Skip to main content

Learn

CortexHub puts AI to work safely: organization-owned agents, a personal co-worker for every member, a governed gateway for outside AI tools, and one layer of governance over every action. These pages explain the product model in plain language for members, admins, and developers.

One gateway, many integrations

Your assistant talks to CortexHub once. CortexHub connects to the tools your workspace allows.

Your AI app

Claude, Cursor, Windsurf, VS Code, or your Python agent runtime connects over MCP.

MCP + OAuth

CortexHub gateway

One endpoint. Search, policy checks, approvals, and audit on every call.

Governed invoke

External tools

Slack, Notion, GitHub, Jira, HubSpot, Stripe, and other integrations your workspace enabled.

Start here​

TopicForSummary
What is CortexHub?EveryoneThe problem we solve and the core surfaces
How it worksEveryoneConnect, discover, invoke under governance, audit
OrganizationsAdmins, partnersAccount model and roles
AgentsEveryoneOrg Agents, co-workers, and external gateway identities
Toolkits and connectionsEveryoneCatalogue, entitlement, connect once
Groups and accessAdminsLayered rules that only get stricter
The BrainMembersThe living map your co-worker builds, and how to correct it
MeetingsMembersYour co-worker as an active meeting participant
Sessions and activityEveryoneWhat appears in Cloud
UsageEveryoneOne view for activity, spend, and savings
AuthenticationDevelopersOAuth on the gateway and Platform API
GlossaryEveryoneCanonical terms

Choose your path​