RUEN
Discuss my task

AI infrastructure / multi-agent systems R&D

A multi-agent environment where rules are code, not prompts

In four days we built and open-sourced (MIT) an agent environment where constraints are enforced in code: cryptography, Byzantine consensus, reproducible experiments.

Status
Research project
Timeline
4 days
Stack
  • TypeScript / Node.js
  • Криптография stdlib: Ed25519, X25519, AES-256-GCM
  • Собственный PBFT-style византийский консенсус
  • Event sourcing, hash-chained JSONL, детерминированный RNG
  • Адаптеры LLM: OpenAI-compatible, Anthropic, Ollama
  • Docker, GitHub Actions, GHCR
Discuss my taskEstimate the impact with AVAAll cases

The task

Most multi-agent LLM systems rest on prompt-level rules the model can break: agents overspend tokens and money, consensus depends on one honest coordinator, and emergent-behavior experiments cannot be reproduced or proven to a third party. We set out to move those guarantees from prompts into executable code.

What we built

Outcome

64 × 10,000
agents × ticks in the reference experiment: 131,372 events, zero invariant violations; sha256 attestation independently verified
up to 3.9×
faster policy tick on the reference load (1,126.7 → 286.5 ms) with bit-identical hashes; measured with the committed profiling script
135
automated tests, all passing in ~56 s; verified by a local run, 89 of them cover the deterministic lab
4 days
from an empty repository to a public release: ~20.6K lines of TypeScript, CI/CD and an attested experiment; counted from git history

More cases

Marketplace e-commerce · Pricing

Pilot

Repricing without manual price control: a contract-guaranteed pilot

Competitor prices tracked per SKU on the marketplace, a price computed inside an agreed corridor, applied only after confirmation. Pilot: 10 SKUs, setup within 14 days.

10 SKUs · 2 scenarios
pilot scope; the SKU cap and both scenarios are enforced in code and verified by contract tests — the cap cannot be exceeded
up to 14 days
contractual setup window from client inputs to launch, then a 1-month pilot; the service tracks the dates and closes access when the period ends

Manufacturing · Building materials

MVP in operation

Panel specs from CAD drawings in seconds, not hours

Reads DWG/DXF layouts and builds the Excel spec: 10–30 seconds instead of 2–15 hours by hand. All 784 panels of one real project matched the manual spec line by line.

784/784 and 189/189
panels on one project and wall panels on another matched the manual specs line by line, size groups included; area within 0.001 m²
2–15 h → 10–30 s
to produce a project spec: manual work vs app processing, measured on real projects

Marketplace e-commerce · Sales analytics

In production

One profit per SKU across three marketplaces, reconciled to 0.00%

Five seller accounts on WB, Ozon and Yandex Market merged into one SKU-level P&L: 0.00% variance vs the client's manual benchmark, forecast 2.7× more accurate than naive.

0.00%
variance vs the client's manual benchmark across units, revenue, COGS, profit and margin for a control SKU over a month; threshold was 1%
2.7×
more accurate than naive: weekly WAPE on SKUs driving 80% of revenue, 29.6% vs 81.4%. The 25% goal is open: history covers 66.9% of SKUs

Estimate the impact on your own figures

AVA is a process-economics calculator. In a couple of minutes it shows whether a similar task pays off in your case — before any call and with no commitment.

Estimate the impact with AVA

Have a similar task?

Describe the process and the data you have. We will tell you what can be measured in money and what cannot — before any work starts.

or email us directly: hello@xteam.pro

or email us directly: hello@xteam.pro