One setup path
The agent handles setup and pauses when browser authentication needs you.
Claude Code and Cursor use the OrgX setup wizard.Enter through the tools you already use.
Without it, the tool switch becomes another manual step and the record arrives late.
OrgX connects through client setup, hosted OAuth MCP, REST, and webhooks. Each recorded session retains its client and workspace boundary.
Connect a client, then send the first outcome.
Choose a supported client to see the current setup path and the first bounded prompt.
Set up OrgX in Claude Code
01
npx @useorgx/wizard@latest setup02The agent pauses when browser authentication needs you.
03Call orgx_bootstrap, report the active workspace, and stop.
The first session starts bounded.
Workspace authority is explicit
The client reports the active workspace before changing work.
The first bootstrap stops before any creation or mutation.The first prompt starts with an outcome
The record begins with intent, not an unscoped agent session.
Irreversible actions stay behind operator approval.The next session receives objects, not a summary.
- Client
- The tool where the work happened.
- Session
- The bounded record written by that tool.
- Authority
- The workspace and scope granted to it.
Questions
Before you start
Still deciding? Bring one piece of agent work to a 30-minute review.
Book a proof reviewWhat does OrgX do?
OrgX is proof for AI-delivered work. Claude Code, Codex, Cursor, and OpenClaw write to one shared record, so a decision keeps its provenance (the sessions, the clients, the evidence) no matter which agent picks the work up next. Capture depth still differs by client today.
Can we control what agents are allowed to do?
Yes. Each initiative runs in manual, gated, or autopilot mode, and each connector is set to allow, ask, or deny. Sending, spending, deploying, merging, and deleting always stop for a person in every mode. Checking finished work against a published quality bar is in beta.
Do we have to switch AI tools?
No. OrgX connects through MCP and plugins to Claude Code, Codex, Cursor, ChatGPT, and OpenClaw. Setup differs by client; the record is shared across all of them.
What counts as “accepted” work?
An agent reporting done is a claim, not an approval. An agent can never approve its own work: that floor is enforced in code and fails closed. Work counts as accepted when an owner records the ruling.
Can someone outside OrgX verify the work?
Agent Work Receipt v0.1 is an open, account-free format. A receipt carries its evidence and integrity hash, and it can be checked with the public validator without an OrgX login.
What does it cost to start?
The Free plan covers one active initiative. Paid plans start at $98 a month. If you want us to run it with you first, two scoped episodes on one of your real deliverables cost $250.