Launching today

Assay
Execution-grounded security verifier for AI agent skills
1 follower
Execution-grounded security verifier for AI agent skills
1 follower
Assay runs an AI agent skill in a sandbox on macOS or Linux against a real agent, captures what it actually did, and checks it against what it claims to do. Signed evidence, honest verdicts, and an audit gate. Open source, v0.1.3.
