ZeroDB is the persistent knowledge layer for AI agents. It provides memory, semantic search, vector storage, file storage, and free embeddings in one product. It works with LangChain, LlamaIndex, MCP, or raw API — framework-agnostic.

How do I add memory to my AI agent?

Run npx zerodb-cli init to set up a ZeroDB project with MCP server configuration in one command. Then use pip install langchain-zerodb for LangChain or pip install llama-index-vector-stores-zerodb for LlamaIndex. Free embeddings included — no OpenAI key required.

How is ZeroDB different from Mem0?

Mem0 is a memory feature layer. ZeroDB is full knowledge infrastructure — memory, vectors, files, tables, and events in one product with free embeddings, MCP servers, and zero-auth instant provisioning. ZeroDB works with any framework, not just Python.

How is ZeroDB different from Pinecone?

Pinecone is a vector database. ZeroDB is a persistent knowledge layer — it includes vectors plus memory, file storage, event streaming, free embeddings, and MCP server integration. ZeroDB also offers zero-auth instant provisioning (one API call, no signup) and a generous free tier.

Yes. ZeroDB has a free tier with 10,000 vectors, 1,000 free embeddings per month, 1GB storage, and 3 projects. Embeddings are powered by TEI (HuggingFace Text Embeddings Inference) at zero cost. No credit card required. Get started with npx zerodb-cli init.

How does ZeroMemory perform on benchmarks?

ZeroMemory achieved 100% Recall@1 and 94% QA accuracy on the LongMemEval benchmark (ICLR 2025), outperforming Mem0 (25% recall), MemGPT/Letta (40% recall), and even GPT-4o full context window (~70% QA). ZeroMemory uses pgvector cosine similarity with blended scoring (similarity + importance + recency) for sub-400ms retrieval. Install with: npm i ainative-zerodb-memory-mcp.

Persistent Knowledge Layer for AI Agents

ZeroDB

Memory, vectors, events, and files — one API for AI agents that remember. The Mem0 alternative built for production agents.

npx zerodb-cli init

Start Free View Documentation

<1ms

Query Latency

99.99%

Uptime SLA

10B+

Vectors Stored

The Full Knowledge Layer for AI Agents

Everything your agents need to remember, reason, and act — memory, vectors, events, files, and knowledge graphs in one API.

ZeroMemory — Cognitive Agent Memory

Working memory, episodic recall, and semantic memory layers with automatic consolidation, decay scoring, and entity relationship graphs.

Vector Search with pgvector HNSW

Sub-millisecond semantic search backed by pgvector HNSW indexes. Free embeddings included — no OpenAI key required.

NoSQL Tables + Event Streams

Schema-free document tables and real-time event streaming alongside vector storage — one API for your full agent data layer.

File Storage (S3-Compatible)

Agent-native object storage for documents, images, and artifacts. Multi-tenant scoping with fine-grained access controls.

MCP Server Integration

10-tool memory MCP server and 83-tool full database server. Works with Cursor, VS Code, and AINative Studio IDE. Hosted remote MCP available — no local install needed.

Context Graph + GraphRAG

Multi-hop knowledge graph traversal with GraphRAG hybrid search. Ontology-aware entity resolution, edge versioning with contradiction detection, and 5 pre-built semantic templates.

Get Started in 30 Seconds

Get a working database in one command. No signup required. Python, Node.js, LangChain, LlamaIndex — pick your stack.

Instant Setup (no signup)

npx zerodb-cli init

Python SDK

pip install zerodb-mcp

LangChain

pip install langchain-zerodb

LlamaIndex

pip install llama-index-vector-stores-zerodb

MCP Server (Agent Memory)

npm i ainative-zerodb-memory-mcp

Zero-auth instant database (72hr trial, no signup)
Free embeddings — BAAI/bge models, no OpenAI costs
Sub-millisecond search with HNSW indexes
MCP servers for Claude Code, Cursor, VS Code, Windsurf
LangChain + LlamaIndex integrations

# Get a database instantly (no signup required)
curl -X POST https://api.ainative.studio/api/v1/public/instant-db

# Or use the CLI
npx zerodb-cli init

# Python — LangChain integration
from langchain_zerodb import ZeroDBVectorStore

store = ZeroDBVectorStore(
    api_key="your-api-key",
    project_id="your-project-id",
)

# Add documents (embeddings generated FREE)
store.add_texts(["ZeroDB is fast", "Semantic search"])

# Search by meaning
results = store.similarity_search("fast database", k=5)

# LlamaIndex integration
from llama_index_zerodb import ZeroDBVectorStore
from llama_index.core import VectorStoreIndex

index = VectorStoreIndex.from_vector_store(store)
response = index.as_query_engine().query("What is ZeroDB?")