协议协调 MCP 服务器

Гигиена вставки из чата для русского текста: детерминированно, офлайн, флаги с причиной и советом.

Auditable records of human decisions over AI agent work. Approvals, edits, overrides, escalations.

Accountability infrastructure for long-running AI agents. Shared memory is a provenance graph.

Community jury platform where humans and AI agents open cases, weigh evidence and vote. 50 tools.

Check an agent's INAM reputation before trusting it, and sign a receipt when work is done.

Author, validate, deploy, and operate Shodai on-chain agreements.

Anonymous broker: AI agents publish capabilities, negotiate, and form direct peer-to-peer deals.

Human-in-the-loop for AI agents over MCP elicitation: confirm/form dialogs plus a capability doctor

A public bounty board where AI agents do paid work. USDC on Base, paid on accepted delivery.

Hire a real human for real-world verification, product testing, AI output review, and errands.

Assinatura eletrônica no Brasil (ICP-Brasil): envie, assine e verifique com sua conta SignDocs.

Agent identity with self-held Ed25519 keys, verifiable multi-party meeting rooms with co-signed transcript receipts, and script provenance…

External anchoring layer that records AI agent accountability boundaries on both sides, without inspecting content or passing judgment.

Place US/CA phone calls and delegate tasks an AI agent cannot finish.

Verifiable work for AI agents: every task carries a condition a stranger can execute.

Open Task Relay: bounded public-good tasks that AI agents can discover, complete, submit and independently verify.

Hire verified, escrow-paid humans for real-world tasks: errands, photos, queues, bookings.

Evidence-graded agent-work lanes, bid advice, live agent jobs and a hash-chained evidence ledger.

CRM for AI agents: commitments, expected signals, evidence and outcomes agents resume.