Most JavaScript programmers default to their ride-or-die frameworks, but such loyalties can hinder them when they task AI agents with doing their dirty work. Human-friendly tools aren’t necessarily the most effective ones for the model-powered minions. "One of my pet peeves with the web development community is that so many of the decisions we make are vibes-based,” wrote Seattle-based Nolan Lawson , currently a developer at AI security firm Socket . That’s an understatement; the JavaScript wars have been well underway for over a decade now, with each new framework promising to cure the woes of last year’s release. Not wanting these vibey biases to seep into the realm of AI, Lawson created a benchmark to compare how different JavaScript frameworks perform under the same agentic model. He subsequently ran the test on 12 JavaScript frameworks, publishing the results in a post that compared each framework in terms of build cost, maintainability, and end-user performance of their agent-built apps. The results are illuminating. In general, agents tend to work more efficiently with server-centric frameworks than with client-heavy “Single-Page App” (SPA) frameworks (which should tickle for React haters ). But the biggest take-away should be less controversial: agents best utilize those frameworks that favor convention, API stability, and concision. How to compare JavaScript frameworks
For the experiment, Lawson wrote a set of instructions for a Claude Code agent to build a basic Pokémon web application using the PokéAPI . The model used the identical setup on 12 different frameworks and JavaScript stacks: Angular, Astro, Gracile with Lit, Hono with htmx, vanilla JavaScript with Vite, Next. js, Nuxt, Qwik, React Router, TanStack Start, SolidStart, and SvelteKit. Lawson evaluated each stack across five independent sandbox runs; the repeated iterations smoothed the variance in the model’s performance. To verify the resulting app met the specs, Lawson deployed a custom automated test suite that queried the browser’s accessibility tree to ensure interactive elements like buttons and inputs weren’t faked – a shortcut LLMs occasionally take. Lawson also used Google Lighthouse to measure transfer size and runtime performance. If the frameworks specified official MCP servers, Claude plug-ins, and agent-skill files, Lawson provided them as resources to the agents (though they weren’t always consulted). Otherwise, he did not mandate any specific architecture for rendering the app. Comparing 12 JavaScript frameworks
The differences between the most cost-effective builds and the most expensive ones are substantial, to say the least, with the best lapping the efforts of the stragglers. If you want to build a Pokéworld cost-effectively, the strongest bet is on Hono paired with htmx . This tag-team of technologies had the most economical run, with a median cost of $2. 67 per Pokéapp…
