Currently in private beta

Create CLI agents.
Set the guardrails.

Build focused agents powered by your APIs and integrations. Control exactly what they can do. Safe for you, your team, and AI systems like Claude Code.

Join n+1 developers on the waitlist

terminal
$moi acme/github "List open PRs in frontend repo"

Found 3 open PRs in acme/frontend:

#142 Add dark mode toggle (ready for review)

#139 Fix auth redirect bug (2 approvals)

#134 Update dependencies (draft)

$# Claude Code tries to use the agent

> "Delete the frontend repo"

⚠ Agent acme/github cannot delete repositories.

Allowed: list_prs, list_issues, create_issue

$

How it works

Define once what an agent can do. Enforced every time it runs.

1

Create a focused agent

Build agents that do one thing well. A deployer, a notifier, a database querier.

2

Set permissions & scopes

Choose which APIs, which orgs, which repos. Define the boundaries - the agent can't exceed them.

3

Run from CLI or AI

Use it yourself, share with your team, or let Claude Code call it. Same guardrails apply.

Control without complexity

Your agents, your rules. Enforced for humans and AI alike.

Enforced guardrails

Define what an agent can do. Those limits apply whether you, your team, or Claude Code runs it.

Scoped access

Restrict agents to specific orgs, repos, channels, or resources. Granular control over what they can touch.

Centrally managed

Update permissions in one place. Changes apply immediately to all users and AI systems.

CLI-first

Run agents from your terminal with moi workspace/agent. Works anywhere.

Tools for AI systems

Let Claude Code, Cursor, and other AI systems call your agents as subagents. They get capabilities without direct API access. You keep control.

What will you build?

Focused agents with clear boundaries. Useful for you and safe for AI.

moi deployTrigger deploys to staging only. Production requires approval.
moi githubList PRs and create issues in your org. No repo deletion.
moi db-queryRead-only access to analytics tables. No PII exposure.
moi slackPost to #engineering. Can't DM or access private channels.
moi ticketCreate tickets in your project. Can't modify sprints or users.
moi logsFetch logs from staging. Production logs require auth.

Ready to set the guardrails?

Create CLI agents you can trust AI with. Join the waitlist.