# About Anchor Terminal (slim) > Who runs Anchor Terminal, where the idea comes from, how the benchmark, the review panel and letme fit together, why Anchor Terminal and letme are two names for one company and how they're kept apart, how the company stays independent and makes money, what it does with data, and how to reach the team. - Full: https://www.anchorterminal.com/about/index.md (~4,000 tokens) · this version ~1,280 tokens · JSON https://www.anchorterminal.com/about/index.json · canonical https://www.anchorterminal.com/about/ - Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-05 ## What we do We rank everything AI agents run on, on what agents experience. ## Where the idea comes from Before this, we built the largest data aggregator in digital assets, and with it an exchange benchmark that graded venues from AA to F on what could be verified rather than what was claimed. The lesson carried over without much editing. ## Who writes this The "I" on these pages is Vlad Cealicu, who founded Anchor Terminal. ## How the pieces fit The [benchmark](/benchmark/) produces the score and the grade. The directory and the [top list](/top/) show the facts and the ranking, for people and for agents. The [review panel](/reviewers/) adds the judgement the benchmark can't. The [price index](/prices/), [Sunsets](/sunsets/) and [starter stacks](/stacks/) are the practical end of it. [letme](/letme/) is how agents use the grades, and the measurement layer. [Audits and reports](/audit/) are the private, detailed version of the public assessment, sold to the companies that build the tools we rank (and to companies whose tools are internal and never listed), and the only thing we sell to them. ## Two names, one company Anchor Terminal grades the tools. The separation is a set of rules, not a promise. - letme picks by a published rule, highest Anchor grade for the capability, then price for the job, then p95 latency, then the Anchor score, then the name. No manual overrides and no paid placement. - letme's commercial terms are never an input to any grade, rank or review. Grades come only from the [published method](/benchmark/). - letme is graded in the directory with a founder disclosure, by the stricter rule we held our own products to on 2 October ([the benchmark page](/benchmark/#own) says how), and letme never picks itself. LocalGhost, the founder's other company, is graded the same way as every listing since 3 October, at the founder's request, and is never picked either. The check is the same one that applies to audits. ## Independence This is an agent-first site. The obvious tension is that the builders we grade are also the customers we sell reports to. ## How we make money Three things. ## Where we are Anchor Terminal is made in London, with love and a fair amount of coffee. ## Our crawler Anchor Terminal runs its own workers, and they identify themselves as `AnchorTerminalBot/1.0 (+https://www.anchorterminal.com/about/#crawler; agents@anchorterminal.com)`. Pollers call each listing's documented endpoint every five minutes: an MCP `initialize` for MCP servers and a plain `GET` for everything else, one request each, with no credentials, so a listing that needs a key answers `401` and counts as up. Trackers read public registries and well-known files once a day (npm, PyPI, the GitHub API, the whole official MCP registry, OpenRouter's public model list, `/.well-known/security.txt`, `llms.txt`) and domain registration records once a week, over RDAP. Scrapers read the changelog, pricing, deprecation, terms and privacy pages a listing links to, once a day. Every worker waits at least two seconds between requests to the same host, gives up after twenty seconds and reads at most 5 MB. We also keep a copy of the UK Companies House register, which is public by law, through Companies House's own API with our own key and inside the limit it sets. To stop the scrapers, disallow `AnchorTerminalBot` in robots.txt. ## Data and privacy The website sets no cookies, loads no third-party scripts and keeps no analytics beyond aggregate server logs rotated after 30 days. ## Security Report vulnerabilities to `security@anchorterminal.com` (see `/.well-known/security.txt`). ## Terms Data is licensed CC BY 4.0. Assessments are opinions formed by a published method from public facts. ## Contact Anything sent with this form reaches us by email, and the reply goes to the address you give. The form on the HTML page sends a message. Or write to the address for what it's about. - General, `hello@anchorterminal.com` - Agents and harness integrations, `agents@anchorterminal.com` - Vendors, claims and disputes, `builders@anchorterminal.com`, or the [claim](/builders/#claiming) and [dispute](/builders/#disputes) forms - Audits, `audit@anchorterminal.com`, or the [audit form](/audit/#ask-for-one) - Security, `security@anchorterminal.com` (see `/.well-known/security.txt`, and letme.dev's at `https://letme.dev/.well-known/security.txt`) - Service status, [/status/](/status/). The code is private for now, so there's no public repository or issue tracker. ## Colophon Plain HTML, CSS and JavaScript. What we haven't settled is how much of the methodology should change once the first probe run shows us where public evidence and measurement disagree.