supermemory
Frameworksupermemoryai/supermemory
Memory engine and API for AI agents, providing persistent context and user profiles.
Overview
Supermemory is a state-of-the-art memory and context engine for AI. It extracts facts from conversations, builds user profiles, and provides hybrid search with RAG. Suitable for both developers and end-users through its API and app.
README Preview
\n \n \n \n \n \n\n\n\n State-of-the-art memory and context engine for AI. And yes - you can use it as a company/personal brain.\n\n\n\n Docs ·\n Quickstart ·\n Dashboard ·\n Discord\n\n\n\n \n \n \n\n\n---\n\nSupermemory is the memory and context layer for AI. **#1 on [LongMemEval](https://github.com/xiaowu0162/LongMemEval), [LoCoMo](https://github.com/snap-research/locomo), and [ConvoMem](https://github.com/Salesforce/ConvoMem)** — the three major benchmarks for AI memory. \n\nWe are a research lab building the engine, plugins and tools around it.\n\nYour AI forgets everything between conversations. Supermemory fixes that.\n\nIt automatically learns from conversations, extracts facts, builds user profiles, handles knowledge updates and contradictions, forgets expired information, and delivers the right context at the right time. Full RAG, connectors, file processing — the entire context stack, one system.\n\n| | |\n|---|---|\n| 🧠 **Memory** | Extracts facts from conversations. Handles temporal changes, contradictions, and automatic forgetting. |\n| 👤 **User Profiles** | Auto-maintained user context — stable facts + recent activity. One call, ~50ms. |\n| 🔍 **Hybrid Search** | RAG + Memory in a single query. Knowledge base docs and personalized context together. |\n| 🔌 **Connectors** | Google Drive · Gmail · Notion · OneDrive · GitHub — auto-sync with real-time webhooks. |\n| 📄 **Multi-modal Extractors** | PDFs, images (OCR), videos (transcription), code (AST-aware chunking). Upload and it works. |\n\nAll of this is in our single memory structure and ontology. \n\n\n\n\n---\n\n## Use Supermemory\n\n\n\n\n\n🧑💻 I use AI tools\n\nBuild your own personal supermemory by using our app. Builds **persistent memory graph across every conversation**.\n\nYour AI remembers your preferences, projects, past discussions — and gets smarter over time.\n\n**[→ Jump to User setup](#give-your-ai-memory)**\n\n\n\n\n🔧 I'm building AI products\n\nAdd memory, RA
FAQ (1)
TroubleshootingWhy does withSupermemory throw AI_UnsupportedModelVersionError when using AI SDK 6?
The withSupermemory function uses object spread to wrap the language model, but AI SDK 6 models store non-enumerable/prototype properties like specificationVersion, provider, modelId, and supportedUrls. Spread doesn't copy these, causing undefined values that trigger the error. Fix: replace the spread pattern in wrapVercelLanguageModel (packages/tools/src/vercel/index.ts) with the standard wrapLanguageModel middleware approach from 'ai' (import { wrapLanguageModel, LanguageModelV3Middleware } from 'ai'). As a temporary workaround, manually implement a wrapper using wrapLanguageModel until the library updates. Versions affected: @supermemory/tools@1.4.1, ai@6.0.158, @ai-sdk/provider@3.0.8.