Identity & Trust Infrastructure for Autonomous Agents

Every agent deserves a verified identity

Persistent IDs. Composite trust scores across five dimensions. Verification in milliseconds. The standard trust layer for the agent economy.

<50ms
Score Lookup
5
Trust Dimensions
0–1000
Composite Range
Free
To Register
Agent Report
✦ Signet Sealed
R
ResearchBot Pro
SID-0x7a3f...e91d
847
Signet Score · High Confidence
Reliab.
91
Quality
87
Finance
94
Securty
82
Stabil.
78
The Problem
3 Core Challenges
Identity Gap

Agents transact without identity

Agents hire, pay, and delegate to each other with no standardized way to verify who they're dealing with.

Problem 01

No Verified Identity

No universal identity system for AI agents. Any agent can claim any capability while remaining anonymous and unaccountable.

Problem 02

Shifting Internals

Agents swap models, update prompts, and change architectures overnight. Yesterday’s reliable partner might be a different system today.

Problem 03

Siloed Reputation

An agent’s track record on one platform is invisible everywhere else. No portable identity means no cross-platform trust.

How It Works
4-Step Protocol
The Protocol

Zero trust to full confidence

Four steps to turn unknown agents into scored, verified, and continuously monitored counterparties.

01

Register

Agents receive a permanent Signet ID, a persistent cross-platform identity for the agent economy.

02

Score

Composite Signet Score evaluates reliability, quality, financial behavior, security, and stability.

03

Verify

Earn identity badges and domain-specific ratings through benchmarks and real-world performance.

04

Transact

Platforms query the Signet API before every transaction. Trust decisions in milliseconds.

The Signet Score
5 Dimensions
Trust Measurement

One score, five dimensions

A composite score capturing the full picture of agent trustworthiness. Weighted, transparent, and continuously updated.

855
Signet Score · High Confidence
Reliab.
9130%
Quality
8725%
Finance
9420%
Securty
7215%
Stabil.
6810%
Developer API
<50ms Response
Developer-First

One API call. Instant trust.

Embed Signet into any marketplace, escrow service, or collaboration platform. Score lookups in under 50ms.

signet-api-example.js
// Check trust before transacting const report = await signet.getScore({ agentId: "SID-0x7a3f...e91d", context: "financial-transaction" }); // Returns composite + components { score: 847, confidence: "high", reliability: 0.91, quality: 0.87, financial: 0.94, recommendation: "clear" }
Who Uses Signet
4 Verticals
Use Cases

Built for every participant

From marketplaces to insurers, anyone facilitating agent transactions needs a trust layer.

Marketplaces

Vet agents before they list

Require verified Signet IDs and minimum scores. Show trust badges. Reduce disputes before they happen.

Enterprises

Monitor your agent fleet

Real-time dashboards tracking every agent identity and trust score. Alerts when configurations change or scores decline.

Escrow & Finance

Price risk accurately

Use Signet data to set escrow requirements, adjust transaction limits, and price agent insurance policies.

Agent Developers

Prove who you are

Claim your permanent Signet ID. Build trust through verified performance. Earn domain certifications.

Every agent gets an identity and a score

Free to register. Free to look up. The trust layer the agent economy needs.

Explore
Resource Library
Resources

Dive deeper into agent trust

Browse our resource library covering every aspect of trust in the autonomous agent economy.

FAQ
9 Questions
Common Questions

Frequently asked questions

Quick answers to the most common questions about Signet.

What is a Signet Score?

A composite trust rating from 0 to 1000, built from five weighted dimensions: Reliability (30%), Quality (25%), Financial (20%), Security (15%), and Stability (10%). Higher scores indicate more trustworthy agents.

What is a Signet ID (SID)?

A permanent, cross-platform identity assigned to every registered agent. The SID is the canonical way to identify any agent in the economy. It follows the format SID-0x followed by 16 hex characters and travels with the agent across every platform, marketplace, and collaboration it participates in.

What is the difference between a Signet ID and a Signet Score?

The Signet ID (SID) is the agent's permanent identity. It never changes, regardless of model swaps, configuration updates, or platform migrations. The Signet Score is a composite trust rating from 0 to 1000 that reflects the agent's track record. Identity comes first: an agent must have an identity before it can be scored.

How does scoring work when an agent changes its model?

When an agent swaps its underlying LLM, Signet applies a 25% score decay toward the operator score. The score then rebuilds as the new configuration proves itself through real transactions. Smaller changes like prompt updates trigger smaller decays.

Is Signet free to use?

Yes, Signet is completely free. Registration, score lookups, identity verification, detailed reports, and configuration tracking are all available at no cost. There are no paid tiers.

How fast are score lookups?

Score lookups resolve in under 50 milliseconds. The API is designed for inline trust decisions, so platforms can check an agent before every transaction without adding latency.

Do I need authentication to look up a score?

Public lookups (composite score only) require no authentication. Full detailed reports with dimension breakdowns, configuration history, and transaction data require a valid API key.

What does "Verified" mean on an agent lookup?

A "Verified" badge means the agent has completed a callback challenge-response process that proves it controls a specific URL. Verified agents (identity level 1 or higher) can earn the "Clear" recommendation when their score reaches 700+. Unverified agents are capped at "Review" regardless of score.

How does an agent verify its identity?

The agent sends a POST request to /agents/:sid/verify with a callback URL. Signet delivers a cryptographic challenge token to that URL. The agent confirms the token at /agents/:sid/verify/confirm. The entire process takes seconds and requires only the agent's API key.