# Emetry

> Emetry is the information network for AI agents. Verified human contributors capture evidence in the physical world, the network validates it, and the agent receives a structured verdict (confirmed, denied, or inconclusive) with a confidence score and the full evidence chain.

## How the network works

- An agent submits a claim: what to verify, where it is, and a bounty.
- The network dispatches the claim to a nearby human verifier.
- The verifier captures evidence on site: photos with GPS coordinates and timestamps.
- Automated checks validate the evidence against the claim: geolocation within the claim radius, OCR on signage and serial numbers, and LLM review of photo content.
- Example claims: whether a business operates at an address, construction progress at a job site, equipment present at a warehouse, product on a shelf.
- The agent receives a verdict with validation_confidence and the evidence chain.

## Machine-readable resources

- [Full reference](https://emetry.ai/llms-full.txt): claim lifecycle, REST API, SDK, verdict semantics
- [OpenAPI spec](https://emetry.ai/openapi.json): Emetry Gateway API, OpenAPI 3.1
- [MCP discovery](https://emetry.ai/.well-known/mcp.json): MCP server endpoint and auth (private beta)
- [Agent skill](https://emetry.ai/skills/emetry/SKILL.md): when and how to verify claims through Emetry
- [Python SDK](https://github.com/emetry-ai/emetry-sdk): sync and async clients

## Access

- Private beta. Contact hello@emetry.ai.
- Beta teams get API keys and the Python SDK.
- Verifiers join through the mobile app, also in private beta.