[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-3690":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":23,"hasPages":23,"topics":25,"createdAt":10,"pushedAt":10,"updatedAt":38,"readmeContent":39,"aiSummary":40,"trendingCount":16,"starSnapshotCount":16,"syncStatus":41,"lastSyncTime":42,"discoverSource":43},3690,"supermemory","supermemoryai\u002Fsupermemory","supermemoryai","Memory engine and app that is extremely fast, scalable. The Memory API for the AI era.","https:\u002F\u002Fsupermemory.ai\u002Fdocs",null,"TypeScript",26742,2328,96,5,0,320,1281,4227,1212,45,"MIT License",false,"main",[26,27,28,29,30,31,32,33,34,35,36,37],"agent-memory","ai-memory","cloudflare-kv","cloudflare-pages","cloudflare-workers","drizzle-orm","memory","postgres","remix","tailwindcss","typescript","vite","2026-06-12 02:00:52","\u003Cp align=\"center\">\n  \u003Cpicture>\n    \u003Csource srcset=\"apps\u002Fweb\u002Fpublic\u002Flogo-fullmark.svg\" media=\"(prefers-color-scheme: dark)\">\n    \u003Csource srcset=\"apps\u002Fweb\u002Fpublic\u002Flogo-light-fullmark.svg\" media=\"(prefers-color-scheme: light)\">\n    \u003Cimg src=\"apps\u002Fweb\u002Fpublic\u002Flogo-fullmark.svg\" alt=\"Supermemory\" width=\"400\" \u002F>\n  \u003C\u002Fpicture>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Cstrong>State-of-the-art memory and context engine for AI.\u003C\u002Fstrong>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fsupermemory.ai\u002Fdocs\">Docs\u003C\u002Fa> ·\n  \u003Ca href=\"https:\u002F\u002Fsupermemory.ai\u002Fdocs\u002Fquickstart\">Quickstart\u003C\u002Fa> ·\n  \u003Ca href=\"https:\u002F\u002Fconsole.supermemory.ai\">Dashboard\u003C\u002Fa> ·\n  \u003Ca href=\"https:\u002F\u002Fsupermemory.link\u002Fdiscord\">Discord\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002Fsupermemory\">\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\">\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\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fdocs-supermemory.ai-blue?style=flat-square\" alt=\"docs\" \u002F>\u003C\u002Fa>\n\u003C\u002Fp>\n\n---\n\nSupermemory is the memory and context layer for AI. **#1 on [LongMemEval](https:\u002F\u002Fgithub.com\u002Fxiaowu0162\u002FLongMemEval), [LoCoMo](https:\u002F\u002Fgithub.com\u002Fsnap-research\u002Flocomo), and [ConvoMem](https:\u002F\u002Fgithub.com\u002FSalesforce\u002FConvoMem)** — 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\u003Cimg width=\"1414\" height=\"937\" alt=\"image\" src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F8863b6d9-c043-4c75-b200-4f1759e7edaf\" \u002F>\n\n\n---\n\n## Use Supermemory\n\n\u003Ctable>\n\u003Ctr>\n\u003Ctd width=\"50%\" valign=\"top\">\n\n\u003Ch3>🧑‍💻 I use AI tools\u003C\u002Fh3>\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\u003C\u002Ftd>\n\u003Ctd width=\"50%\" valign=\"top\">\n\n\u003Ch3>🔧 I'm building AI products\u003C\u002Fh3>\n\nAdd memory, RAG, user profiles, and connectors to your agents and apps with **a single API**.\n\nNo vector DB config. No embedding pipelines. No chunking strategies.\n\n**[→ Jump to developer quickstart](#build-with-supermemory-api)**\n\n\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003C\u002Ftable>\n\n---\n\n## Give your AI memory\n\nThe Supermemory App, browser extension, plugins and MCP server gives any compatible AI assistant persistent memory. One install, and your AI remembers you.\n\n### The app\n\nYou can use supermemory without any code, by using our consumer-facing app for free.\n\nStart at https:\u002F\u002Fapp.supermemory.ai\n\n\u003Cimg width=\"1705\" height=\"1030\" alt=\"image\" src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F5b43af30-b998-4585-8de6-f3e9a26d894a\" \u002F>\n\nIt also comes with an agent embedded inside, which we call Nova.\n\n### Supermemory Plugins\n\nSupermemory comes built with Plugins for Claude Code, OpenCode, OpenClaw, and Hermes.\n\n\u003Cimg width=\"844\" height=\"484\" alt=\"image\" src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Fecb879a2-8652-495d-9228-f305a97ba603\" \u002F>\n\nThese plugins are implementations of the supermemory API, and they are open source! \n\nYou can find them here: \n\n- Openclaw plugin: https:\u002F\u002Fgithub.com\u002Fsupermemoryai\u002Fopenclaw-supermemory\n- Claude code plugin: https:\u002F\u002Fgithub.com\u002Fsupermemoryai\u002Fclaude-supermemory\n- OpenCode plugin: https:\u002F\u002Fgithub.com\u002Fsupermemoryai\u002Fopencode-supermemory\n- Hermes agent (Supermemory memory provider): https:\u002F\u002Fgithub.com\u002FNousResearch\u002Fhermes-agent\n\n### MCP - Quick install\n\n```bash\nnpx -y install-mcp@latest https:\u002F\u002Fmcp.supermemory.ai\u002Fmcp --client claude --oauth=yes\n```\n\nReplace `claude` with your client: `cursor`, `windsurf`, `vscode`, etc.\n\nRead more about our MCP here - https:\u002F\u002Fsupermemory.ai\u002Fdocs\u002Fsupermemory-mcp\u002Fmcp\n\n### What your AI gets\n\n| Tool | What it does |\n|---|---|\n| `memory` | Save or forget information. Your AI calls this automatically when you share something worth remembering. |\n| `recall` | Search memories by query. Returns relevant memories + your user profile summary. |\n| `context` | Injects your full profile (preferences, recent activity) into the conversation at start. In Cursor and Claude Code, just type `\u002Fcontext`. |\n\n### How it works\n\nOnce installed, Supermemory runs in the background:\n\n1. **You talk to your AI normally.** Share preferences, mention projects, discuss problems.\n2. **Supermemory extracts and stores the important stuff.** Facts, preferences, project context — not noise.\n3. **Next conversation, your AI already knows you.** It recalls what you're working on, how you like things, what you discussed before.\n\nMemory is scoped with **projects** (container tags) so you can separate work and personal context, or organize by client, repo, or anything else.\n\n### Supported clients\n\n**Claude Desktop** · **Cursor** · **Windsurf** · **VS Code** · **Claude Code** · **OpenCode** · **OpenClaw** · **Hermes**\n\nThe MCP server is open source — [view the source](https:\u002F\u002Fsupermemory.ai\u002Fdocs\u002Fsupermemory-mcp\u002Fmcp).\n\n### Manual configuration\n\nAdd this to your MCP client config:\n\n```json\n{\n  \"mcpServers\": {\n    \"supermemory\": {\n      \"url\": \"https:\u002F\u002Fmcp.supermemory.ai\u002Fmcp\"\n    }\n  }\n}\n```\n\nOr use an API key instead of OAuth:\n\n```json\n{\n  \"mcpServers\": {\n    \"supermemory\": {\n      \"url\": \"https:\u002F\u002Fmcp.supermemory.ai\u002Fmcp\",\n      \"headers\": {\n        \"Authorization\": \"Bearer sm_your_api_key_here\"\n      }\n    }\n  }\n}\n```\n\n---\n\n## Build with Supermemory (API)\n\nIf you're building AI agents or apps, Supermemory gives you the entire context stack through one API — memory, RAG, user profiles, connectors, and file processing.\n\n### Install\n\n```bash\nnpm install supermemory    # or: pip install supermemory\n```\n\n### Quickstart\n\n```typescript\nimport Supermemory from \"supermemory\";\n\nconst client = new Supermemory();\n\n\u002F\u002F Store a conversation\nawait client.add({\n  content: \"User loves TypeScript and prefers functional patterns\",\n  containerTag: \"user_123\",\n});\n\n\u002F\u002F Get user profile + relevant memories in one call\nconst { profile, searchResults } = await client.profile({\n  containerTag: \"user_123\",\n  q: \"What programming style does the user prefer?\",\n});\n\n\u002F\u002F profile.static  → [\"Loves TypeScript\", \"Prefers functional patterns\"]\n\u002F\u002F profile.dynamic → [\"Working on API integration\"]\n\u002F\u002F searchResults   → Relevant memories ranked by similarity\n```\n\n```python\nfrom supermemory import Supermemory\n\nclient = Supermemory()\n\nclient.add(\n    content=\"User loves TypeScript and prefers functional patterns\",\n    container_tag=\"user_123\"\n)\n\nresult = client.profile(container_tag=\"user_123\", q=\"programming style\")\n\nprint(result.profile.static)   # Long-term facts\nprint(result.profile.dynamic)  # Recent context\n```\n\nSupermemory automatically extracts memories, builds user profiles, and returns relevant context. No embedding pipelines, no vector DB config, no chunking strategies.\n\n### Framework integrations\n\nDrop-in wrappers for every major AI framework:\n\n```typescript\n\u002F\u002F Vercel AI SDK\nimport { withSupermemory } from \"@supermemory\u002Ftools\u002Fai-sdk\";\nconst model = withSupermemory(openai(\"gpt-4o\"), { containerTag: \"user_123\", customId: \"conv-1\" });\n\n\u002F\u002F Mastra\nimport { withSupermemory } from \"@supermemory\u002Ftools\u002Fmastra\";\nconst agent = new Agent(withSupermemory(config, \"user-123\", { mode: \"full\" }));\n```\n\n**Vercel AI SDK** · **LangChain** · **LangGraph** · **OpenAI Agents SDK** · **Mastra** · **Agno** · **Claude Memory Tool** · **n8n**\n\n### Search modes\n\n```typescript\n\u002F\u002F Hybrid (default) — RAG + Memory in one query\nconst results = await client.search.memories({\n  q: \"how do I deploy?\",\n  containerTag: \"user_123\",\n  searchMode: \"hybrid\",\n});\n\u002F\u002F Returns deployment docs (RAG) + user's deploy preferences (Memory)\n\n\u002F\u002F Memories only\nconst results = await client.search.memories({\n  q: \"user preferences\",\n  containerTag: \"user_123\",\n  searchMode: \"memories\",\n});\n```\n\n### User profiles\n\nTraditional memory relies on search — you need to know what to ask for. Supermemory automatically maintains a profile for every user:\n\n```typescript\nconst { profile } = await client.profile({ containerTag: \"user_123\" });\n\n\u002F\u002F profile.static  → [\"Senior engineer at Acme\", \"Prefers dark mode\", \"Uses Vim\"]\n\u002F\u002F profile.dynamic → [\"Working on auth migration\", \"Debugging rate limits\"]\n```\n\nOne call. ~50ms. Inject into your system prompt and your agent instantly knows who it's talking to.\n\n### Connectors\n\nAuto-sync external data into your knowledge base:\n\n**Google Drive** · **Gmail** · **Notion** · **OneDrive** · **GitHub** · **Web Crawler**\n\nReal-time webhooks. Documents automatically processed, chunked, and searchable.\n\n### API at a glance\n\n| Method | Purpose |\n|---|---|\n| `client.add()` | Store content — text, conversations, URLs, HTML |\n| `client.profile()` | User profile + optional search in one call |\n| `client.search.memories()` | Hybrid search across memories and documents |\n| `client.search.documents()` | Document search with metadata filters |\n| `client.documents.uploadFile()` | Upload PDFs, images, videos, code |\n| `client.documents.list()` | List and filter documents |\n| `client.settings.update()` | Configure memory extraction and chunking |\n\nFull API reference → [supermemory.ai\u002Fdocs](https:\u002F\u002Fsupermemory.ai\u002Fdocs)\n\n---\n\n## Benchmarks\n\nSupermemory is state of the art across all major AI memory benchmarks:\n\n| Benchmark | What it measures | Result |\n|---|---|---|\n| **[LongMemEval](https:\u002F\u002Fgithub.com\u002Fxiaowu0162\u002FLongMemEval)** | Long-term memory across sessions with knowledge updates | **81.6% — #1** |\n| **[LoCoMo](https:\u002F\u002Fgithub.com\u002Fsnap-research\u002Flocomo)** | Fact recall across extended conversations (single-hop, multi-hop, temporal, adversarial) | **#1** |\n| **[ConvoMem](https:\u002F\u002Fgithub.com\u002FSalesforce\u002FConvoMem)** | Personalization and preference learning | **#1** |\n\nWe also built **[MemoryBench](https:\u002F\u002Fsupermemory.ai\u002Fdocs\u002Fmemorybench\u002Foverview)** — an open-source framework for standardized, reproducible benchmarks of memory providers. Compare Supermemory, Mem0, Zep, and others head-to-head:\n\n```bash\nbun run src\u002Findex.ts run -p supermemory -b longmemeval -j gpt-4o -r my-run\n```\n\n### Benchmarking your own memory solution\n\nWe provide an Agent skill for companies to benchmark their own context and memory solutions against supermemory.\n\n```\nnpx skills add supermemoryai\u002Fmemorybench\n```\n\nSimply run this and do `\u002Fbenchmark-context` - Supermemory will automatically do the work for you!\n\n---\n\n## How memory works under the hood\n\n```\nYour app \u002F AI tool\n        ↓\n   Supermemory\n        │\n        ├── Memory Engine     Extracts facts, tracks updates, resolves contradictions,\n        │                     auto-forgets expired info\n        ├── User Profiles     Static facts + dynamic context built from engine, always fresh\n        ├── Hybrid Search     RAG + Memory in one query\n        ├── Connectors        Real-time sync from Google Drive, Gmail, Notion, GitHub...\n        └── File Processing   PDFs, images, videos, code → searchable chunks\n```\n\n**Memory is not RAG.** RAG retrieves document chunks — stateless, same results for everyone. Memory extracts and tracks *facts about users* over time. It understands that \"I just moved to SF\" supersedes \"I live in NYC.\" Supermemory runs both together by default, so you get knowledge base retrieval *and* personalized context in every query. Read more about this here - https:\u002F\u002Fsupermemory.ai\u002Fdocs\u002Fconcepts\u002Fmemory-vs-rag\n\n**Automatic forgetting.** Supermemory knows when memories become irrelevant. Temporary facts (\"I have an exam tomorrow\") expire after the date passes. Contradictions are resolved automatically. Noise never becomes permanent memory.\n\n---\n\n## Links\n\n- 📖 [Documentation](https:\u002F\u002Fsupermemory.ai\u002Fdocs)\n- 🚀 [Quickstart](https:\u002F\u002Fsupermemory.ai\u002Fdocs\u002Fquickstart)\n- 🧪 [MemoryBench](https:\u002F\u002Fsupermemory.ai\u002Fdocs\u002Fmemorybench\u002Foverview)\n- 🔌 [Integrations](https:\u002F\u002Fsupermemory.ai\u002Fdocs\u002Fintegrations)\n- 💬 [Discord](https:\u002F\u002Fsupermemory.link\u002Fdiscord)\n- 𝕏 [Twitter](https:\u002F\u002Ftwitter.com\u002Fsupermemory)\n\n---\n\n\u003Cp align=\"center\">\n  \u003Cstrong>Give your AI a memory. It's about time..\u003C\u002Fstrong>\n\u003C\u002Fp>\n","Supermemory 是一个专为AI设计的记忆和上下文引擎，旨在解决AI在对话间遗忘信息的问题。它能够自动从对话中学习、提取事实、构建用户画像、处理知识更新与矛盾，并适时忘记过期信息。其核心功能包括高效的记忆管理、用户画像维护、混合搜索（结合检索增强生成和记忆）、多模态数据提取以及与多种云服务的连接器集成。项目使用TypeScript开发，具备极高的可扩展性和性能。适用于需要持续上下文支持的AI应用场合，如聊天机器人、虚拟助手等场景，以提供更加个性化和连贯的用户体验。",2,"2026-06-06 02:56:20","top_language"]