Supermemory
A developer-friendly memory API with semantic search and content ingestion for building AI apps that remember.
At a Glance
About Supermemory
Supermemory is a semantic memory API designed for developers building AI applications that need contextual recall. It offers vector-based memory storage, semantic search, and ingestion tools for URLs, PDFs, text, and more. The API supports metadata, filters, and query enhancement—making it ideal for Retrieval-Augmented Generation (RAG), chatbots, and custom assistants.
Behind the scenes, Supermemory continuously indexes and organizes your content into meaningful 'memories' that can be searched and recalled by AI systems. With SDKs for TypeScript and Python, integration takes minutes. It’s built for grounding, personalization, and eliminating hallucinations in AI outputs.
Community Discussions
Be the first to start a conversation about Supermemory
Share your experience with Supermemory, ask questions, or help others learn from your insights.
Pricing
Free
Get started with Supermemory at no cost with Limited API usage and Basic ingestion and search.
- Limited API usage
- Basic ingestion and search
- Access to SDKs
Free Trial
Try Supermemory for 7 days with access to Free trial available.
- Free trial available
Pro
Professional plan with Higher ingestion and query limits and Private memory partitions for power users.
- Higher ingestion and query limits
- Private memory partitions
- Access to full feature set
Capabilities
Key Features
- Semantic search over stored knowledge
- Ingest content from URLs, PDFs, images, or raw text
- Metadata support and advanced filtering
- User-based memory partitioning
- Query rewriting and reranking
- SDKs for TypeScript and Python
- Simple API for storing and retrieving memories
- Supports grounding and RAG workflows