# xysq documentation

- [Introduction](https://docs.xysq.ai/index.md): xysq is a context engineering platform. Capture your AI work, let the Memory Engine distill it into your context lake, and give every agent and teammate the same improving context.
- [Quickstart](https://docs.xysq.ai/getting-started/quickstart.md): Connect your first AI tool, push a session into your context lake, see it in your vault, then correct a fact and watch the fix land.
- [AI tools](https://docs.xysq.ai/connect/overview.md): Wire any MCP-capable AI tool to your xysq memory, or link WhatsApp and text it from your phone. One context lake behind all of them.
- [Claude Code](https://docs.xysq.ai/connect/claude-code.md): Install the xysq plugin, sign in via /mcp, done. About one minute, no API key to copy.
- [Claude](https://docs.xysq.ai/connect/claude.md): Add xysq as a custom integration in Claude web or desktop. About three minutes, OAuth handles authentication.
- [Cursor](https://docs.xysq.ai/connect/cursor.md): One-click install or paste the MCP config into mcp.json. About two minutes, authenticated with an API key.
- [ChatGPT](https://docs.xysq.ai/connect/chatgpt.md): Create an app in ChatGPT's settings and approve the OAuth flow. About two minutes.
- [Windsurf](https://docs.xysq.ai/connect/windsurf.md): Standard MCP: paste the config into mcp_config.json and restart. About two minutes, authenticated with an API key.
- [Antigravity](https://docs.xysq.ai/connect/antigravity.md): Direct SSE connection with header support. About two minutes, authenticated with an API key.
- [any MCP client](https://docs.xysq.ai/connect/generic.md): Wire any MCP client with HTTP or SSE transport to xysq. About two minutes, authenticated with an API key.
- [WhatsApp](https://docs.xysq.ai/connect/whatsapp.md): Link your phone number and text your memory. xysq answers from your vault, keeps what is worth keeping, and shows you which messages it kept.
- [MCP reference](https://docs.xysq.ai/builders/mcp-tools.md): The xysq Memory Engine's MCP surface is four tools: userinfo, push_context, pull_context, share_context. Exact parameters, returns, and one example each.
- [The Memory Engine](https://docs.xysq.ai/concepts/memory-engine.md): How the xysq Memory Engine works: verbatim logs under a distilled context graph, a fact ledger with recency and lineage, deterministic gates, and a write-ahead log on every change.
- [Context Lake](https://docs.xysq.ai/concepts/context-lake.md): One context lake per user or team, holding many context graphs: Personal, Teams, and Agents. An agent key reaches agent graphs only, never your personal memory.
- [Sharing and Governance](https://docs.xysq.ai/concepts/sharing-governance.md): Share one page or one source with one person by email. View-only, live, revocable anytime, with every change on a shared graph auditable.
- [Projects and Access](https://docs.xysq.ai/concepts/projects-and-access.md): Group your agent vaults into projects, add people with a role, and control who can read or write each vault. Access is per-request, so removing someone cuts them off on their next call.
- [Ownership](https://docs.xysq.ai/your-data/ownership.md): Your context lake is yours: isolated per vault, readable as plain markdown, deletable for real. BYO drive and private deployment are what we are building next.
- [Getting Started](https://docs.xysq.ai/sdk/getting-started.md): Install the xysq Python SDK and start adding persistent memory to your AI agents in minutes.
- [Vaults](https://docs.xysq.ai/sdk/vaults.md): Vaults are the context graphs your agents read and write. Create them, push what happened, pull the context back.
- [Thread-level memory](https://docs.xysq.ai/sdk/threads.md): Your conversation's turns, stored server-side as they happen: instantly readable back, automatically promoted into long-term memory.
- [Tags](https://docs.xysq.ai/sdk/tags.md): Curate labels, apply them to any source, then pull context scoped to exactly that set. Live end to end.
- [Metadata](https://docs.xysq.ai/sdk/metadata-filters.md): Declare a metadata key like email, and search one person's context without losing the notes that never mentioned them.
- [PII scrubbing](https://docs.xysq.ai/sdk/pii-scrub.md): Strip identifying details out of what you push, at ingest, before anything is written to the log.
- [LiteLLM & Anthropic](https://docs.xysq.ai/sdk/agent.md): Give your existing LLM loop memory: xysq as function-calling tools the model can pull and push.
- [2026](https://docs.xysq.ai/product-releases/2026.md): Product updates and release notes for xysq in 2026.
- [2026 06 18 reflect to recall skill synthesis](https://docs.xysq.ai/superpowers/plans/2026-06-18-reflect-to-recall-skill-synthesis.md)
- [2026 06 17 reflect to recall skill synthesis design](https://docs.xysq.ai/superpowers/specs/2026-06-17-reflect-to-recall-skill-synthesis-design.md)

## Optional

- [Open App](https://app.xysq.ai)