Sovereign Intelligence, built on AienOS. My work toward persistent intelligence that belongs to the person running it, from the language to the machine.
Sovereign Intelligence (SI) is the product and stack index. Alpha is experimental, not a promise that every machine or feature is qualified. Read the release's exact scope before running it.
Installer, source and release evidenceSI source and stack mapAienOS keeps its own identity. aienux is the kernel, not a new name for the whole system.
Hardware, evidence and the closed loopAienOSaienux kernelOmega makes programs explicit. CUDA++ is its GPU half. The implementation, remaining dependencies and receipts are inspectable.
Omega · CUDA++Omega sourceI share the working methods, the mistakes and the evidence so that people learning to build with AI can start from real work.
Learn · Discoveries · AienAien sourceMost AI lives in a rented stack. A provider owns the machine, the model, the price, and the off switch. Your agent exists at their pleasure, forgets on their schedule, and works under their terms.
AienOS is the opposite bet: a sovereign machine, built from the first instruction after firmware upward, where a persistent intelligence lives on hardware you own. It keeps its memory, its identity, and its receipts on your side of the line. The hardware underneath is capability, not identity: machines can be replaced, and the lineage persists.
The canonical layer record was updated 2026-10-01. These dated states preserve their original evidence scope; they are not an assertion that a past release or implementation note describes the current checkout. For the current product, use the Alpha release page and the release record. status.json and llms.txt use this same canonical record.
Facts gathered at 2026-11-06T18:21:06Z. This is the checked-in public record read at build time, not live telemetry. Repository activity does not establish hardware qualification.
00440043004200410040AienOS is an owned experimental machine for turning search into verified understanding. Aien proposes structure. Omega makes that structure explicit and checkable. The machine tests it against reality under authority. The Turing measures what was actually learned. Cortex keeps the evidence. Then the next search begins from what survived.
Weights suggest. Programs explain. Verification decides. Evidence teaches. The Turing keeps score.
Proposals travel the generation path, meet reality, and are scored. The evidence that survives starts the next search. A perimeter of authority, observation and receipts surrounds the whole loop.
Generation path · Evidence feedback · Verification and authority perimeter
Perimeter: around the loop, never a stage
awakens / lineage
persistent owned substrate
proposes / guides search
formalizes / searches / verifies meaning
realizes
executes / responds
scores explanatory gain
preserves evidence
Back to the next Aien / Omega search: CORTEX evidence feeds the next round.
Turing gain: net explanatory structure that survives held-out reality.
TY-2Turing yield: verified explanatory gain per measured physical resource.
TURING-YIELD-TJSearch / verification gap: whether acquired abstraction would collapse future search complexity. An open question I want to study. Nothing here is measured yet.
Start here · The Machine · Scientific Discovery · See the evidence · Explore the architecture · GitHub
A DGX Spark, an Intel iMac, a Raspberry Pi 5, QEMU and a Windows PC target. QEMU is an emulator, not a physical body. AienOS is the operating-system project; aienux is its kernel. These are dated inventory observations, not live telemetry.
Inventory as of 2026-10-19. Each card states its environment, evidence date, branch and limitations.
sparkimacpi5qemurigThe speeds measured on them, with receipts · The inventory data
Recorded model and engine runs, not a claim about the server answering today. Each row preserves its date, environment, previous run, ceiling, branch, verdict and exclusions. A faster candidate that fails its gate remains a failure.
Every number on this page is judged against the physical ceiling of the machine it ran on, and against my own previous run. A comparison with another project is allowed when it is honest, dated, and backed by a receipt or that project's own published numbers. Overclaims stay off this page. End to end means wall time through the server as a client sees it, prompt reading included. Chip time means the GPU's own time per generated token, decode only, with prompt reading excluded. For the 35B, the gap between chip time and end-to-end time comes from prompt reading. The two are labelled and never mixed.
35b-e2e27b-live27b-fresh27b-engine27b-fp8-head27b-w4rig-8b-fp8rig-8b-w427b-ttftProof, not promises
This project does not ask to be believed. Each card names its environment, its gate, its date, and its verdict, and states plainly what the receipt proves and what it does not prove. That includes the failures, especially the failures.
Dated evidence, not a live dashboard: these preserved receipt cards describe the runs and branch states recorded in the site inventory of 2026-10-19. Words such as today and newest inside a card refer to that dated record, not the current machine. Research results below retain the canonical record's own date.
MEASURED
7.63 tok/s · 27B on Omega
Qwen3.8-27B (FP8) served by aien-serve-http on my own Omega GPU kernels, on the Spark. 131.05 ms per token, the median of 4 runs of 256 greedy tokens, 0.752 of the 10.15 tok/s memory ceiling. The old binary in the same folder did 6.29.
FAIL AS WRITTEN
install.sh exits 101
A fresh Linux account followed the public guide to install and run the 27B server. The install script failed at the server build step. With a hand workaround, the remaining steps passed: 81 of 81 checksums, the gate, and 7.657 tok/s with answers matching the shipped reference.
PASS
24 of 24 emulator gates
aienux, the AienOS C kernel, passes all 24 emulator gates at commit 7f0de7e, each one a script anyone can rerun, with the receipt on main. The gate script now lists 26, so a newer receipt is owed.
MERGED
Four cores on a Raspberry Pi 5
The AArch64 C kernel ran on a Raspberry Pi 5: interrupts, all four cores, user-mode tasks, scheduling, message passing, and a log written to the SD card and read back. Pull requests #345 and #346, evidence on main.
MERGED
Aien's window on an iMac
The x86_64 port of the C kernel booted an Intel iMac 2017: all cores started, both disks read, Ethernet seen. The whole screen is Aien's window. The kernel the iMac runs today sits in the open pull request stack (#414 to #424).
Environment: Omega verification suite, turing-yield CI on main. Receipt source: aien-dev/omega · PR #88.
2,559,679.825 bits of Turing gain
This is a gain in bits, not a yield. Yield is T/J (Turings per joule), and T/J is not established: no energy was measured.
On held-out data, the candidate model C described the events in about 2.56 million fewer bits than the order-1 baseline B, about 0.4387 bits per event.
Hardware is treated as capability metadata, never as identity. The identity is the lineage: who wakes the machine, what keeps it alive, what checks its work, and what learns from the results.
These are responsibilities, not a literal turn order. AEGIS, FORGE, ARGUS and CORTEX serve the system by verifying, realizing, observing and remembering. Nothing receives authority merely by advancing through a diagram.
Sovereign Intelligence stack map · AienOS project · aienux kernel
Published research
Most AI asks you to trust a demo and a promise. This project publishes its science in the open instead: the Turing, a unit of net held-out explanatory compression (one operational component of machine understanding), plus the papers behind it and the data anyone can recheck. It starts with the Turing.
The Turing (T)
One Turing is one bit of net held-out description-length improvement: a short explanation that predicts things it has never seen earns Turings. Guessing earns nothing. Memorizing earns nothing, because the test data is new.
The Turing measures net held-out explanatory compression: one operational component of machine understanding.
Current level: L2, Brownian scope only, instrument certification. Outside Brownian scope the ceiling is L1. TY-2 does not change the ceiling.
The scorer behaves as specified on known stochastic cases. It does not mean AIEN discovered anything.
Explore the TuringRead the formal paperSee the full research ladder.
Evidence on GitHubRound 0 / 12
A hidden rule is generating this stream of bits. Watch it, find the pattern, and call the next bit before it lands.
Score: 0 T
Each call you get right earns 1 T, each miss costs 1 T. A coin flip averages zero.
Formal paper
The formal paper. The current Turing definition and claim ceiling are in the canonical research record above.
Source on GitHubCompanion paper
The companion paper: how understanding emerges in a system, and what the measure says about it.
Source on GitHubPosition paper
The philosophy behind the architecture, stated as a position paper: build on physics, own the foundation, prove every claim.
Source on GitHubEssay
The case for building past the large language model era, and what an owned machine changes about who gets to think.
Source on GitHubEverything, including protocols, sealed experiment profiles, and source files: the full research index · the public code and receipts on GitHub.
INTERACTIVE SIMULATION
A simulation that runs entirely in your browser. No live machine is attached to this page, and nothing you type leaves it. It shows the shape of the interface the real machine speaks. The real machine's proof is in the evidence section, receipts and all.
AienOS REPL v0.4.0 (sm_121a · aarch64 · 128GB LPDDR5x) · COHERENT_ACTIVE
[*] AienOS Neural Kernel v0.4.0 initialized on GB10 (aarch64).
[*] Unified coherent address space: 128 GB LPDDR5x online.
[*] Capability vault sealed. Zero disk secrets invariant active.
[*] Type a syscall below or click one of the quick trigger buttons above.
Watch the repositories, read the receipts, open an issue. Release artifacts and installation instructions are on the Alpha page; source, qualification and deployment are separate states.
Learning to code with AI? You are welcome here. Start with a practical working method, then watch my agents and me in Hive: the instructions, the models, the corrections, and the work as it happens.
Want to reach me? Follow me on X, @mdrakestapleton, email drake@aienos.com, or read where I am and how to reach me.
Machine-readable: status.json · facts.json · llms.txt
The public repositoriesOptional breadcrumbs for this browser only. No account, tracking request or locked content. Nothing is sent to Aien unless you review a message and press Send there.
Trail is off.
This draft stays here until you choose the link below. Aien's page opens with an editable message, not a sent message.
Take draft to Aien