Skip to main content
Nebula Hero

​
Welcome to Nebula

Nebula is the memory layer for AI applications. It ingests documents, conversations, files, and connected sources, then builds a vector graph your AI can search and reason over. Retrieval returns entities, facts, and source utterances instead of flat text chunks.

​
Quick Example

from nebula import Nebula, Memory

nebula = Nebula()

# Create a collection
collection = nebula.create_collection(name="engineering_team")

# Store a memory
nebula.store_memory(
    Memory(
        collection_id=collection.id,
        content="Sarah led the migration from PostgreSQL to Aurora last quarter. The project reduced our p99 latency from 200ms to 45ms.",
        metadata={"source": "standup_notes"}
    )
)

# Search
results = nebula.search(
    query="What has Sarah worked on?",
    collection_ids=[collection.id]
)
Get your API key and start building →

​
How It Works

1

Ingest

Store documents, conversations, or files. Connect external sources like Google Drive, Gmail, Notion, and Slack. Nebula parses 40+ file formats including PDFs, images, and audio.
2

Extract

Nebula automatically builds a vector graph from your content, linking entities and relationships with temporal awareness and fact corroboration across sources.
3

Recall

Search returns three layers of memory: entities (who and what), facts (assertions about them), and utterances (the original source text).

​
Key Features

  • Vector Graph - Automatic entity and relationship extraction from raw content
  • Hierarchical Retrieval - Three layers: entities, facts, and source utterances
  • Multimodal Ingestion - 40+ file formats including PDFs, images, audio, and code
  • Connectors - Sync from Google Drive, Gmail, Notion, and Slack via OAuth
  • Conversation Memory - Multi-turn context with speaker identity tracking
  • Multi-Language SDKs - Python, JavaScript/TypeScript, REST API, and MCP

​
Core Concepts

Memory Operations

Store, retrieve, and manage documents, conversations, and files

Collections

Group related memories with scoped access control

Search

Vector graph traversal with effort levels and collection scoping

Conversations

Build multi-turn chat applications with persistent context

Connectors

OAuth-based sync for Google Drive, Gmail, Notion, and Slack

Architecture

Memories, chunks, and the vector graph

​
Client Libraries

Python SDK

Sync and async client for Python 3.8+

JavaScript SDK

TypeScript SDK with full type definitions

MCP Integration

Connect AI assistants via Model Context Protocol

​
Support

Need help? Reach out to support@trynebula.ai