Agent Permission Gateway

A single hub for all your personal AI agents' third-party connections, with visible, auditable permissions

Problem

Every personal agent (Muse, Instinct, Grokbot, Poke, etc.) makes you reconnect email, calendar, and tools again. Permissions are opaque, every provider rebuilds the same integrations, and users have no idea what an agent actually read or sent.

Solution

A local-first connection hub that stores all third-party OAuth credentials, lets agents access calendar/email/files through one proxy, logs every access with who/when/what, and supports fine-grained rules per service, per action, and per time window, plus an approval prompt for sensitive operations.

Users

Heavy users of multiple personal AI agents, privacy-conscious developers, and small teams that want internal agent oversight.

MVP

Support Gmail and Google Calendar connectors; central OAuth storage and refresh; per-action permission config (read/write/delete); per-agent activity log and revoke button; local SQLite with credentials never leaving the device.

Revenue

Open-source core with paid hosted tier (cross-device sync, team audit dashboard); enterprise per-seat pricing; connector marketplace rev-share.

Why now

Personal agents are multiplying while staying siloed, and people are just starting to realize how risky 'an agent can read my email' is. An indie dev can start with the two most painful connectors instead of racing a platform to build a hundred.