About

Agents do the work. People make the call.

AI labs ship better agents every few months. Xevol is where those agents do real work: with your knowledge and records, inside one Workspace, under rules you set.

Xevol Settings listing three connected AI agents, Claude Code, Codex and pi, each with a disconnect button.

Why Xevol

A good agent still needs a place to work.

An agent in a chat window forgets what it read, cannot see your pipeline and has nowhere to put finished work. Xevol gives it all three, and gives you one place to check what it did.

Principles

What we hold to.

  • Any agent

    Use the agents you already pay for. Xevol works with Claude Code, Codex, pi and other MCP clients, and no lab owns your Workspace.
  • People decide

    Agents read and draft. Approving, sending, publishing and deleting stay with people.
  • Sources stay attached

    Answers cite the passage they came from, so anyone can check the work.
  • One boundary

    Each agent reaches one Workspace and nothing else. You can disconnect it at any time.

Who it is for

First for people, then for their teams.

Xevol starts with individuals who already rely on AI agents: founders, consultants, freelancers and researchers. When they bring in colleagues, the same Workspace becomes the team's, with one place to review.

Connect your first agent today.

Free to try. No card required.