aiMe is a compact, personalised decision runtime that acts under uncertainty, works offline, and produces a replayable ledger of every decision it makes. Not an LLM. Not a wrapper. One can decide; millions can coordinate.
Most AI systems depend on large remote models, prompt chains and opaque agent behaviour. aiMe takes a different path: a compact runtime for resolving intent, applying policy, making decisions and recording proof.
aiMe resolves vague English intent into structured, executable outcomes extremely quickly, while preserving the decision trail behind the result. In internal tests it has produced complete runnable application structures in milliseconds, with no model call in the hot path. A row is accepted only if a verifier can re-derive it from the environment plus the frames.
See the proofMost AI systems leave behind a transcript. aiMe leaves behind a ledger. The proof bundle ships a verify-only reproducibility pack: Rust verifier source, artifacts, checksums and exact expected verdicts. A skeptic re-derives every claim from the data, nothing is taken from the producer's self-report. Same inputs produce identical outputs on any machine.
Open the proof packaiMe is currently in private beta. We are working with selected technical users, partners and organisations that need governed intelligence close to where decisions actually happen. If that sounds like you, we'd like to hear about it.