OrgX — Proof for AI-Delivered Work

What is OrgX?

OrgX is not another chat assistant. It is the shared operating record for work performed across AI clients: what the organization is building, what was decided, which artifacts were produced, what was approved, and what needs human attention next.

Supported clients: ChatGPT, Claude, Cursor, Codex, VS Code, and any MCP-compatible tool. MCP endpoint: https://mcp.useorgx.com/mcp

Proof Strip

• Works in ChatGPT, Claude, Cursor, Codex, VS Code
• One shared record across MCP-compatible clients
• Install with the wizard or connect directly over MCP
• Receipts preserve decisions, approvals, and available evidence
• Approval gates for actions that require human judgment
• Configurable autonomy with an auditable execution history

What OrgX Does

OrgX organizes work around initiatives and connects them to decisions, artifacts, blockers, objectives, and receipts. Connected agents can orient from the same organizational state instead of reconstructing context from separate chat histories.

• Turn a goal into an initiative with accountable next actions
• Surface pending decisions for human approval while agents run in parallel
• Query live org memory and initiative health from any AI client
• Run autonomous execution sessions with hard budget guardrails
• Record outcomes and preserve the evidence available at completion

What Connects to OrgX

• ChatGPT (via MCP connector)
• Claude — claude.ai, Claude Desktop, Claude Code
• Cursor
• Codex
• VS Code (via MCP extension)
• Any MCP-compatible client
• OrgX web Mission Control (https://www.useorgx.com/command)

Trust and Control

OrgX is built around the assumption that autonomy should be explicit, scoped, and reviewable. Teams can keep sensitive actions behind human approval, constrain tools by scope, and inspect execution history after work completes.

• Clerk authentication with OAuth 2.1 for MCP
• Row-level data isolation per workspace
• Explicit scopes per agent and per tool category
• Human-in-the-loop decision workflows
• Artifact verifier proofs and citation trails
• Configurable agent autonomy limits

How to Start

1. Add the MCP config to your client: {"mcpServers":{"orgx":{"url":"https://mcp.useorgx.com/mcp"}}}
2. Or run: npx @useorgx/wizard@latest setup
3. First prompt: Plan my next launch across product, design, and marketing — and hold anything irreversible for my approval.
4. Call orgx_bootstrap to discover your workspace and capabilities
5. Call get_org_snapshot to orient before acting
6. Call scaffold_initiative to create your first initiative

Why Not Just Use Claude or ChatGPT Alone?

Individual AI clients are powerful but isolated. Claude doesn't know what your Cursor agent decided yesterday. ChatGPT doesn't have access to the decision your team approved last week. OrgX is the operating record your agents and tools share — the persistent org memory and governance system that makes all your AI clients work as a coordinated system instead of independent tools.

Agent Fleet

• Mark (Marketing) — Campaign drafts, launch messaging, brand-safe content
• Eli (Engineering) — Code reviews, PR management, deployment coordination
• Dana (Design) — Design tokens, accessibility audits, motion specs
• Pace (Product) — Initiative strategy, milestone tracking, cross-team coordination
• Sage (Sales) — Pipeline insights, follow-up drafts, deal hygiene
• Orion (Operations) — Budget monitoring, escalations, schedule coordination
• Xandy (Orchestrator) — Cross-domain routing, conflict resolution, quality gates

Pricing

• Free — $0/month — One real initiative, all 7 agents, no card
• Starter — $98/month — Unlimited initiatives, approval-gated autonomous execution
• Team — $298/month — Up to 5 seats, shared agent memory, SLA
• Enterprise — Custom — Dedicated capacity, SSO/SCIM, custom guardrails