Credential isolation proxy for AI agents. Injects API keys at the network boundary so your agent never sees the raw credential. Supports domain allowlists, agent auth, policy enforcement, and audit logging.
Enables AI agents to securely access authenticated services (HTTP, SSH, SMTP) without exposing secrets, by acting as a server-side proxy that injects authentication.
OAuth token broker for AI agents to securely act on a user's behalf across third-party APIs (Gmail, Slack, GitHub, Notion, etc.) by vaulting tokens server-side and never exposing them to the LLM.
Bounded egress gateway & secret proxy for AI agents and applications, enabling safe credential injection into upstream requests while keeping raw secrets out of LLM prompt contexts.
Permission gateway that hands an AI agent a scoped MCP endpoint instead of an OAuth token: connect 27 services (Gmail, Google Calendar/Drive/Ads/Search Console, Slack, Notion, GitHub, Jira, Salesforce, HubSpot, Stripe, LinkedIn, X, Meta Ads and more), grant per-action permissions finer than native OAuth scopes, audit every call and revoke a key in one click. Self-hostable, MIT.
Local credential broker that enables AI agents to securely run CLI tools like SSH and MySQL without exposing passwords to the AI context, environment variables, or process listings.
