About xeref.ai
An AI agent builder and productivity platform — from first prompt to production deployment.
The Vision
Most AI tools give you a generic assistant. xeref.ai lets you build your own — an agent that knows your workflow, connects to your tools, and remembers everything.
We believe the people who will get the most out of AI are not those who use the most tools, but those who design agents that are deeply specific to how they work. xeref.ai is built for those people: it gives you a structured way to design agents, a dashboard to run them, and an MCP backend so your agents and your workspace share the same brain.
Built by Bugra Karsli — developer, content creator, and AI automation enthusiast based in Turkey.
The Platform
XerefClaw — Build
Browse 48+ agent capabilities organized by the CLAWS methodology. Select the features you need, generate a structured system prompt, and save it as a named agent project. No code required.
Open XerefClaw →Dashboard — Manage
A full productivity environment: AI Chat powered by your agents, Tasks with AI prioritization, Calendar, Workflows (cron automations), Stats, and a Memory layer that grows with your work.
Go to Dashboard →Deploy — Ship
Connect your agents to Telegram, Discord, WhatsApp, or a web chat widget. Set up cron workflows that run your agent on a schedule and deliver output wherever you need it.
Learn more →The MCP Backbone
Every feature in the Dashboard — projects, tasks, notes, memory, daily targets — is also available as an MCP (Model Context Protocol) tool. This means your Claude or Antigravity agent can connect directly to your xeref workspace and work with your real data in real time.
What you manage in the UI is what your agent knows. There is no manual sync — the Dashboard and your agent share the same backend.
Read the MCP docs →Memory Architecture
Long-term memory is powered by Gemini Embedding 2 (3072-dimensional, 100+ languages) and Pinecone for vector storage. Every task, note, and document you create is automatically embedded and semantically searchable — by you and by your agents.
Personal memories are stored in isolated per-user namespaces. Your data is never mixed with other users' data.