I built an open source computer-use SDK enabling agents to authenticate
I built an open source computer-use SDK enabling agents to authenticate
over this weekend myself and two of my friends took part in a hackathon and built this side-project. we have been diving into computer-use recently and developed an sdk to make it easy to implement for devs like us. one feature we were missing though, was the agent being able to log into services. anthropic understandably blocks this capability with their guardrails, and you wouldn't want your credentials to end up in any model context anyways. so we added a keychain service to the vm that the agent is using. it was built using the pass cli ( https://www.passwordstore.org/ ). it's not perfect yet but already works solidly (feel free to contribute any improvements). take a look at the implementation here ( https://github.com/cuse-dev/cuse/blob/main/platforms/linux/a... ), all feedback is highly appreciated. if you want to get going asap, here is a quick nextjs quickstart repo ( https://github.com/cuse-dev/cuse-quickstart ), if you want to take a look at the whole sdk, see the documentation ( https://docs.cuse.dev ).
Share cardActual performance
Launch Intel predictions
Analyze your own launch →Correct prediction on native model
Similar products
SpongeCake – open-source SDK for OpenAI computer use agents
Open Computer Use
Open-source background computer use for Windows agents
Cerebellum – Open-Source Browser Control with Claude 3.5 Computer Use
Open-source framework to deploy personalized computer-use agents
Open-Cowork – an open-source, model-agnostic computer-use agent
Open-Source KMS SDK
CUA-S1 – A System One Model for Computer Use
Open-source AI agent with background computer-use
Docker for computer-use agents