Compact decision runtime

Intelligence small enough to run anywhere.

aiMe, pronounced "Amy"

aiMe is a compact, personalised, decision runtime that can act under uncertainty, work offline, and produce a replayable ledger of every decision it makes.

It is not an LLM, wrapper or agent framework. aiMe turns vague intent into governed action using a tiny runtime that can run in a browser, on mobile, in private cloud or inside constrained devices.

Request private beta access See how aiMe works

Scale

One is enough. Millions are possible.

A single aiMe instance can sit beside a user, device, workflow or application and make local governed decisions in real time. That is already useful.

Because aiMe is small, it is not limited to one central assistant. You can deploy many of them: one per user, one per device, one per workflow, one per customer, one per agent, one per decision boundary.

Each aiMe can operate independently, maintain its own context, follow its own policy and produce its own ledger. When needed, aiMes can coordinate as swarms: large numbers of tiny governed intelligence units working together without becoming one opaque black box.

The difference

Not a bigger model. A smaller runtime.

Most AI systems depend on large remote models, prompt chains and opaque agent behaviour. aiMe takes a different path. It is a compact runtime for resolving intent, applying policy, making decisions and recording proof.

LLMs generate probable text.
aiMe produces governed decisions.

Agents act.
aiMe proves why.

Cloud models need inference.
aiMe can run locally.

One aiMe can help a user.
A swarm of aiMes can coordinate across a system.

Capabilities

What makes aiMe different

Tiny runtime

Small enough to run close to the work: browser, mobile, private cloud, edge and constrained environments.

Offline-capable

aiMe does not need an internet connection in the hot path. It can keep deciding when cloud AI cannot.

Decision ledger

Every meaningful action can be recorded as a replayable decision event: context, policy, confidence, outcome and proof.

Works with existing AI

aiMe can sit in front of LLMs, agents and OpenAI-compatible tools as a trust, routing and governance layer.

Works without existing AI

aiMe is not just a wrapper. It can operate independently using its own runtime decisioning.

Swarm-native

Deploy one aiMe or millions. Each instance remains small, governed and inspectable.

What aiMe is not

  • Not a chatbot
  • Not a prompt wrapper
  • Not a fine-tuned LLM
  • Not a no-code template generator
  • Not a rules engine
  • Not a cloud-only agent framework

What aiMe is

  • A compact decision runtime
  • A local-first intelligence layer
  • A policy-aware action engine
  • An auditable proof system
  • A swarmable unit of governed intelligence
  • A bridge between vague intent and controlled execution

Execution

From vague intent to working software

aiMe can resolve vague English intent into structured, executable outcomes extremely quickly. In internal tests, it has produced complete runnable application structures in milliseconds while preserving the decision trail behind the result.

A row is accepted only if the verifier can re-derive it from the environment plus the frames. Nothing is taken from the producer's self-report.

In one internal benchmark, aiMe assembled a complete runnable production application from vague English intent in 8ms, without a model call in the hot path.

Deployment

Deploy close to the decision

aiMe is designed to run where decisions actually happen: inside products, tools, workflows, private environments and edge contexts.

Browser

Run governed decisions inside web surfaces without routing every action through a remote model.

Mobile

Keep decisioning on the device when latency, privacy or connectivity make cloud AI a poor fit.

IoT and edge

Operate inside constrained hardware where a full LLM stack cannot live in the hot path.

Private cloud

Deploy inside customer environments without turning every workflow into external inference traffic.

Enterprise systems

Sit beside existing products, APIs and operational workflows with policy and proof attached.

Agent and MCP workflows

Work with LLMs, agents, MCP tools and OpenAI-compatible clients as a governed runtime layer.

Proof

Built for proof, not vibes

Most AI systems leave behind a transcript. aiMe leaves behind a ledger.

Verification

Proof bundle results

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.

Proof bundle verified · 2026-06-08
Convergence atlas 200000 / 200000

every start, every world → one target

Tamper suite 3 / 3 rejected

provenance, overlap, and physics forgeries fail

Fraud proof 0 silent misses

878 / 878 fraud caught; novel patterns escalated

Verifier 6 / 6 PASS

offline · no LLM · no network

ProofRe-derived claimVerdict
Frame log aime-proof-verify frames
2000 frames · 0 violations · 1000/1000 grounded arrivals
PASS
Atlas aime-proof-verify atlas
200 worlds × 1000 starts → one endpoint [[0,0,0,0]]
PASS
Tamper aime-proof-verify tamper
All forged logs rejected (provenance · overlap · physics)
PASS
Fraud aime-proof-verify fraud
0 silent fraud misses · 123/123 novel frauds escalated
PASS
SVG dot aime-proof-verify svg-dot
5 / 5 cases · dot detected · hard negatives ignored
PASS
SVG traces aime-proof-verify svg-traces
10 / 10 variations detected · faint scores below bold
PASS

Deterministic, offline native verification (~690 KB). Same inputs ⇒ identical outputs on any machine. Download the pack to reproduce every verdict locally.

Compression

Carbon — byte-exact code compression

Carbon is aiMe's content compressor for source code, shipped in the aim CLI (aim carbon). It reconstructs files byte-for-byte while producing a smaller output than zstd-19 — a large fraction of each file is regenerated rather than transmitted, so only the genuinely novel content is shipped. Byte-exactness is asserted on every file inside the run.

Carbon verified byte-exact · 2026-06-10
Byte-exact vs zstd-19 1.480 vs 2.053 b/B

~28% smaller on held-out source, losslessly

Byte-exact verified 44 / 44 files

held-out files reconstruct identically (in-run)

Under 1.5 bits/byte 1.480 b/B

on real, held-out Rust source

Reconstructed, not sent majority

only the novel content is transmitted

ResultMeasured on held-out sourcevs zstd-19
Byte-exact codec aim carbon pack/unpack
reconstructs the original source files losslessly · 1.480 b/B vs zstd-19 2.053 · 44/44 held-out verified
1.39×
Size win (held-out) aim carbon bench
~28% smaller than zstd-19 on held-out source, under 1.5 bits/byte
-28%
Lossless round-trip aim carbon unpack
every held-out file decompresses byte-for-byte identical to the original
44/44
Safe fallback aim carbon pack
inputs it cannot model fall back to a standard baseline · never larger · always byte-exact
PASS

Reproduce on your own files with the shipped tool: aim carbon pack <input> -o out.carbon, then aim carbon unpack out.carbon -o restored (identical to the input). aim carbon bench <dir> --ext .rs prints carbon vs zstd-19 bits/byte and re-asserts byte-exactness. The method is proprietary.

Source control

aim — byte-exact version control with a semantic wire

aim is aiMe's source-control core — the git alternative. It reconstructs every file byte-for-byte (git parity) and is already smaller than git's pack at rest. And because aim tracks meaning rather than bytes, an org-wide reformat costs essentially nothing — far fewer bytes cross to a remote over a repo's life. The wire is content-addressed and transport-agnostic (not bound to HTTP).

aim verified byte-exact · 2026-06-10
Byte-exact round-trip git parity

aim verify = byte_exact; every file reconstructs identically

Byte-exact size at rest ~5× smaller

EXACT mode 29,703 B vs git pack 156,897 B, losslessly

Org-wide reformat sweep ≈ free

meaning-preserving: git re-ships 1.21 MB; aim ~1.7 KB

Cumulative wire to a remote 18× less

meaning-preserving representation, over 40 commits

ResultMeasured to a remote (pack-vs-pack)vs git
Byte-exact fidelity aim verify
commit -> checkout reconstructs every file identically; whole-tree semantic root_hash
PASS
Byte-exact size at rest aime-aim-bench
EXACT mode is byte-lossless AND smaller than git's pack: 29,703 B vs 156,897 B
~5×
Reformat-sweep cost (meaning-preserving) aime-aim-bench --history 40
10 org-wide reformats: git re-ships 1,213,974 B; aim ships 1,716 B (canonical frame unchanged)
≈ free
Cumulative wire, lifetime (meaning-preserving) aime-aim-bench --history 40
bytes that cross to a remote: git 1,280,277 B vs aim 71,247 B — pack-vs-pack, git's own packer
18×

Reproduce it yourself: aim init && aim commit -m snapshot && aim verify prints byte_exact = true on any tree. cargo run -p aime-aim-bench --release -- --history 40 --reformat-every 4 measures lifetime wire/storage to a remote (pack-vs-pack, git's own packer). Byte-exact (EXACT) mode is git parity and ~5x smaller than git's pack at rest; the 18x figure is the meaning-preserving representation (formatting normalised).

Early access

Private beta

aiMe is currently in private beta. We are working with selected technical users, partners and organisations that need governed intelligence close to the work.