Clawvisor

Intelligent authorization for any AI agent

[Clawvisor @clawvisor]

Introducing Clawvisor, the authorization layer for AI agents.

Before today, giving access to your agents was all-or-nothing. Now, you can give your agents access that is scoped to your specific task. If your agent drifts or is compromised, it's blocked.

Try it today for free.

[Clawvisor @clawvisor]

Clawvisor's most requested feature is here! Your agent can now archive emails and write drafts in Gmail safely using Clawvisor. If you're already using Clawvisor, navigate to the accounts page and re-authorize your Gmail to activate. New users get it automatically.

[Clawvisor @clawvisor]

@OverlordsAi When you approve a task with scopes like send or delete, you approve it either for temporary or ongoing access, but only if it is aligned with the task description. If you permit it to delete XYZ and it tries to delete ABC instead, it will be blocked automatically.

[Clawvisor @clawvisor]

Introducing Clawvisor, the authorization layer for AI agents.

Before today, giving access to your agents was all-or-nothing. Now, you can give your agents access that is scoped to your specific task. If your agent drifts or is compromised, it's blocked.

Try it today for free.

[Clawvisor @clawvisor]

@aritifactual @ycombinator @ericlevine It uses OAuth, yes, but OAuth wasn't built for nondeterministic agents. In OAuth, "read email" means both "read recently received emails for triage" and "exfiltrate all emails". Clawvisor allows you to scope access to only the data your agent needs.

[Clawvisor @clawvisor]

@AndrewWarner @ycombinator @ericlevine @zapier Not quite! We're big fans of Zapier, but they allow you to define more deterministic workflows. Clawvisor governs always-on agents that reason and improvise. Very different problems.

[Clawvisor @clawvisor]

Go to https://t.co/QJyVF3jWGy to create a free account, or go to https://t.co/f89PPFD2sk to self-host.

[Clawvisor @clawvisor]

@harikp2002 @ycombinator @ericlevine It's multi-tiered. When you connect an account, you can put in hard restrictions on what actions it can take. Then, agents need to enumerate the actions they need to complete the task. Finally, an LLM judge makes sure the usage of those actions is coherent with the task itself.