PromptLab
A Chrome extension for local-first LLM prompt testing with zero cloud dependencies. Developers can test prompts across OpenAI, Anthropic, and OpenRouter with complete privacy.
🔗 Visit PromptLab
Description
Testing how an AI model responds to different prompt wording usually means either pasting text back and forth into a chat window, or signing up for a hosted playground that stores your prompts and API keys on someone else's server. PromptLab tries to remove that trade-off by putting the whole workflow inside your own browser, with nothing leaving your machine except the direct request to the model provider.
PromptLab is a Chrome sidepanel extension for local-first LLM prompt testing, storing everything in chrome.storage.local with zero telemetry and no cloud dependencies. It connects directly from the browser to OpenAI, Anthropic, and OpenRouter APIs using your own keys, tracks token usage in real time, and holds up to 20 prompt fixtures at once. It's built with React, TypeScript, and Tailwind CSS, and distributed as free, open-source software.
💬 Our review
The short version: PromptLab is a lightweight, privacy-first alternative to hosted prompt playgrounds like the OpenAI Playground or Anthropic's own workbench, trading their polish and team-collaboration features for a tool that never sends anything to a server you don't control.
Hosted playgrounds from the model providers themselves are free, more polished, and support things like prompt versioning and sharing — but by design they run through the provider's own infrastructure, which is exactly the trade-off some developers want to avoid, especially when testing prompts against sensitive or proprietary data. Compared to a general API-testing tool like Postman repurposed for LLM calls, PromptLab is purpose-built for prompt iteration with token tracking baked in, at the cost of being locked to Chrome and to whatever the 20-fixture limit allows. It's a good fit for a solo developer or small team doing quick, private prompt iteration across multiple providers; it's not a replacement for a real prompt-engineering platform with versioning, evals, and team sharing if that's what you actually need.
💰 Pricing
📊 Global score
🤖 AI-enriched data
Open source, gratuit — coût réel = les appels API aux fournisseurs (OpenAI, Anthropic, OpenRouter) avec vos propres clés.
Pros
100% local-first, zéro télémétrie, aucune dépendance cloud
Compatible OpenAI, Anthropic et OpenRouter avec vos propres clés
Suivi de consommation de tokens en temps réel
Gratuit et open source
Panneau latéral Chrome pratique pour itérer rapidement
Cons
Limité à Chrome (extension navigateur, pas d'app native)
Capacité de 20 fixtures de prompts seulement
Pas de versioning ni de partage d'équipe comme sur un vrai playground hébergé