[{"data":1,"prerenderedAt":4},["ShallowReactive",2],{"readme:supermemory":3},"\u003Cp align=\"center\">\n  \u003Cpicture>\n    \u003Csource srcset=\"apps\u002Fweb\u002Fpublic\u002Flogo-fullmark.svg\" media=\"(prefers-color-scheme: dark)\">\u003C\u002Fsource>\n    \u003Csource srcset=\"apps\u002Fweb\u002Fpublic\u002Flogo-light-fullmark.svg\" media=\"(prefers-color-scheme: light)\">\u003C\u002Fsource>\n    \u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Fsupermemoryai\u002Fsupermemory\u002FHEAD\u002Fapps\u002Fweb\u002Fpublic\u002Flogo-fullmark.svg\" alt=\"Supermemory\" width=\"400\" \u002F>\n  \u003C\u002Fpicture>\n\u003C\u002Fp>\u003Cp align=\"center\">\n  \u003Cstrong>State-of-the-art memory and context engine for AI.\u003C\u002Fstrong>\n\u003C\u002Fp>\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fsupermemory.ai\u002Fdocs\" rel=\"nofollow ugc noopener\">Docs\u003C\u002Fa> ·\n  \u003Ca href=\"https:\u002F\u002Fsupermemory.ai\u002Fdocs\u002Fquickstart\" rel=\"nofollow ugc noopener\">Quickstart\u003C\u002Fa> ·\n  \u003Ca href=\"https:\u002F\u002Fsupermemory.ai\u002Fdocs\u002Fself-hosting\u002Foverview\" rel=\"nofollow ugc noopener\">Self-host\u003C\u002Fa> ·\n  \u003Ca href=\"https:\u002F\u002Fconsole.supermemory.ai\" rel=\"nofollow ugc noopener\">Dashboard\u003C\u002Fa> ·\n  \u003Ca href=\"https:\u002F\u002Fsupermemory.link\u002Fdiscord\" rel=\"nofollow ugc noopener\">Discord\u003C\u002Fa>\n\u003C\u002Fp>\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002Fsupermemory\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fnpm\u002Fv\u002Fsupermemory?style=flat-square&color=blue\" alt=\"npm\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fpypi.org\u002Fproject\u002Fsupermemory\u002F\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fv\u002Fsupermemory?style=flat-square&color=blue\" alt=\"pypi\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fsupermemory.ai\u002Fdocs\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fdocs-supermemory.ai-blue?style=flat-square\" alt=\"docs\" \u002F>\u003C\u002Fa>\n\u003C\u002Fp>\u003Cp align=\"center\">\n  \u003Cstrong>English\u003C\u002Fstrong> · \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fsupermemoryai\u002Fsupermemory\u002Fblob\u002FHEAD\u002FREADME.zh-CN.md\" rel=\"nofollow ugc noopener\">简体中文\u003C\u002Fa>\n\u003C\u002Fp>\u003Cp align=\"center\">\n  \u003Cstrong>#1 on every major AI memory benchmark — \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fxiaowu0162\u002FLongMemEval\" rel=\"nofollow ugc noopener\">LongMemEval\u003C\u002Fa>, \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fsnap-research\u002Flocomo\" rel=\"nofollow ugc noopener\">LoCoMo\u003C\u002Fa>, and \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FSalesforce\u002FConvoMem\" rel=\"nofollow ugc noopener\">ConvoMem\u003C\u002Fa>.\u003C\u002Fstrong>\u003Cbr \u002F>\n  \u003Cstrong>95% Recall@15 with a 99.4% context reduction · ~50ms user profiles.\u003C\u002Fstrong>\u003Cbr \u002F>\n  \u003Ca href=\"https:\u002F\u002Fsupermemory.ai\u002Fresearch\" rel=\"nofollow ugc noopener\">Read the research →\u003C\u002Fa>\n\u003C\u002Fp>\u003Chr \u002F>\n\u003Cp>Supermemory is the memory and context layer for AI. \u003Cstrong>#1 on \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fxiaowu0162\u002FLongMemEval\" rel=\"nofollow ugc noopener\">LongMemEval\u003C\u002Fa>, \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fsnap-research\u002Flocomo\" rel=\"nofollow ugc noopener\">LoCoMo\u003C\u002Fa>, and \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FSalesforce\u002FConvoMem\" rel=\"nofollow ugc noopener\">ConvoMem\u003C\u002Fa>\u003C\u002Fstrong> — the three major benchmarks for AI memory. \u003C\u002Fp>\n\u003Cp>We are a research lab building the engine, plugins and tools around it.\u003C\u002Fp>\n\u003Cp>Your AI forgets everything between conversations. Supermemory fixes that.\u003C\u002Fp>\n\u003Cp>It 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.\u003C\u002Fp>\n\u003Ctable>\n\u003Cthead>\n\u003Ctr>\n\u003Cth>\u003C\u002Fth>\n\u003Cth>\u003C\u002Fth>\n\u003C\u002Ftr>\n\u003C\u002Fthead>\n\u003Ctbody>\u003Ctr>\n\u003Ctd>🧠 \u003Cstrong>Memory\u003C\u002Fstrong>\u003C\u002Ftd>\n\u003Ctd>Extracts facts from conversations. Handles temporal changes, contradictions, and automatic forgetting.\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>👤 \u003Cstrong>User Profiles\u003C\u002Fstrong>\u003C\u002Ftd>\n\u003Ctd>Auto-maintained user context — stable facts + recent activity. One call, ~50ms.\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>🔍 \u003Cstrong>Hybrid Search\u003C\u002Fstrong>\u003C\u002Ftd>\n\u003Ctd>RAG + Memory in a single query. Knowledge base docs and personalized context together.\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>🔌 \u003Cstrong>Connectors\u003C\u002Fstrong>\u003C\u002Ftd>\n\u003Ctd>Google Drive · Gmail · Notion · OneDrive · GitHub — auto-sync with real-time webhooks.\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>📄 \u003Cstrong>Multi-modal Extractors\u003C\u002Fstrong>\u003C\u002Ftd>\n\u003Ctd>PDFs, images (OCR), videos (transcription), code (AST-aware chunking). Upload and it works.\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003C\u002Ftbody>\u003C\u002Ftable>\n\u003Cp>All of this is in our single memory structure and ontology. \u003C\u002Fp>\n\u003Cimg width=\"1414\" height=\"937\" alt=\"image\" src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F8863b6d9-c043-4c75-b200-4f1759e7edaf\" \u002F>\u003Chr \u002F>\n\u003Ch2>Use Supermemory\u003C\u002Fh2>\n\u003Ctable>\n\u003Ctr>\n\u003Ctd>\u003Ch3>🧑‍💻 I use AI tools\u003C\u002Fh3>\u003Cp>Give Claude Code, Muse Code, Cursor, Codex and OpenCode \u003Cstrong>persistent memory across every conversation\u003C\u002Fstrong> with a plugin or the MCP server.\u003C\u002Fp>\n\u003Cp>Your AI remembers your preferences, projects, past discussions — and gets smarter over time.\u003C\u002Fp>\n\u003Cp>\u003Cstrong>\u003Ca href=\"#give-your-ai-memory\" rel=\"nofollow ugc noopener\">→ Jump to User setup\u003C\u002Fa>\u003C\u002Fstrong>\u003C\u002Fp>\n\u003C\u002Ftd>\n\u003Ctd>\u003Ch3>🔧 I'm building AI products\u003C\u002Fh3>\u003Cp>Add memory, RAG, user profiles, and connectors to your agents and apps with \u003Cstrong>a single API\u003C\u002Fstrong>.\u003C\u002Fp>\n\u003Cp>No vector DB config. No embedding pipelines. No chunking strategies.\u003C\u002Fp>\n\u003Cp>\u003Cstrong>\u003Ca href=\"#build-with-supermemory-api\" rel=\"nofollow ugc noopener\">→ Jump to developer quickstart\u003C\u002Fa>\u003C\u002Fstrong>\u003C\u002Fp>\n\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003C\u002Ftr>\u003C\u002Ftable>",1790633832920]