I spent years interested in blockchains. What stayed with me wasn’t the tokens. It was the question of verifiability. Now AI agents are starting to act on our behalf. After an agent acts, can you prove what it knew, what it recorded, and that the record wasn’t rewritten afterward? That’s why I’m building Daryl. Append-only, hash-chained memory for AI agents. Independently verifiable. Open source under MIT. Not a blockchain. Not a claim of truth. Not production-ready theater. daryl.md

My Supernova ID ✦ Class of 2021 2,043 days onchain - here before the 600ms era begins on 10 September. Reveal yours: supernova.multiversx.com/

What Daryl verification does not prove. dsm verify recomputes the hash chain from the raw entries, then compares the tip to the expected integrity pin. Modify or reorder an entry, and the chain breaks. Delete the last entries cleanly, and the remaining chain still verifies — unless the recomputed tip no longer matches the pin. That is integrity against the state you expect. Not truth. An agent can append a wrong fact. The chain will still verify. It also does not, today, defeat someone who rewrites both the shard and the local pin in the same step. That needs an external witness. That is not shipped. What you get now: a trail you can replay, and a check that fails if the trail was quietly edited. DSM proves properties of the record, not reality itself. #AIAgents #DSM #OpenSource

Agent memory is usually mutable. A vector store updates. A logfile gets edited. A session is patched after the fact. When something goes wrong, you are left with a story about what the agent knew — not a record you can check. Append-only means an entry is written once. Not updated. Not deleted. The chain only grows. Hash-chained means each entry’s hash is SHA-256(content + prev_hash). The next entry commits to the last one. Change a byte in the middle, and the chain no longer verifies. That is not a metaphor. dsm verify recomputes the chain from the raw entries. One altered byte, and verification fails.