Documentation Index
Fetch the complete documentation index at: https://docs.xysq.ai/llms.txt
Use this file to discover all available pages before exploring further.
Follow along at app.xysq.ai or check back here as xysq ships new features.
Now live — 24 May 2026
Integrations
Connect the apps you already use and let xysq watch them for you. Gmail is live today — your inbox and sent folder flow into your memory through a rule pipeline you control. The defaults skip the loud stuff (Promotions, Social, Spam, mailing lists,
no-reply@ senders) and keep the rest: personal replies, flight confirmations, receipts, anything that survives the gauntlet. Filtering happens before storage, so noise never reaches your vault.Google Calendar, Outlook, Slack, Notion, GitHub, Linear, Jira, Confluence, and Granola are queued up next.Open Integrations → · Learn how Integrations work · Gmail setup guideYour rules. Your filter. Your audit trail.Every event xysq receives — kept, skipped, or quota-dropped — lands in activity logs with a human-readable “why”. You can see exactly which rule fired, override any skipped message with one click, and edit your filter rules in a live YAML editor with inline validation. Nothing happens silently.
What’s in it
Two-stage filter pipeline
Deterministic YAML rules decide most events instantly. A lightweight LLM tie-breaks the ambiguous cases — confirming a real flight booking, recognising an actual receipt — only when a rule explicitly asks for it.
Live rule editor
Edit rules in Monaco with autocomplete, inline schema validation, and a side panel showing your effective rule set. Save is disabled until validation passes — you can’t ship a broken config.
Activity logs with provenance
Every event in one timeline. Filter by app, decision, date, or full-text search the subject and sender. Each row tells you which rule won and what the LLM said, in plain English.
Keep anyway override
Spot a real email the filter mis-classified as skip? One click pulls it into memory after the fact. The audit row updates in place so the timeline stays honest.
Disconnect-safe by design
Disconnecting stops new events. Everything else — memories, rules, logs — stays. Reconnect later and pick up where you left off. No double-ingestion, no fresh start.
Now live — 7 May 2026
Chat & Organise
Two new surfaces shipped together. Chat lets you talk to xysq directly inside the dashboard — it remembers what you tell it across conversations, switches models based on what you ask, and searches the web when you need something recent. Organise is your file workspace: drop in PDFs, notes, images, or data exports and xysq reads them, indexes the contents, and makes them available to Chat and to every connected agent.Chat and Organise work together. Right-click any file in Organise and choose Use in Chat to pin it to a conversation. Or drag a file into Chat directly — it lands in Organise automatically.Open Chat → · Learn about Chat · Learn about Organise
You don’t need Chat to use xysq. Your own AI tool — Claude, Cursor, anything that speaks MCP — talks to the same memory. Chat is there for when you want to use xysq directly. Files you put in Organise are available in both places.
What’s in it
Talk to xysq directly
Conversations live in the sidebar and persist across sessions. Auto, Fast, Smart, Vision, and Reasoning modes pick the right depth for each turn. 20 messages a day on the free plan.
A workspace for your files
Folders, drag-drop upload, breadcrumb navigation. PDFs, text, JSON, CSV, and images up to 10 MB. Files are extracted, indexed, and ready to use in seconds.
Use in Chat
Pin any file or folder to a conversation — its contents stay in scope for every turn. Or
@-mention a file inline for a single turn. Folders pinned live: new files added later are automatically in scope.Personal and team Organise
Each team gets its own Organise space alongside its vault. Files belong to the team, follow team roles for read/write access, and feed the team’s shared memory.
Now live — 20 April 2026
Graph View
Your vault, rendered as a 3D galaxy of connected memories. Every memory is a star; every link between them a filament. Clusters pull together into hemispheres, entities surface as their own nodes, and clicking any star opens the memory alongside every connection it has.Open Graph View →
See how your context connects.Graph View turns the vault from a list into a map. You can see at a glance which topics are dense, which entities sit at the centre of your work, and which memories bridge between clusters. It’s a read-only lens over the same vault your agents already use — no new data to maintain, just a new way to navigate what’s already there.
What’s in it
Personal, team, and knowledge scopes
Stepper on top to pick Personal or a Team; scope selector on the left to narrow to memories, confidential, or knowledge within that mode.
Dynamic clusters
Hemispheres are built live from your vault’s own themes — no hard-coded categories. Clusters rank by size, so the biggest topics in your memory always sit at the top.
Focus + detail drawer
Click a memory to frame it with its neighbours. The drawer shows the full text, context, entities, tags, and every connected memory — click through without losing your place.
3D navigation with LOD
Orbit, zoom, and fly through the galaxy. Level-of-detail, gravity wells, and bloom intensity are all tunable from the render panel.
Now live — 15 April 2026
Python SDK
The xysq Python SDK is live. Add persistent memory to your own agents and applications — directly, without an MCP server.
pip install xysqThe SDK gives you three core operations: capture to store a memory, surface to retrieve relevant context, and synthesize to ask a natural language question answered from your vault. Everything works on your personal vault and on shared team vaults.Get started with the SDK →Built for developers building agents.The SDK is the direct API path — lower overhead than MCP, full control over when and what to capture, and the same memory bank your MCP-connected agents already use. Personal vault, team vaults, knowledge base — all accessible from code.
What’s in the SDK
Memory operations
Capture, surface, synthesize, list, delete, and status/wait for deterministic indexing. Async and sync clients included.
Knowledge Base
Index links, code snippets, and text quotes. Sources become part of the same vault — they surface automatically through memory queries.
Team Vaults
Scope any operation to a shared team vault with
client.team(team_id). Same interface, shared context.XysqAgent & Tool Calling
XysqAgent wraps any LiteLLM-compatible model with automatic memory retrieval and capture. Configurable context strategies, including custom ones. LiteLLM and Anthropic tool-calling integrations also included.Now live — 13 April 2026
Teams
Teams are live. Create a shared vault for your team — every member with access can retain and recall from the same memory bank, across every connected agent. Decisions, agreements, and shared context survive session boundaries and accumulate over time.The knowledge base now works at team scale. Drop in meeting notes, share architectural decisions, retain anything your whole team needs to know — and every agent your team uses will start informed.Learn how to set up and use teams →
Personal and team vaults are fully independent.Your personal memories stay yours. Team memories belong to the vault — they’re accessible to every member with read access, regardless of which agent they’re using. One member retains a decision in Claude. Another recalls it in Cursor. Same vault, same context.
Why this matters
Decisions don't get lost
Retain architectural decisions, agreements, and outcomes to the team vault the moment they’re made. Every future session — by any team member, in any agent — starts with that context already loaded.
No more re-explaining to new agents
Every time you spin up a new agent or start a fresh session, the team vault is there. The onboarding process, the API conventions, the deployment rules — already in memory, already recalled.
Role-based access
Four roles: read-only, read/write, admin, and owner. You control who can add to the vault, who can delete from it, and who can manage membership. The vault is shared — access is granular.
Works with every connected agent
Claude, Cursor, ChatGPT, any MCP client — team vault access works the same way across all of them. The same
memory_recall and memory_retain tools, scoped to the team.Now live — 9 April 2026
Skills
Skills are system instruction files that teach your AI agent how to work with xysq — what to capture, when to recall, how to use tags, and how to start every session already informed. Install once, benefit every session.Skills come in two tiers. The baseline skill is available immediately — a hand-crafted protocol covering session start, aggressive capture, surgical recall, and consent rules. The personalised skill unlocks once you have more than 5 memories: xysq reflects on your memory bank and injects a section personalised to your working style, active context, tool preferences, and agent behaviour notes.Download from the Dashboard → Get Started panel. Works with Claude Code, Claude Desktop, Cursor, Windsurf, ChatGPT, and any generic agent.Learn how to install and use skills →
Your skill evolves with your memory.Every time your memories change meaningfully, xysq generates a new skill version. The dashboard silently refreshes your skill daily. Connected agents can call
skill_sync() to fetch and install the latest version directly — no dashboard visit required.The north star: less tokens = same or better output. Every memory captured today is tokens saved tomorrow.Now live — 8 April 2026
Knowledge Base
The Knowledge Base is live. Drop in a link, paste a quote, share a chat transcript — xysq reads it, synthesises it, and integrates it into a persistent, structured knowledge base that gets richer with every source you add.Memories and knowledge are now linked: your conversations accumulate as memories, your memories accumulate as knowledge. The knowledge base is the source of truth everything else is built from.Learn how to use it →
Your memories find their place here too.Every conversation you have, every problem you solve, every interaction with an agent — all of it accumulates into your knowledge base. Not scattered across sessions. Structured, cross-referenced, and always current.Memories are episodic — what happened, when, in what context. Knowledge is structural — what it means, how it connects, what’s true. xysq links both layers. Your interactions become memories. Your memories become knowledge. The knowledge base is the source of truth everything else is built from.
Why this matters
Never re-explain your health
Upload your reports, summaries, prescriptions. Your agent knows your baseline, history, and patterns — permanently. Every new system you interact with starts informed, not from zero.
Your team's knowledge, always current
Feed in meeting notes, Slack exports, product docs. The wiki stays maintained because xysq handles the upkeep no one on your team does. Every agent that touches your business knows what it should.
Insights that don't disappear
Drop in a chat, an article, your own notes — or just keep having conversations. The problem-solving and breakthroughs get filed back permanently. Your knowledge base compounds with every interaction, not lost to chat history.
Your memory, structured
Your interactions become memories. Your memories become knowledge. The wiki is the source of truth — not a RAG bucket that re-derives answers on every query. What you know compounds over time. You never start over.
Coming up next
Knowledge Base CLI
Build your knowledge base from the command line. Point the CLI at a local folder, codebase, or set of files — xysq indexes everything in one pass.