diff --git a/README.md b/README.md index 7c83e240..d93814c6 100644 --- a/README.md +++ b/README.md @@ -1,105 +1,318 @@ -

+

- supermemory Logo + Supermemory -

- Your AI second brain for saving and organizing everything that matters. -

- - Web App - -   - - Chrome Extension - -   - - Raycast Extension - -   - - Discord -

-

- Building with Supermemory? Check out the Developer Console and Documentation for API access. +

+ State-of-the-art memory for AI.

-

- Want to self-host? See our Self-Hosting Guide for enterprise deployment options. + +

+ Docs · + Quickstart · + Dashboard · + Discord

-
-
- supermemory -
+

+ npm + pypi + docs +

-## Features +--- -### Core Functionality +Supermemory 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. -- **[Add Memories from Any Content](#add-memory)**: Easily add memories from URLs, PDFs, and plain text—just paste, upload, or link. -- **[Chat with Your Memories](#chat-memories)**: Converse with your stored content using natural language chat. -- **[Supermemory MCP Integration](#mcp-integration)**: Seamlessly connect with all major AI tools (Claude, Cursor, etc.) via Supermemory MCP. -- **[Browser Extension](#browser-extension)**: Save memories directly from your browser with integrations for ChatGPT, Claude, and Twitter/X. -- **[Raycast Extension](#raycast-extension)**: Add and search memories directly from Raycast with keyboard shortcuts. +Your AI forgets everything between conversations. Supermemory fixes that. -## How do I use this? +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. -Go to [app.supermemory.ai](https://app.supermemory.ai) and sign in with your account +| | | +|---|---| +| 🧠 **Memory** | Extracts facts from conversations. Handles temporal changes, contradictions, and automatic forgetting. | +| 👤 **User Profiles** | Auto-maintained user context — stable facts + recent activity. One call, ~50ms. | +| 🔍 **Hybrid Search** | RAG + Memory in a single query. Knowledge base docs and personalized context together. | +| 🔌 **Connectors** | Google Drive · Gmail · Notion · OneDrive · GitHub — auto-sync with real-time webhooks. | +| 📄 **Files** | PDFs, images (OCR), videos (transcription), code (AST-aware chunking). Upload and it works. | -1. Start Adding Memory with your choice of format (Note, Link, File) -
- supermemory -
+--- -2. You can also Connect to your favourite services (Notion, Google Drive, OneDrive) -
- supermemory -
+## Use Supermemory -3. Once Memories are added, you can chat with Supermemory by clicking on "Open Chat" and retrieve info from your saved memories -
- supermemory -
+ + + + + +
-4. Add MCP to your AI Tools (by clicking on "Connect to your AI" and select the AI tool you are trying to integrate) -
- supermemory -
+

🧑‍💻 I use AI tools

-5. **Browser Extension**: Install the [Chrome/Edge extension](https://chromewebstore.google.com/detail/supermemory/afpgkkipfdpeaflnpoaffkcankadgjfc) to save memories directly from any webpage, integrate with ChatGPT and Claude conversations, and import from Twitter/X. Right-click on any content or use the extension popup to save memories instantly. +Give Claude, Cursor, or any MCP-compatible AI assistant **persistent memory across every conversation**. -6. **Raycast Extension**: Install the [Raycast extension](https://www.raycast.com/supermemory/supermemory) to add and search memories directly from Raycast. Use the "Add Memory" command to quickly save content, or "Search Memories" to find and retrieve your saved information with keyboard shortcuts. +Your AI remembers your preferences, projects, past discussions — and gets smarter over time. -## Support +**[→ Jump to MCP setup](#give-your-ai-memory-mcp)** -Have questions or feedback? We're here to help: +		 -- Email: [support@supermemory.ai](mailto:support@supermemory.ai) -- Discord: [Join our Discord server](https://supermemory.link/discord) -- Documentation: [docs.supermemory.ai](https://docs.supermemory.ai) +

🔧 I'm building AI products

-## Contributing +Add memory, RAG, user profiles, and connectors to your agents and apps with **a single API**. -We welcome contributions from developers of all skill levels! Whether you're fixing bugs, adding features, or improving documentation, your help makes supermemory better for everyone. +No vector DB config. No embedding pipelines. No chunking strategies. -For detailed guidelines, development setup, coding standards, and the complete contribution workflow, please see our [**Contributing Guide**](CONTRIBUTING.md). +**[→ Jump to developer quickstart](#build-with-supermemory-api)** -### Ways to Contribute +
-- 🐛 **Bug fixes** - Help us squash those pesky issues -- ✨ **New features** - Add functionality that users will love -- 🎨 **UI/UX improvements** - Make the interface more intuitive -- ⚡ **Performance optimizations** - Help us make supermemory faster +--- -Check out our [Issues](https://github.com/supermemoryai/supermemory/issues) page for `good first issue` and `help wanted` labels to get started! +## Give your AI memory (MCP) -## Updates & Roadmap +The Supermemory MCP server gives any compatible AI assistant persistent memory. One install, and your AI remembers you. -Stay up to date with the latest improvements: +### Quick install -- [Changelog](https://docs.supermemory.ai/changelog/overview) -- [X](https://x.com/supermemory). +```bash +npx -y install-mcp@latest https://mcp.supermemory.ai/mcp --client claude --oauth=yes +``` + +Replace `claude` with your client: `cursor`, `windsurf`, `vscode`, etc. + +### What your AI gets + +| Tool | What it does | +|---|---| +| `memory` | Save or forget information. Your AI calls this automatically when you share something worth remembering. | +| `recall` | Search memories by query. Returns relevant memories + your user profile summary. | +| `context` | Injects your full profile (preferences, recent activity) into the conversation at start. In Cursor and Claude Code, just type `/context`. | + +### How it works + +Once installed, Supermemory runs in the background: + +1. **You talk to your AI normally.** Share preferences, mention projects, discuss problems. +2. **Supermemory extracts and stores the important stuff.** Facts, preferences, project context — not noise. +3. **Next conversation, your AI already knows you.** It recalls what you're working on, how you like things, what you discussed before. + +Memory is scoped with **projects** (container tags) so you can separate work and personal context, or organize by client, repo, or anything else. + +### Supported clients + +**Claude Desktop** · **Cursor** · **Windsurf** · **VS Code** · **Claude Code** · **OpenCode** · **OpenClaw** + +The MCP server is open source — [view the source](https://supermemory.ai/docs/supermemory-mcp/mcp). + +### Manual configuration + +Add this to your MCP client config: + +```json +{ + "mcpServers": { + "supermemory": { + "url": "https://mcp.supermemory.ai/mcp" + } + } +} +``` + +Or use an API key instead of OAuth: + +```json +{ + "mcpServers": { + "supermemory": { + "url": "https://mcp.supermemory.ai/mcp", + "headers": { + "Authorization": "Bearer sm_your_api_key_here" + } + } + } +} +``` + +--- + +## Build with Supermemory (API) + +If 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. + +### Install + +```bash +npm install supermemory # or: pip install supermemory +``` + +### Quickstart + +```typescript +import Supermemory from "supermemory"; + +const client = new Supermemory(); + +// Store a conversation +await client.add({ + content: "User loves TypeScript and prefers functional patterns", + containerTag: "user_123", +}); + +// Get user profile + relevant memories in one call +const { profile, searchResults } = await client.profile({ + containerTag: "user_123", + q: "What programming style does the user prefer?", +}); + +// profile.static → ["Loves TypeScript", "Prefers functional patterns"] +// profile.dynamic → ["Working on API integration"] +// searchResults → Relevant memories ranked by similarity +``` + +```python +from supermemory import Supermemory + +client = Supermemory() + +client.add( + content="User loves TypeScript and prefers functional patterns", + container_tag="user_123" +) + +result = client.profile(container_tag="user_123", q="programming style") + +print(result.profile.static) # Long-term facts +print(result.profile.dynamic) # Recent context +``` + +Supermemory automatically extracts memories, builds user profiles, and returns relevant context. No embedding pipelines, no vector DB config, no chunking strategies. + +### Framework integrations + +Drop-in wrappers for every major AI framework: + +```typescript +// Vercel AI SDK +import { withSupermemory } from "@supermemory/tools/ai-sdk"; +const model = withSupermemory(openai("gpt-4o"), "user_123"); + +// Mastra +import { withSupermemory } from "@supermemory/tools/mastra"; +const agent = new Agent(withSupermemory(config, "user-123", { mode: "full" })); +``` + +**Vercel AI SDK** · **LangChain** · **LangGraph** · **OpenAI Agents SDK** · **Mastra** · **Agno** · **Claude Memory Tool** · **n8n** + +### Search modes + +```typescript +// Hybrid (default) — RAG + Memory in one query +const results = await client.search.memories({ + q: "how do I deploy?", + containerTag: "user_123", + searchMode: "hybrid", +}); +// Returns deployment docs (RAG) + user's deploy preferences (Memory) + +// Memories only +const results = await client.search.memories({ + q: "user preferences", + containerTag: "user_123", + searchMode: "memories", +}); +``` + +### User profiles + +Traditional memory relies on search — you need to know what to ask for. Supermemory automatically maintains a profile for every user: + +```typescript +const { profile } = await client.profile({ containerTag: "user_123" }); + +// profile.static → ["Senior engineer at Acme", "Prefers dark mode", "Uses Vim"] +// profile.dynamic → ["Working on auth migration", "Debugging rate limits"] +``` + +One call. ~50ms. Inject into your system prompt and your agent instantly knows who it's talking to. + +### Connectors + +Auto-sync external data into your knowledge base: + +**Google Drive** · **Gmail** · **Notion** · **OneDrive** · **GitHub** · **Web Crawler** + +Real-time webhooks. Documents automatically processed, chunked, and searchable. + +### API at a glance + +| Method | Purpose | +|---|---| +| `client.add()` | Store content — text, conversations, URLs, HTML | +| `client.profile()` | User profile + optional search in one call | +| `client.search.memories()` | Hybrid search across memories and documents | +| `client.search.documents()` | Document search with metadata filters | +| `client.documents.uploadFile()` | Upload PDFs, images, videos, code | +| `client.documents.list()` | List and filter documents | +| `client.settings.update()` | Configure memory extraction and chunking | + +Full API reference → [supermemory.ai/docs](https://supermemory.ai/docs) + +--- + +## Benchmarks + +Supermemory is state of the art across all major AI memory benchmarks: + +| Benchmark | What it measures | Result | +|---|---|---| +| **[LongMemEval](https://github.com/xiaowu0162/LongMemEval)** | Long-term memory across sessions with knowledge updates | **81.6% — #1** | +| **[LoCoMo](https://github.com/snap-research/locomo)** | Fact recall across extended conversations (single-hop, multi-hop, temporal, adversarial) | **#1** | +| **[ConvoMem](https://github.com/Salesforce/ConvoMem)** | Personalization and preference learning | **#1** | + +We also built **[MemoryBench](https://supermemory.ai/docs/memorybench/overview)** — an open-source framework for standardized, reproducible benchmarks of memory providers. Compare Supermemory, Mem0, Zep, and others head-to-head: + +```bash +bun run src/index.ts run -p supermemory -b longmemeval -j gpt-4o -r my-run +``` + +--- + +## How memory works under the hood + +``` +Your app / AI tool + ↓ + Supermemory + │ + ├── Memory Engine Extracts facts, tracks updates, resolves contradictions, + │ auto-forgets expired info + ├── User Profiles Static facts + dynamic context, always fresh + ├── Hybrid Search RAG + Memory in one query + ├── Connectors Real-time sync from Google Drive, Gmail, Notion, GitHub... + └── File Processing PDFs, images, videos, code → searchable chunks +``` + +**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. + +**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. + +--- + +## Links + +- 📖 [Documentation](https://supermemory.ai/docs) +- 🚀 [Quickstart](https://supermemory.ai/docs/quickstart) +- 🧪 [MemoryBench](https://supermemory.ai/docs/memorybench/overview) +- 🔌 [Integrations](https://supermemory.ai/docs/integrations) +- 💬 [Discord](https://discord.gg/supermemory) +- 𝕏 [Twitter](https://twitter.com/supermaborai) + +--- + +

+ Give your AI a memory. It's about time. +