
  });
  const memoryId = created.id;

  // Search memories
  const { results } = await client.memories.search({
    query: 'machine learning healthcare',
    collection_ids: [collection.id],
    include_sources: true,
  });

  // Results contain semantic, procedural, episodic, and sources
  results.semantic?.forEach(fact =>
    console.log(`[${fact.category}] ${fact.description}`)
  );
  results.sources?.forEach(source => console.log(source.text));
}

storeAndSearch();

# 1) Create a collection
curl -X POST "https://api.zeroset.com/v1/collections" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{"name": "my_notes", "description": "Personal notes"}'

# 2) Store a memory (use collection ID from step 1)
curl -X POST "https://api.zeroset.com/v1/memories" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "collection_id": "COLLECTION_ID",
    "kind": "document",
    "raw_text": "Machine learning is transforming healthcare",
    "metadata": {"topic": "AI", "importance": "high"}
  }'

# 3) Search memories
curl -X POST "https://api.zeroset.com/v1/memories/search" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "query": "machine learning healthcare",
    "collection_ids": ["COLLECTION_ID"],
    "include_sources": true
  }'

What You’ll Get Back

When you store a memory, Nebula returns the memory ID:

memory_id = "eng_abc123def456"

When you search, Nebula returns a MemoryResponse with structured memory:

{
  "semantic": [
    {
      "category": "fact",
      "description": "Machine Learning is transforming healthcare",
      "activation_score": 0.92
    }
  ],
  "procedural": [],
  "episodic": [],
  "sources": [
    {
      "text": "Machine learning is transforming healthcare",
      "activation_score": 0.91
    }
  ]
}

Semantics: Subject-predicate-value assertions (facts, inferences, tasks)
Procedures: User preferences and behavioral patterns
Episodes: Temporally clustered events
Sources: The original source text that grounds each assertion

See Core Concepts for a deeper explanation of the memory response.

Next Steps

Core Concepts - Understand how Nebula works
Memory Operations Guide - Detailed examples and advanced usage
Collections Guide - Organize your memories effectively
Search Guide - Semantic search and filtering
Support: Join our Slack community or email support@zeroset.com

​Prerequisites

​1. Install

​2. Initialize Client

​3. Store & Search

​What You’ll Get Back

​Next Steps

Prerequisites

1. Install

2. Initialize Client

3. Store & Search

What You’ll Get Back

Next Steps