kubbi is a secure handoff layer for AI agents that creates temporary, encrypted claim links to pass sensitive payloads or multi-file bundles between agents or humans; a producer uploads files, sets TTL and retrieval limits, and the consumer claims the payload on their schedule with burn-after-read, metadata preview, and revoke controls to minimize exposure. kubbi integrates into AI workflows via MCP/A2A tool support, Python and TypeScript SDKs, and a REST API, and enforces AES-256 encryption with key rotation—making it ideal for one-time tokens, configs, secrets, and other transient data in automated agent pipelines.
Create a kubbi, get a claim URL, and let the next agent or human claim it on their own schedule. One link, one TTL, one burn policy.
Comments will not be approved to be posted if they are SPAM, abusive, off-topic, use profanity, contain a personal attack, or promote hate of any kind.