Keycard
Identity and access management for AI agents, replacing static secrets and API keys with short-lived, task-scoped tokens issued at runtime for teams running agents in production.
About Keycard
Keycard, based in San Francisco, gives each AI agent its own cryptographically verified identity, evaluated together with the user it acts for and the place it runs.
Every credential request is checked against policy at runtime, and approved requests receive short-lived, scoped tokens rather than stored API keys.
Teams can add it through SDKs for Python, TypeScript, Go and Ruby, a gateway that needs no code changes, or a sidecar proxy that swaps placeholder secrets for real tokens so the agent never holds a credential.
Policies are written in Cedar and managed with Terraform, and events export to SIEMs. It is built for developers and security teams putting agents into production.
Investors
Work at Keycard? Link to this listing
Optional badge for your site or README. It changes nothing about the listing, its order or its review. Other formats and a dark version: press kit.
<a href="https://securitystartups.com/companies/keycard"><img src="https://securitystartups.com/badge/listed.svg" alt="Listed on Security Startups" width="184" height="44"></a>