Who is Andon Labs for?

Andon Labs is a B2B product built for AI researchers and labs.

Is Andon Labs still maintained?

Unverified. Andon Labs has not been re-checked since it entered the index, so there is no finding either way — and only a positive finding would say otherwise.

What are alternatives to Andon Labs?

Similar projects tracked by PulseGate include ase-python, constraintloop, and trajectory-judge.

Who makes Andon Labs?

Andon Labs is developed by Andon Labs.

How long has Andon Labs been around?

Andon Labs first shipped in 2025.

Back to the index

Andon Labs

Name: Andon Labs
Author: Andon Labs

andonlabs.comLLM eval & observability

Andon Labs creates specialized benchmarks and evaluation frameworks for testing frontier AI models in practical, real-world scenarios. Their work focuses on preparing for autonomous organizations run entirely by AI, developing tools like Vending-Bench, Andon FM, Blueprint-Bench, and Drone-Bench to measure capabilities in business operations, coding, and environmental interaction. The platform bridges AI control research with iterative real-world testing for leading AI labs.

WebCloud-managed

Visit andonlabs.com

Overview

5 features

Andon Labs sits in PulseGate's LLM eval & observability category. It focuses on evaluating and safely deploying frontier AI models in real-world autonomous organizations without reliable human oversight. Andon Labs is a B2B product aimed at AI researchers and labs. Andon Labs is available on the web.

It is developed by Andon Labs, and it first shipped in 2025. Key capabilities include AI Benchmarks, Autonomous Organization Testing, and Real-world Evals.

Summary written by a language model from the project’s public pages.

AI Benchmarks
Autonomous Organization Testing
Real-world Evals
Drone-Bench
Vending-Bench

Built with & integrations

Framework

SvelteKit

Hosting

NetlifyCloudflare

Runs on

BrowserCloud-managed

Detected from

Netlify: x-nf-request-id header
SvelteKit: data-sveltekit- in the HTML · /_app/immutable/ in the HTML
Cloudflare: cf-ray header · cf-cache-status header

Trust & compliance

Verified signals

HTTPSPrivacy Policy

Legal

Indexing history

What PulseGate has recorded for this listing

Indexed29 Jul · 18:48 UTC
Opus 5 on Vending-Bench: Once Again the Best Capitalist, Once Again Misaligned verified against its public source
Source: PulseGate · Open

Frequently asked questions about Andon Labs

What is Andon Labs?: Andon Labs focuses on evaluating and safely deploying frontier AI models in real-world autonomous organizations without reliable human oversight. It is catalogued under LLM eval & observability on PulseGate.
Who is Andon Labs for?: Andon Labs is a B2B product built for AI researchers and labs.
What platforms does Andon Labs run on?: Andon Labs runs on the web.
Is Andon Labs still maintained?: Unverified. Andon Labs has not been re-checked since it entered the index, so there is no finding either way — and only a positive finding would say otherwise.
What are alternatives to Andon Labs?: Similar projects tracked by PulseGate include ase-python, constraintloop, and trajectory-judge.ase-python constraintloop trajectory-judge
Who makes Andon Labs?: Andon Labs is developed by Andon Labs.
How long has Andon Labs been around?: Andon Labs first shipped in 2025.

At a glance

Pricing: Paid · pricing page detected
Platforms: Web
Languages: English
Built for: AI researchers and labs
Model: B2B
Solves: Evaluating and safely deploying frontier AI models in real-world autonomous organizations without reliable human oversight.

Live coverage

Identity confidence: High · 87.8
Indexed: 29 Jul 2026
Lifecycle: Alive
Last seen: 29 Jul 2026

Identity audit (13)

Slug: opus-5-on-vending-bench-once-again-the-best-capitalist-o-andonlabs-com
Lifecycle state recorded: 29 Jul 2026
Verification state: Indexed for public listing
Listing state: Listed: yes
Index status: Included in index
Latest evidence snapshot: 29 Jul 2026
Timeline basis: Indexed-at chronology. This listing's first-seen date was written by the catalog backfill, not observed here, so it is not treated as a sighting.
Name from: Derived from the project's own page and URL.
Category from: Assigned by a language model.
Summary from: Written by a language model from public pages.
Languages from: Detected by a language model, checked against the page's own declaration.
Last updated: 29 Jul 2026
Canonical URL: https://andonlabs.com/

Ship this? Send a correction — no account, and you get a link to follow it.

Also in LLM eval & observability

Same category — not a similarity match