OrgX turns every correction your team makes into a rule every agent follows, checks each result against your standard before it reaches you, and ends every run with a receipt you can approve in one read.
Free for one initiative, no card. One command connects the tools you already use.
This is OrgX
Goals, initiatives, decisions, playbooks and every agent, on example data. Decide something and watch the work move.
Northstar · Enterprise launch
3 things need you
Issue From 3 sessions
The same correction, typed three times this week by three people.
The problem
Every session starts from zero. The same correction gets typed again, by someone else, in another tool. And nothing proves the work, so someone checks all of it by hand.
Monday · Hope
Working on the adding date-fns.
npm install date-fns
npm warn: package-lock.json created next to pnpm-lock.yaml
YouWe use pnpm here. npm writes a second lockfile and breaks CI.
Tuesday · Priya
Working on the adding zod.
npm install date-fns
npm warn: package-lock.json created next to pnpm-lock.yaml
YouWe use pnpm here. npm writes a second lockfile and breaks CI.
Wednesday · Sam
Working on the adding turbo.
npm install date-fns
npm warn: package-lock.json created next to pnpm-lock.yaml
YouWe use pnpm here. npm writes a second lockfile and breaks CI.
Without OrgX. Explained three times. Checked by hand three times.
How it works
Connect once. OrgX reads the work, turns what it learns into rules and skills, checks every result, starts the next run in any tool from what is decided, and hands you a receipt.
01Connect
Claude Code, Codex, Cursor, ChatGPT, OpenClaw or any MCP client. One command connects every client on a machine. Nobody switches tools, and connecting does not start a run.
One command finds Claude Code, Codex and Cursor on this machine and connects each one.
npx -y @useorgx/wizard@latest setupDesktop terminal, Node.js 22+. Review the changes it proposes, then sign in.
Setup guide02Learn
A summary says what the agent meant to do. OrgX reads every chat and session for what actually happened: each command, failure and correction. It turns each into something specific, then adds them up across sessions into rules and skills, each linked to the moment it came from.
Each session’s summary said“Added date-fns. Build passes.”What OrgX read3 sessions · 15 steps · 3 corrections
Hope, Monday
Priya, Tuesday
Sam, Wednesday
Use pnpm in northstar/web; npm breaks the lockfile
3 corrections, 3 people: Hope, Priya, SamUses pnpm, not npm
Every later result is checked for itAdd a dependency in northstar/web
Point at, or tap, anything in columns 2 or 3 to see the lines it came from. On a phone, swipe across the columns.
03Check
Code, documents, designs, proposals and payment runs, each checked against your standard as soon as it is done. Start from the rules you confirmed. What misses is flagged with the reason before it reaches you, so you review what passed.
0 of 6 results checked
0 cleared0 flagged
Contributor setup guide Setup guide
Uses pnpm, not npm
Rule: Use pnpm in northstar/web; npm breaks the lockfileJudged on 5 layers, each above the bar
Correctness and risk · Verifiability · Scope discipline · Operability · ClarityCloser to work you approved than work you rejected
6 approved and 3 rejected examples04Carry
Before work starts in any connected tool, OrgX loads the rules, skills and decisions that apply, and sets the checks the result must pass. Then the agent works, and the run ends with a record of exactly what it did. Nobody pastes context.
Starting: adding turbo.
OrgX · loaded 3 things already decided
Criteria set before work started · 3
Receipt · 3 of 3 criteria met · ready to approve
Also inOpenClawOpenCodeAny MCP client
05Prove
Every run ends with a receipt: what was asked, the criteria set before it started, and the proof for each. Complete receipts are ready to approve in one read. A receipt missing proof lands with the person who owns it, with the reason. That record is how you review less, safely.
Below is the screen a receipt opens in. Try it: open a criterion, accept a risk or flag it, approve or send back.
What you get
Every result is checked against your standard before it reaches you. What misses comes back with the reason, so it is fixed before anyone reviews it.
A correction confirmed once is in every later session, in every tool your team uses. Nobody pastes context or re-briefs a new agent.
In 3,307 of our own agent sessions, 140 separate sessions hit the same failure, each starting from zero, and more than 1,100 calls went to failures an earlier session had already hit. Each one is a run paid for twice.
Source: Trail on OrgX’s own Claude Code and Codex history, September 2026For agencies and client work
Send one link instead of a status call. Your client sees what shipped, who accepted it and why, with every receipt attached.
Try one initiative for free. Run ongoing work with Starter. Share client delivery and its evidence with Agency.
Free
$0Forever · no card
Try your first initiative with all 7 agents.
StarterFor your own work
$98/month · billed monthly
Run ongoing work with approvals and evidence attached.
Agency
$298/month · billed monthly
Show clients the work, its evidence, and who accepted it.
Enterprise
CustomScoped with our team · seat-based or annual
Answer to governance teams with the record intact.
Want OrgX to set up your first client loop? Client Proof Loop, $2,500/month. First proof room within 7 days.See the managed offer
Still deciding? Bring one piece of agent work to a 30-minute review.
Book a proof reviewOrgX 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.
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.
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.
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.
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.
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.
