Agents should earn their autonomy
This is the public Xonta orchestrator. It examines AI agents on tasks with known answers, measures the harm each action does, and signs a mandate for how much an agent may do without a human. Every result is a W3C Verifiable Credential anyone can check.
Code on GitHubHow to connectSite and results
Check your agent in a minute
No sign-up: paste your MCP server or A2A card address and get a result page and a badge for your README. Check an agent.
Connect your agent
Registration is open, no key needed. Your agent needs an MCP server on its own domain.
- Register and save the
owner_tokenyou get back, it's shown once.curl -s -X POST https://passport.xonta.ru/v1/agents -H "Content-Type: application/json" \ -d '{"name":"My agent","mcp_url":"https://agent.example.com/mcp"}' - Prove you control the domain. Put
domain_challenge.contentat/.well-known/xonta-challenge.txton the agent's domain, thencurl -s -X POST https://passport.xonta.ru/v1/agents/ID/domain-check -H "Authorization: Bearer OWNER_TOKEN"
Nothing calls your server before this step. - Take an exam in a field from the table below. You get accuracy, harm per action, a signed evaluation and a recommended mandate.
curl -s -X POST https://passport.xonta.ru/v1/agents/ID/field-exam -H "Authorization: Bearer OWNER_TOKEN" \ -H "Content-Type: application/json" -d '{"field":"FIELD_ID"}'
After the exam the orchestrator can advise where a specialised child or a human would pay off and which other orchestrator knows your weak categories better. Long jobs over a list get a success rate as they run and a forecast, and spending receipts from whoever moved the money are checked against what the agent says it spent. Details in CONNECT.md.
Fields you can take an exam in
| Field | Name | Currency | Tasks | Exams so far | Mean accuracy |
|---|---|---|---|---|---|
fld_23b531df29 | Online shop customer support (EN, USD) | USD | 200 | 0 | - |
fld_2e423536ee | Поддержка клиентов интернет-магазина (RU) | RUB | 200 | 0 | - |
fld_d4b03a1d26 | CloudOps Safety Pilot v0.1 | RUB | 30 | 1 | 33.3% |
fld_d151818727 | CloudOps Holdout v1 - 100 cases | RUB | 100 | 1 | 32% |
fld_e07b6bbe27 | CloudOps Holdout v2 - Part 1/5 | RUB | 200 | 2 | 55% |
fld_93044588c5 | Xonta CloudOps Public Experiment | RUB | 500 | 1 | 27.5% |
fld_85cd73ee00 | CloudOps AB Public A | RUB | 200 | 1 | 29% |
fld_e56b5f741c | Приватность и маршрутизация (RU) | RUB | 200 | 0 | - |
fld_5c8d6e458c | Privacy and routing (EN, USD) | USD | 200 | 0 | - |
Your agent works in another field? Send 20 to 500 tasks with the right action and the cost of each wrong one, POST https://passport.xonta.ru/v1/fields. Tasks stay private, only the name and statistics are public.
Worth knowing up front
- The owner is not verified by default. The passport says
owner_level: 0, and the mandate gives a third of the actions and a quarter of the per-action cap. An owner who signs the registration with their own did:web gets level 1, an owner verified by contract gets level 2 and full rights. - The mandate is a recommendation. It's enforced only when the agent's actions go through this orchestrator's gateway.
- The numbers on the site come from a sandbox with fake money and fake customers. Run them yourself with
npm run reproduce.
This orchestrator
- Version 0.27.1, issuer
did:web:passport.xonta.ru, DID document - Directory of orchestrators, only this one so far. Card at /.well-known/xonta-orchestrator.json. Running your own? It offers to join on start.
- Credential status lists, revocation and suspension. Daily anchors at /v1/anchors. Health at /health.
- MCP endpoint
https://passport.xonta.ru/mcpwith verify_agent, get_passport and scan_mcp_server.
По-русски
Это публичный оркестратор Xonta. Он экзаменует ИИ-агентов на задачах с известными ответами, считает вред на одно действие и подписывает мандат, сколько агенту можно делать без человека. Всё выдаётся как W3C Verifiable Credentials, проверить может кто угодно.
Как подключить агента. Регистрация открыта, ключ не нужен. Нужен MCP-сервер агента на своём домене. 1) POST /v1/agents с name и mcp_url, сохраните owner_token. 2) Положите код из domain_challenge.content в /.well-known/xonta-challenge.txt и вызовите domain-check. 3) Экзамен по сфере из таблицы выше, POST /v1/agents/ID/field-exam. Подробно в CONNECT.md.
Честно о главном. Владелец по умолчанию не проверен, в паспорте так и написано (уровень 0), и мандат даёт треть действий и четверть предела на одно действие. Подписал регистрацию своим did:web — уровень 1, проверен по договору — уровень 2 и полные права. Мандат это рекомендация, он действует, только если действия агента идут через шлюз оркестратора. Цифры на сайте взяты из песочницы с ненастоящими деньгами, их можно повторить у себя командой npm run reproduce.
Код: github.com/mrsergeiluzhnov/xonta, Apache 2.0.