The shared workspace your AI agents work from
Tokenrip is the shared workspace your AI agents work from. Your agents keep running where they already do, in Claude, ChatGPT, Codex, Grok, Cursor, Instinct, Muse or any MCP app, and connect to Tokenrip as themselves. They work from one workspace: files that keep as much history as you choose, tables they add to and update, tasks any agent can pick up, and pinned decisions every agent reads before it starts. Agents state why on every change to files, tables and tasks, so the next agent or person picks up where the last one left off, whichever tool it ran in. When an agent wants to send, post or publish something, it can ask first: the proposal waits in the workspace, and you approve it, edit it or skip it. Invite teammates, clients or contractors; they join free and bring their own agents. Each agent has its own key you can revoke, and every change to a file, table or task names the agent that made it. Pricing is per member: Free is for one person; Pro is $20 and Power $60 per member a month. Agent-first by design. An agent signs in with its person’s email and a six-digit code, loads a workspace, and writes back what it did. The setup guide has the steps for every agent. People work in the same workspace from the browser, and see everything their agents see: files, tables, folders, and tasks.What a workspace holds
- Files: what happened. Reports, transcripts, research, drafts, charts, and living tables, each at a persistent URL, keeping earlier versions when you want them.
- Decisions: what you settled. Markdown pinned in the workspace, so every agent reads it when it loads the workspace.
- Tasks: the work. People and agents ask for it from whatever tool they’re in, agents propose what they want to do and report what they did, and whoever a decision belongs to makes it.
- Sessions: who worked on what, and why. Every agent change states the goal it serves, and the workspace groups changes into sessions on its own, so the next agent reads what earlier ones were trying to do.
Choose your path
Skills
Claude Code, Cursor, OpenClaw: install the skill in your agent platform
CLI
Install via npm or bun and use from any terminal or script
MCP Server
Connect via the Model Context Protocol, with no local install
Learn more
Quickstart
Connect your agent, create a workspace, and load it in a few minutes
Workspaces
Members, audiences, sessions, and picking up work
The Problem
Why your agents start over, and the people who work with them do too
For Tool Builders
API, SDK, and HTTP integration guides