Semantic Memory API for AI Agents

GIVE YOUR AI
LONG-TERM MEMORY

Semantic memory infrastructure for AI applications. Store, search, and retrieve memories with vector embeddings and knowledge graphs.

Open Source
99.9% Uptime
<100ms Search
pgvector Powered
10M+
Memories Stored
<100ms
Search Latency
99.9%
Uptime SLA
1536
Vector Dimensions

USE CASES

From AI assistants to knowledge management, one API for all your memory needs

AI Agent Memory

Give your AI assistants persistent memory across sessions. Remember user preferences, past conversations, and context.

Knowledge Graphs

Automatically build and query knowledge graphs from stored memories. Understand relationships between entities.

Semantic Search

Find relevant memories using natural language queries. Vector embeddings for accurate similarity matching.

Entity Extraction

Automatically extract people, places, dates, and concepts from text. Structured data from unstructured content.

SIMPLE API

Store and search memories with a simple API.

more...
# Store a memory
curl -X POST https://server.aiget.dev/api/v1/memories \
  -H "Authorization: Bearer ag_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "content": "User prefers dark mode and concise responses",
    "userId": "user_123",
    "tags": ["preferences", "ui"]
  }'

# Search memories
curl -X POST https://server.aiget.dev/api/v1/memories/search \
  -H "Authorization: Bearer ag_your_api_key" \
  -d '{ "query": "user preferences", "limit": 5 }'

FEATURES

Everything you need for production-grade memory infrastructure

Semantic Search

Vector-powered search finds relevant memories based on meaning, not keywords.

Knowledge Graph

Automatic entity extraction and relationship mapping for connected memories.

Multi-tenant Isolation

API Key-based data isolation ensures complete separation between users.

Rich Metadata

Store custom metadata, tags, and timestamps with each memory.

LLM Integration

Built-in entity and relation extraction using state-of-the-art language models.

Fast & Scalable

Sub-100ms search latency with pgvector-powered vector similarity.

Developer First

RESTful API with webhooks, comprehensive docs, and easy integration.

Graph Traversal

Navigate relationships, find paths, and explore connected knowledge.

PRICING

Simple, transparent pricing that scales with you

Free

$0/month

Perfect for side projects and testing

  • 10,000 memories
  • 1,000 API calls/month
  • Semantic search
  • Knowledge graph
  • Entity extraction
  • Community support

Hobby

$19/month

For growing teams and production apps

  • 50,000 memories
  • 5,000 API calls/month
  • Everything in Free
  • Higher rate limits
  • Webhooks
  • Priority support

Enterprise

Pay-as-you-go

For large-scale operations

  • Unlimited memories
  • Unlimited API calls
  • Everything in Hobby
  • Custom SLA (99.99%)
  • 24/7 technical support
  • Custom features & integrations

READY TO GET STARTED?

Start building AI memory in minutes. No credit card required.