supermemory™

What it does

Supermemory is a universal memory API for the AI era, designed to help developers stop building retrieval from scratch and personalize LLMs for their users. It provides an unlimited context API that offers automatic long-term context across conversations. Built for developers who ship, it handles enterprise-grade performance at any scale, seamlessly integrates across teams and tools, and allows users to own their data while maintaining compliance with secure and controllable deployment options (cloud, on-prem, on-device). It is model-agnostic, works with any LLM provider, and delivers sub-400ms latency with best-in-class precision and recall.

How to use: Supermemory can be used by integrating its API or SDKs into your applications. To add memories, make a POST request to `https://api.supermemory.ai/v3/memories` with content (text, URL, or PDF) and optional metadata. To search memories, make a GET request to the same endpoint with a query `q`. To connect apps like OneDrive, use specific connection endpoints (e.g., `https://api.supermemory.ai/v3/connections/onedrive`). For OpenAI integration, simply change your OpenAI client's `baseUrl` to `https://api.supermemory.ai/v3/https://api.openai.com/v1/` for automatic long-term context. SDKs are available for Python (`pip install 'supermemory'`) and Javascript (`npm install 'supermemory'`).

Core features

• ✦Universal memory API for the AI era
• ✦Unlimited context API for LLMs
• ✦Enterprise-Grade Performance at Any Scale (billions of data points, low-latency retrieval)
• ✦Seamless Integration Across Teams & Tools (Notion, Google Drive, CRMs)
• ✦Secure by Design, Fully Controllable deployment (cloud, on-prem, on-device)
• ✦Model-agnostic APIs (works with any LLM provider)
• ✦Sub-400ms latency at scale
• ✦Best in class performance (stronger precision and recall)
• ✦Works with AI SDK, Langchain, and more
• ✦Language Agnostic SDKs (Python, Javascript)

Use cases

• →Personalizing LLMs for users.
• →Adding automatic long-term context across conversations for agentic apps.
• →Building memory infrastructure without starting from scratch.
• →Indexing documents, video, or structured product data at scale.
• →Connecting to existing data sources like Notion, Google Drive, and custom CRMs.
• →Flow uses Supermemory to build the cursor for writing.
• →Medtech Vendors use Supermemory to search through 500k vendors.
• →Mixus uses Supermemory to power co-intelligence Agentic platform.