Open Memory Protocol – One Memory Store for Claude, ChatGPT, Curso

The Open Memory Protocol (OMP) launches as an open standard for portable, interoperable AI memory across tools like Claude, ChatGPT, and Cursor, enabling shared user context and eliminating memory silos. The vendor-neutral specification includes a self-hostable server, SDKs, and adapters, allowing any OMP-compatible AI tool to read and write to a single memory store.

An open standard for portable, interoperable AI memory across tools, sessions, and devices. Every AI tool remembers you differently — and only within its own walls. Claude knows what you told it yesterday. Cursor doesn't. ChatGPT learned your preferences. Your custom agent hasn't. Copilot saw your code style. Your terminal AI is starting from zero. Every time you switch tools, your AI forgets you. You repeat yourself. Context is lost. The AI that was finally starting to know you resets to a stranger. This is the AI memory silo problem . And it has the same solution as every silo problem before it: an open protocol. Open Memory Protocol is a vendor-neutral specification for how AI tools store, retrieve, and share memory about users and their context. It is: A specification — a precise definition of memory objects, storage format, and HTTP API A reference server — self-hostable, open-source, runs in Docker in one command A set of SDKs — TypeScript and Python libraries for building OMP-compatible tools A set of adapters — plug-ins for Claude MCP , OpenAI, Cursor, and more Any AI tool that implements OMP can instantly share memory with any other OMP-compatible tool. Requirements:Node.js 22 or newer npx omp-server Or with Docker: docker run -p 3456:3456 -v omp-data:/data ghcr.io/smjai/omp-server Your server is now running at http://localhost:3456 . Test it: curl http://localhost:3456/v1/health {"status":"ok","version":"0.1","compliance":"OMP-Core","memories count":0} Add to your Claude Desktop config ~/.claude/claude desktop config.json : { "mcpServers": { "omp": { "command": "npx", "args": "omp-mcp" , "env": { "OMP SERVER": "http://localhost:3456", "OMP API KEY": "your-omp-key" } } } } To enable AI-powered memory extraction and compression, also set these on the server: OMP AI PROVIDER=anthropic or "openai" OMP AI API KEY=sk-ant-... your Anthropic or OpenAI key curl -X POST http://localhost:3456/v1/memories \ -H "Content-Type: application/json" \ -d '{ "content": "User prefers TypeScript over JavaScript and dislikes verbose comments", "type": "semantic", "source": { "tool": "claude" }, "tags": "preferences", "coding" }' curl "http://localhost:3456/v1/memories/search?q=coding+preferences" ┌─────────────┐ ┌─────────────┐ ┌─────────────┐ │ Claude │ │ Cursor │ │ Your Agent │ │ MCP │ │ SDK │ │ REST API │ └──────┬──────┘ └──────┬──────┘ └──────┬──────┘ │ │ │ └───────────────────┼───────────────────┘ │ ┌────────▼────────┐ │ OMP Server │ │ self-hosted │ │ │ │ ┌───────────┐ │ │ │ SQLite │ │ │ │ / Pgvec │ │ │ └───────────┘ │ └─────────────────┘ Every tool reads and writes to a single OMP server you control. One memory store. All tools. Zero silos. OMP defines: Memory Object — the canonical schema for a memory content, type, source, tags, timestamps, optional embedding Memory Types — episodic events , semantic facts/preferences , procedural how-to knowledge REST API — standard CRUD + semantic search endpoints Authentication — bearer token, per-tool API keys Export/Import — portable JSON format for moving memories between servers Read the full specification: SPEC.md /SMJAI/open-memory-protocol/blob/main/SPEC.md { "id": "mem 01j9xk2p3q4r5s6t", "content": "User is building a fintech startup, prefers clean architecture, dislikes over-engineering", "type": "semantic", "source": { "tool": "claude", "session id": "sess abc123", "timestamp": "2026-06-29T12:00:00Z" }, "tags": "profile", "preferences", "engineering" , "created at": "2026-06-29T12:00:00Z", "updated at": "2026-06-29T12:00:00Z", "expires at": null } | Tool | Status | Install | |---|---|---| | Claude MCP | ✅ Available | npx omp-mcp | | OpenAI Assistants | 🙋 Help wanted | | Open issue https://github.com/SMJAI/open-memory-protocol/issues Open issue https://github.com/SMJAI/open-memory-protocol/issues Open issue https://github.com/SMJAI/open-memory-protocol/issues Want to build one? An adapter is typically 100–200 lines — read CONTRIBUTING.md /SMJAI/open-memory-protocol/blob/main/CONTRIBUTING.md and use as a template. /SMJAI/open-memory-protocol/blob/main/adapters/claude-mcp adapters/claude-mcp The OMP API is plain REST — any HTTP client works out of the box. Typed SDKs are on the roadmap. Want to build one? Python, Go, Rust, and Ruby SDKs are all needed. See CONTRIBUTING.md /SMJAI/open-memory-protocol/blob/main/CONTRIBUTING.md . Save a memory curl -X POST http://localhost:3456/v1/memories \ -H "Content-Type: application/json" \ -d '{"content":"User prefers TypeScript","type":"semantic","source":{"tool":"myapp","timestamp":"2026-06-30T00:00:00Z"}}' Search memories curl -X POST http://localhost:3456/v1/memories/search \ -H "Content-Type: application/json" \ -d '{"q":"TypeScript","limit":5}' Your memories are yours. They should not be locked inside a company's database, used to train models without your consent, or lost when you switch tools. OMP is designed on these principles: Self-hosted first — you run the server, you own the data Vendor neutral — no company controls the standard Privacy by design — memories never leave your server unless you export them Portable — import/export your full memory in one command - v0.1 — Core spec, reference server, MCP adapter - v0.2 — AI memory extraction, conversation compression, MCP resources + prompts - v0.3 — Semantic search with embeddings, pgvector support - v0.4 — Memory namespacing per-project memories - v0.5 — Multi-user support, access control - v1.0 — Stable spec, submitted to open standards body OMP is community-driven. We need: Adapter builders — connect your favourite AI tool SDK contributors — Go, Rust, Java SDKs welcome Spec reviewers — read SPEC.md /SMJAI/open-memory-protocol/blob/main/SPEC.md and open issues Early adopters — try it and report what breaks See CONTRIBUTING.md /SMJAI/open-memory-protocol/blob/main/CONTRIBUTING.md to get started. GitHub Discussions — questions, ideas, feedback Issues — bugs and spec clarifications Apache 2.0 — free to use, modify, and distribute. See LICENSE /SMJAI/open-memory-protocol/blob/main/LICENSE . Built by SMJAI https://github.com/SMJAI and contributors.