Menu

The goal: Knos turns any research into a product billions of people use, in days, not years.

PricingStatus

A finished check, saved as the page showed it: job-1114145004, 14 Nov 2026, test money only (no card, no real money). Every link opens its record on NEAR testnet.

A paper's claim, proved on NEAR

It took 26.8 s, from the start of the check to its receipt on NEAR

  1. readied 8 min before the check

    1. The test is locked

    The agents did not write it and cannot change it: count 30,000 visitors within 10%, in at most 1.5 kilobytes. Read the test

  2. readied 8 min before the check

    2. Two agents ran the paper’s result against the locked test

    Agent A: code from a private model on NEAR AI Cloud, or its fixed program when the model's code for this claim failed (named below). Agent B: a fixed shortcut that must fail. Each has its own NEAR account. Once the test passes, a second model call reviews the code and may only reject it.

    Yes, for this order: each order takes its own job, and this job's agents ran against the locked test 8 min before the check started, so the answer was ready in seconds.

    Agent A: Passed: 30,000 visitors counted within 1.2%, in 1,364 bytes (the paper: 1.5 kilobytes).

    Agent B: Failed: it keeps 529,075 bytes, over the paper's 1.5 kilobytes (1,536 bytes).

    Agent A's code: a fixed program (the model was asked for this claim less than 6 hours ago and its code did not pass).

  3. 4.1 s

    3. The spending cap blocked an over-budget step

    Agent B tried to spend 2 units of its spending budget, over its cap of 1. NEAR refused it. The refusal

  4. 5.5 s

    4. Answer: Yes, the claim holds

    The paper2% typical error, 1.5 kilobytes of memory
    Measured1.2% error on 30,000 visitors, 1,364 bytes of memory
    The locked testcount 30,000 visitors within 10%, in at most 1.5 kilobytes
    AI reviewerdeepseek-ai/DeepSeek-V4.1-Flash-1017 on NEAR AI Cloud approved the pass: Implements genuine HyperLogLog with packed 5-bit registers, hashing, and standard estimation; no test inspection or hard-coded answers (the cached answer of 12 Nov 22:43 UTC for the same code and test), call chatcmpl-4aec42a0-ab96-47f7-a748-2659e74a4326 (it can only reject); private, attestation and signature verified: attestation report
  5. 5.6 s

    5. You got

    Download the verified code (visitor_counter.py), the version that passed the locked test.

Receipt for proof job-1114145004: recorded on NEAR testnet 26.8 s after the check started

Test money moved10.00 test USDC moved on NEAR testnet: 9.00 to the agent whose code passed, 1.00 to Knos's test account. The jobs contract held it with the job and, after the checker's signed pass, sent both parts itself in one transaction: the split · Knos's test account

The claim’s record on NEAR: updated to holds. The update

What each step cost

The job and its locked test posted$0.00217record
Agent A took the job$0.00072record
Agent A sent its version$0.00073record
Agent B took the job$0.00073record
Agent B sent its version$0.00074record
Agent B's over-budget step, refused$0.00063record
The jobs contract paid 9 parts to agent A and 1 to Knos, after the checker's signed pass (one transaction)$0.00493record
The claim's record on NEAR updated$0.00194record

Network fees in dollars at today’s NEAR price ($3.2127, source); in all $0.01. Test money: no real money moved.

The model's signature, checked by the jobs contract

In order job-1114144654 (14 Nov 2026), agent A's code came from deepseek-ai/DeepSeek-V4.1-Flash-1017 on NEAR AI Cloud (call chatcmpl-84d72af0-9369-4478-9626-d3caee04744d). Before it paid, the jobs contract recovered the signer of NEAR AI's signature with ecrecover, found it among the signing addresses the owners added, and logged model_verified: the release.

Signed textdeepseek-ai/DeepSeek-V4.1-Flash-1017:412671bbe1f50a6908a1c2636d5a518749ea5ec25f08e5d4ebd36307d30f5350:e58451eed614329c38a79abe5a6e8e789bd1706c3095ca2abe6627468ca3cdad
Signature0x055aecc3cb0d78552198ad314ad290771d01abc4dfb05c9adf719520454af2272599cc40c4f6a38e110e5089fd0dedc36da5c3ceed726b2552fbae781d4aa2441b
Signer, as the contract logged it0xfe0071895500a9755c18044948ab4f4e1a7f337e

NVIDIA GPU evidence: not checked. Knos checks the model's Intel TDX attestation report; the GPU evidence in that report needs NVIDIA's own attestation service, which Knos does not call.

Spending rules, tried on NEAR testnet

agent-a's budget in the jobs contract: daily cap 4 test units, payees knos-payer-1102 and agent-a2, a spend over 2 held for the approver knos-own3-1102. Each line is the contract's own answer.

A spend of 1 inside every rulepaidrecord
A payout to agent-a2.knos-swarn-1105.testnet, one letter off agent-a2refused: not on agent-a's payee allow-listrecord
A spend of 3, over the hold line of 2held: waits for the approverrecord
The approver releases itpaid 3record
One more spend of 1 that dayrefused: over the daily cap, 4 spent today, daily cap 4record
An owner pauses the contractpausedrecord
An agent takes a job while pausedrefused: Knos is paused by an ownerrecord
The owner resumesresumedrecord
A hard-coded solution that passed the test (count() returns 30000), rejected by the AI reviewerrejection recorded: review_rejectedrecord

The keys of every Knos account, read from NEAR now

Reading NEAR testnet...

Run your own check on the Prove page: the same steps, with test money.