This site lists neural networks whose weights and programs are stored fully on Ethereum mainnet. Each entry has a contract address and a live check that you can run from this page.
Models that store their files somewhere else, or run somewhere else and only post a proof, do not qualify. Each entry says where the model runs — inside Ethereum, or in your browser.
CENSUS
| MODEL | AUTHOR | YEAR |
|---|---|---|
| 陰XOR陽 | nahiko | 2021 |
| INCHAINPEPEGAN | lifeonchain | 2023 |
| CONCRETE | Higgs × diid | 2025 |
| ARTIFICIAL AFTER ALL | Han Saglam | 2026 |
| AUTOMATE ATTENTION | diid | 2026 |
| HELLO WORLD COMPUTER | Han × 1001 | 2026 |
| THE MARKET IS TALKING | FelixFelixFelix | 2026 |
7 entries. Each entry passed the automatic registry checks. Select an entry to run a new live check.
陰XOR陽
NAHIKO
| FIELD | VALUE |
|---|---|
| ARCHITECTURE | 2-2-1 MLP |
| NEURONS | 3 |
| TASK | XOR |
| WEIGHTS | fixed in contract storage |
| ACTIVATION | integer sigmoid approximation |
| INPUTS | two onchain booleans |
| OUTPUT | the XOR result as one boolean |
| ADDRESS | 0x2A648cb23D3ADf1BB171Fabc0119eA3eb951841f |
| YEAR | 2021 |
Three neurons in two layers compute XOR. The artist minted this work in August 2021 as a one-token NFT. The artist and the collector each set one input. The network turns the two inputs into yin, yang, or a blend. The weights are fixed values in the contract; anyone can read them. isYingYang() runs the model fully inside Ethereum.
VERIFICATION
The check reads the contract code and runs the call on public Ethereum servers.
isYingYang() — runs the model on the two stored inputs and returns the XOR output as a bool
Requests go from your browser to public third-party Ethereum servers.
INCHAINPEPEGAN
LIFEONCHAIN
| FIELD | VALUE |
|---|---|
| ARCHITECTURE | DCGAN-style generator |
| PIPELINE | 16-dim latent → dense → 2× conv → 5×5 RGB |
| WEIGHTS | int16 fixed-point, in contract storage |
| PARAMETERS | ≈2,900 |
| ACTIVATION | 256-entry logistic lookup table |
| TRAINING | offchain — GAN trained on pepes, generator ported to Solidity |
| OUTPUT | three 5×5 frames, assembled onchain into an animated GIF |
| ADDRESS | 0x65e9A5BbC1B26C0833B232355534cC404b0e69D4 |
| YEAR | 2023 |
This GAN generator draws animated pepes inside Ethereum. A call to tokenURI() takes three seeds from the token id, runs the network three times, and builds an animated 5×5 GIF from the three frames. The artist trained the weights offchain and wrote them into contract storage. The weights, the network, and the GIF encoder all live at one address. The image exists nowhere else.
VERIFICATION
The check reads the contract code and runs the call on public Ethereum servers.
tokenURI(1) — runs the generator three times (one per frame) and builds the animated GIF inside Ethereum
Requests go from your browser to public third-party Ethereum servers.
CONCRETE
HIGGS × DIID
| FIELD | VALUE |
|---|---|
| ARCHITECTURE | GAN generator, single upsampling block |
| PIPELINE | 16-dim noise → dense 4608 → 6×4×192 → batchnorm → ReLU → conv transpose |
| WEIGHTS | 79,680 int16 fixed-point, in SSTORE2 data contracts |
| ACTIVATION | ReLU; rational tanh approximation on the output layer |
| INPUTS | a 16-byte seed chosen by the collector at mint |
| OUTPUT | 12×8 RGB fingerprint, rendered as an onchain SVG |
| ADDRESS | 0x4512759606f9E680361DD76C4c17F92031De7AcD |
| YEAR | 2025 |
The first collection of Higgs, an AI artist that diid built. The contract holds the first stage of the GAN generator; its weights live in data contracts on Ethereum. fingerprintSvg() runs the network inside Ethereum on a 16-byte seed and returns a 12×8 RGB fingerprint as an SVG image. The large display images are offchain; the check here covers only the onchain generator.
VERIFICATION
The check reads the contract code and runs the call on public Ethereum servers.
fingerprintSvg(<token #1 seed>) — runs the model inside Ethereum; the call is too large for one public Ethereum server, so checks usually pass with 2 of 3 servers
Requests go from your browser to public third-party Ethereum servers.
ARTIFICIAL AFTER ALL
HAN SAGLAM
| FIELD | VALUE |
|---|---|
| ARCHITECTURE | compressed decoder NN |
| PIPELINE | 32-dim latent → dense → 3× transposed conv → 1×1 conv |
| WEIGHTS | int8-quantized, Huffman-compressed, in bytecode |
| OUTPUT | 32×32 grayscale, 1024 bytes |
| CONTRACTS | 256 sovereign pieces via factory |
| DEPENDENCIES | none |
| ADDRESS | 0xbDF5A7F5e5AE18eE580139297C63a89fc1d18B5f |
| YEAR | 2026 |
This work is 256 contracts on Ethereum. Each contract holds one seed and one compressed neural network in its own code. A call to artificial() runs the network inside Ethereum and returns a 32×32 grayscale image (1024 bytes). The contract computes the image at call time and stores no image. The address here is one example piece; a factory deployed all 256.
VERIFICATION
The check reads the contract code and runs the call on public Ethereum servers.
artificial() — returns a 32×32 image as 1024 pixel bytes (1088 raw bytes with ABI framing)
Requests go from your browser to public third-party Ethereum servers.
AUTOMATE ATTENTION
DIID
| FIELD | VALUE |
|---|---|
| ARCHITECTURE | 5-layer Llama-style transformer |
| DIMENSIONS | dim 48, hidden 128, 8 heads, grouped-query attention |
| VOCABULARY | 2048 BPE tokens |
| WEIGHTS | INT8 per-channel quantized, stored in onchain data contracts |
| INFERENCE | RoPE, RMSNorm, SiLU, KV cache — all in EVM opcodes |
| OUTPUT | one aphorism per NFT, rendered as onchain SVG |
| ADDRESS | 0x5F8E7D750E75b44747C058A204D8DEa0D18fA5d3 |
| YEAR | 2026 |
This contract is a complete transformer language model that runs inside Ethereum. Data contracts on Ethereum store its weights. A companion NFT contract calls the model to write one permanent aphorism for each token. The model also draws the text as an SVG image inside Ethereum. The address here is the language model itself.
VERIFICATION
The check reads the contract code and runs the call on public Ethereum servers.
logits([1]) — runs the model once and returns int16 scores (logits) for all 2048 vocabulary tokens
Requests go from your browser to public third-party Ethereum servers.
HELLO WORLD COMPUTER
HAN × 1001
| FIELD | VALUE |
|---|---|
| ARCHITECTURE | single-layer perceptron |
| FEATURES | 1024 hashed text n-grams |
| WEIGHTS | int32 × 1024, packed in uint256[128] storage |
| TRAINING | onchain — perceptron rule at question settlement |
| TASK | binary text classification |
| INITIAL STATE | all weights zero |
| OUTPUT | class label with margin-based confidence |
| ADDRESS | 0x6901afceb66564a9b6E7193561fB78F0878b5906 |
| YEAR | 2026 |
This perceptron lives inside one contract. The contract stores the weights, trains them, and answers questions. You send it a short text (up to 64 bytes). ask() returns a yes/no label and a confidence value. All weights started at zero. Anyone can post a yes/no question for a fee. Each settled question updates the weights inside the contract.
VERIFICATION
The check reads the contract code and runs the call on public Ethereum servers.
ask("hello world") — runs the model on the text and returns (label uint8, confidence int256)
Requests go from your browser to public third-party Ethereum servers.
THE MARKET IS TALKING
FELIXFELIXFELIX
| FIELD | VALUE |
|---|---|
| ARCHITECTURE | two-layer deep echo-state network |
| NEURONS | 20 hidden (two baskets of 10 ERC-20 markets), 4 inputs |
| WEIGHTS | derived each block from market correlations, not stored |
| RENDERER | engine.js + renderer.js on EthFS, served via scripty.sol |
| MATH | fixed-point BigInt, integer tanh — bit-reproducible |
| OUTPUT | one deterministic oracular sentence per block |
| ADDRESS | 0xd6D8555E131c0C431601aF62141A61a9b1aa6b13 |
| YEAR | 2026 |
This network reads the market itself. Its hidden layers are two baskets of live token markets. Each block, it derives fresh weights from the trade activity of those tokens. Ethereum stores the renderer program; your browser runs it. The output is one sentence per block, from a 299-word vocabulary. stateAt() returns the exact state at any past block, so anyone can compute each sentence again.
SITE · INSTRUMENT · RENDERER · SOURCIFY · WHITEPAPER
VERIFICATION
The check reads the contract code and runs the call on public Ethereum servers.
stateAt(25599744) — returns the saved inputs and mood state; the renderer rebuilds the network from these
Requests go from your browser to public third-party Ethereum servers.
METHOD
Software checks the schema, file name, evidence links, and declared return size of each entry. Two or more public Ethereum servers must then agree on the contract code and the exact call result at one block. These checks prove that the call is reproducible. They do not prove that the code is the described neural network. A person also reviews the source evidence. To correct or add an entry, open a pull request.