# Memrio

> One shared intelligence for every AI at your company. Memrio is the central intelligence hub your AIs plug into over MCP. ChatGPT, Claude, Cursor, and your own agents read from one source of truth — and write back what they learn.

Memrio exposes one remote MCP server per workspace at `https://memrio.ai/api/mcp/{workspace-slug}`. Agents authenticate with a Bearer API key that is scoped to one agent page set. Read tools: browse, search_pages, get_page. Write tools (opt-in per agent): get_page_source, create_page, update_page, append_to_page. Writes are versioned and reviewed by humans before publishing unless the agent may publish.

## Documentation

- [What Memrio is](https://memrio.ai/docs/introduction.md): Memrio is a human-governed knowledge base that AI agents read over MCP. Learn the model: workspaces, pages, page sets, agents, keys, and review.
- [Quickstart: publish a page and connect an agent](https://memrio.ai/docs/quickstart.md): Go from an empty Memrio workspace to an agent answering from an approved page in about ten minutes.
- [Connecting over MCP](https://memrio.ai/docs/connect-mcp.md): How Memrio exposes a remote MCP server: endpoint, authentication, protocol version, and the JSON-RPC handshake.
- [MCP tools reference](https://memrio.ai/docs/tools.md): Every tool Memrio exposes over MCP: browse, search_pages, get_page, and the write tools get_page_source, create_page, update_page, append_to_page.
- [Registry markdown](https://memrio.ai/docs/registry-markdown.md): The markdown dialect agents and people use to write Memrio pages, including instruction, fact, callout, and fields blocks.
- [Governance: review, publish, and agent permissions](https://memrio.ai/docs/governance.md): How review and publishing work in Memrio, and what each agent permission — read drafts, can edit, can publish — actually allows.
- [Brief for an agent](https://memrio.ai/docs/agent-brief.md): A copy-paste system prompt that teaches any AI agent how to use Memrio well: browse first, open pages, answer only from them.
- [llms.txt and machine-readable docs](https://memrio.ai/docs/llms-txt.md): Where to find Memrio documentation in formats built for language models: /llms.txt, /llms-full.txt, and per-page markdown.

## Integration guides

- [Memrio for ChatGPT](https://memrio.ai/integrations/chatgpt): Custom connector via Developer mode. Give ChatGPT one approved place to look before it answers about your company.
- [Memrio for Claude](https://memrio.ai/integrations/claude): Custom connectors, Desktop, and the Messages API. Connect Claude.ai, Claude Desktop, or your own Claude-powered product to a page set your team approved.
- [Memrio for Claude Code](https://memrio.ai/integrations/claude-code): One command, project-scoped. Put your engineering runbooks, API conventions, and architecture decisions where Claude Code can read them before it writes a line.
- [Memrio for Cursor](https://memrio.ai/integrations/cursor): .cursor/mcp.json — project or global. Cursor’s agent is only as good as what it knows about your codebase’s rules.
- [Memrio for Windsurf](https://memrio.ai/integrations/windsurf): mcp_config.json with serverUrl. Cascade can plan across your whole repo — now let it plan with your company’s approved knowledge too.
- [Memrio for VS Code Copilot](https://memrio.ai/integrations/vscode-copilot): .vscode/mcp.json with prompted secrets. Copilot agent mode discovers MCP servers from .vscode/mcp.json.
- [Memrio for Gemini CLI](https://memrio.ai/integrations/gemini-cli): httpUrl in settings.json. Gemini CLI runs in your terminal and picks up MCP servers from settings.json.
- [Memrio for OpenAI Agents SDK](https://memrio.ai/integrations/openai-agents-sdk): MCPServerStreamableHttp or hosted MCP tool. Building agents on the OpenAI Agents SDK? Attach the registry as an MCP server and your agent inherits a governed page set with no retrieval pipeline to maintain.
- [Memrio for Vercel AI SDK](https://memrio.ai/integrations/vercel-ai-sdk): createMCPClient with HTTP transport. Turn the registry into tools for generateText and streamText in a few lines.

## Optional

- [Full documentation in one file](https://memrio.ai/llms-full.txt)
- [Landing page](https://memrio.ai/)
- [Blog](https://memrio.ai/blogs)
- [Terms](https://memrio.ai/terms)
- [Privacy](https://memrio.ai/privacy)