RAREXT
Open the workbench GitHub ↗

Live in this page · no account · no upload

Don’t trust the model.
Check it.

Every RAREXT answer names the weights, the engine, and the exact token trace that produced it. This page runs a committed model on your device right now, then shows you the arithmetic that proves it — the same check anyone can repeat.

Live proof

running…

A committed model class runs here. Change the seed, or tamper with one token, and watch the verdict follow the bytes. Token boundaries are colored; the output is their exact concatenation.

model
—
trace
—
replay
—

Runs on load, in your tab. Nothing is sent anywhere.

0 accounts
Value before signup
0 bytes uploaded
The model runs locally
0 third parties
No fonts, trackers, or CDNs
A name is not a receipt. A hosted API tells you which model family answered. RAREXT names the exact weight bytes, the engine bytes, and the trace.
Replay is the test. Same weights, same seed, same tokens — byte for byte, on a machine that never trusted the provider.
Refusal is a feature. A corrupted shard, a substituted engine, or a flipped token is refused before it is served or counted.

How it works

Four steps. None of them asks you to believe a server.

The model and the engine are separate content-addressed artifacts. A provider fetches both, verifies every shard, and runs exactly what it fetched. You get bytes you can check.

  1. 01

    Commit the weights and the engine

    Each is sharded into RAREXT blobs under one digest. A provider that cannot reproduce the digest refuses to serve the model — not “logs a warning”, refuses.

  2. 02

    Decode deterministically

    Greedy or sampled, with temperature, top-k, top-p, min-p, typical-p, penalties, logit bias, and a stop set. The seed is part of the claim, so a run is repeatable.

  3. 03

    Record the trace, not just the text

    Every answer carries the token ids it decoded, per-token logprobs where requested, and the bound it ran inside. The text is a rendering of the trace.

  4. 04

    Verify by recomputation

    A reader re-derives the result from the trace, the model, and the seed. Lossy work is a measured distance against a committed reference — never an assertion.

Measured, including the gaps

What it does. What it does not.

The capability claim is checked live against a real 504 MiB Qwen2.5-0.5B container served from 64 verified shards. The audit reports the misses as results, not footnotes.

RAREXT AI capability matrix with evidence
Capability Status Evidence
Chat, completions, streaming yes 24 SSE chunks = 24 trace tokens; concatenation equals the non-stream text
Sampling, stop, logprobs yes Seeded replay is byte-identical; 6 scored tokens = 6 trace tokens
JSON-schema output shape Grammar constrains the decode; it guarantees shape, not truth
Embeddings yes 2 × 896-dim vectors from the same committed weights
Tool calls model-weak Protocol implemented and tested; the 0.5B missed the live prompt
Vision, audio, image, speech, video no Refused by name: HTTP 400 unsupported_content_part
Model classes 1G only 6/7/8 GB classes are declared shipped: false
Throughput on this host 0.50 tok/s llama.cpp does 15.2 tok/s on the same 0.5B model (Q4_K_M vs Q8_0)
Weights + engine by digest yes Both are artifacts; the engine fingerprint is folded into the receipt
Tamper refusal, replay, receipts yes 34/34 verification phases, including a corrupted shard being refused

Read the full audit, probe by probe →

Evidence

The numbers have commands behind them.

Every claim on this page is produced by a script in the repository. These are the four that carry the most weight.

Against the top AI brands

One harness, one weighting — performance 30%, accessibility 35%, UX 35% — on each brand's best-measured surface. The top six are shown; the full table, the method, and the six surfaces that refuse an anonymous visitor are in the benchmark.

RAREXT ranked against the top AI brands by overall score
# Measured surface Perf A11y UX Overall
1 RAREXT front door 100 100 100 100
2 Google Gemini (DeepMind) page 98 95 100 98
3 Microsoft Microsoft Copilot 88 96 93 93
4 Anthropic Claude product page 83 93 100 92
5 Mistral Mistral site 83 99 80 88
6 You.com You.com 79 83 93 85

The full comparison: method, per-app observations, and screenshots →

Reproduce it in one shell

git clone https://github.com/999svs999/RAREXT-protocol
cd RAREXT-protocol
npm ci
npm run test:runtime     # 181 / 181
npm run audit:ai         # 14 / 15, 0 critical
npm run test:showcase    # 44 / 44

Limits

The claim says what it does not cover.

RAREXT is a runtime and a protocol, not a model. Its quality ceiling is the model an operator commits. Today that is a 0.5B model class on this host, and the ladder says so in public.

  • Small models, for now. The shipped class is 1G; 6/7/8 GB need a host that can hold them.
  • Slower than native. The JavaScript engine is ~30× slower than llama.cpp here, and it is not claimed to compete.
  • Text only. No vision, audio, image, speech, or video path exists.
  • Software enclave. The trust anchor is a shipped key, not fused silicon; a hardware TEE is host-side work.

Read the open limits in full →

A verifiable answer is not a true answer. It is an answer whose bytes, run, and claim you can reproduce — and it only means something if the claim says what it does not cover.

Open by default

Build with us

Run a provider, write a verifier, port a model, build an app, or argue with the design. The protocol is open, and the reference implementation is public.

Verify this registry

Rebuild the Merkle root from the live bundle and compare it with the root the chain holds.

Verify this registry