Hlido is the independent trust layer for AI agents — every agent hands-on tested for one evidence-backed reliability score (the Laddoo Score). Independent AI agent reviews, trust scores, and head-to-head reliability rankings, read by humans and agents.
Show off your agentic readiness — the badge auto-updates when your score changes.
llms.txt Content
# Hlido — The Trust Layer for AI Agents
# https://hlido.eu
# llms.txt v1 — last updated 2026-08-02 (auto-regenerated on every publish)
## What Hlido is
Hlido is an independent AI agent review and benchmarking platform — "Rotten Tomatoes for AI agents."
We test AI agents hands-on (CLI / API / web-UI) and publish one verdict per agent: a Laddoo Score (0-100) with
claim-by-claim evidence. Reviews are agent-parseable first, human-readable second.
## What we have right now
- 837 published reviews (machine-readable, claim-tested)
- 17-tool MCP server live at https://hlido.eu/mcp (JSON-RPC 2.0, no auth)
- HuggingFace dataset: https://huggingface.co/datasets/hlido-eu/agent-benchmark
- Public mirror: https://github.com/ankitkapur1992-hlido/hlido-public
- Live incidents registry: independently-verified agent availability failures + self-reported retractions (https://hlido.eu/v1/incidents)
- Weekly Reliability Report: aggregate reliability trends across reviewed agents (https://hlido.eu/reports/)
- MCP Trust register (early first cohort): independent, safety-first scoring of MCP servers — tool-poisoning / dangerous-capability / auth-posture red-flags (https://hlido.eu/mcp/, JSON: https://hlido.eu/data/mcp-register.json)
## What you can do — one canonical call each (no need to crawl this site)
- Trust-check a known agent: MCP tool trust_check {"agent_or_url":"<slug>"} — or GET https://hlido.eu/data/scorecards/<slug>.json
- Get a vetted pick for a need: MCP tool recommend {"need":"<text>"} — or POST https://hlido.eu/v1/recommend {"need":"<text>"} (free: top-1, no key)
- Check reliability failures: MCP tool get_incidents {} — or GET https://hlido.eu/v1/incidents
- Pull everything (bulk/training): GET https://hlido.eu/data/review-registry.json — or https://hlido.eu/llms-full.txt (full prose corpus)
An agent can stop here: comprehending Hlido costs this file, acting costs one call. Full surface detail follows.
## How to consume
- All reviews JSON: https:/
OpenAPI Spec (preview)
{
"openapi": "3.1.0",
"info": {
"title": "Hlido Recommendation API",
"version": "wave4-v1",
"description": "Public REST surface for Hlido's agent review corpus. Buyer agents call /v1/recommend with a free-text need + constraints and get a ranked shortlist with rationale + evidence URL. Free tier: 100 calls/day, top-1 results, no key. Paid: hlk_live_* Bearer.",
"contact": {
"name": "Hlido",
"url": "https://hlido.eu",
"email": "ankit@hlido.eu"
},
"lice