
Agentic Fabriq gives AI agents their own identities and enforces permissions on every tool call. It also keeps credentials in a vault and records each action in an audit trail.
Web appContact for pricing
Step 1: Register the app your agents run under with an app id, a display name and the scopes it may request.
Step 2: Have each user approve their own tools on the hosted consent page, using the provider's own consent screen.
Step 3: Mint a short-lived token scoped to one of your users.
Step 4: Call tools through the single gateway endpoint using the SDK or REST API.
Step 5: Review the audit trail and request logs to see which identity did what.
Yes. The Free plan is listed as free forever and includes 20,000 calls per month and unlimited agents.
Every request an agent makes through Fabriq, including authenticating, accessing a tool or retrieving credentials, counts as one call.
Yes, on a custom plan it can be installed into your own Kubernetes cluster on AWS or GCP. Other plans run on its managed cloud.
Developer plans are for products whose agents act for your customers. Enterprise is for governing agents across your employees, with teams, per-user permissions, SSO and an org-wide audit trail.
Workers IOWorkers IO publishes a testing skill for coding agents that helps them write tests which catch real regressions instead of only raising coverage. It runs in Codex and Claude Code.
Expel WorkbenchExpel is a managed detection and response provider with 24x7 human analysts supported by its Ruxie AI. Customers see every alert, investigation and action in Expel Workbench.
ZenityZenity is a security and governance platform for AI agents. It watches what agents can reach and what they are trying to do, then steers or stops risky actions as they happen.