devendra116

something that you dont like about using AWS secrets Manager or think it should be handle differently?

im researching around building a execution environment that handle the secret + actual execution, any input is appreciated

devendra116

3 ay öncediscuss

so do we need something like `safe agent execution layer - that is policy enforced` (SEAL) we can manage what should be allowed and what not

agent uses llm to plan the action, but the actual execution happens in SEAL.

any example where it would make sense to start with?

open for thoughts

devendra116

3 ay öncediscuss

is there any tool that can do this ?

devendra116

3 ay öncediscuss

keyring is one of solution but even substituting values at excution does not gaurantee the security as agents can read the process itself.

im building a safe agent execution layer, A runtime where agents can act, but cannot access secrets. kinda sidecar that is callable by agent for using api keys, secrets, private keys, etc and plus one can add policy on how and what a agent can do.

does this seems good?

devendra116

6 ay öncediscuss

For those interested, the playground uses a guest wallet stored on browser localstorage so there’s no signup friction.

devendra116

Submissions

[untitled]

[untitled]

Show HN: Hum – ad-free terminal music player (Rust, no API keys)

Ask HN: Do you trust AI agents with API keys / private keys?

Show HN: Ledge - Policy layer for AI agent payments (prevents unauthorized txns)

Show HN: A playground to test stablecoin gas fees and concurrent txns on Tempo

comments