Hono Agent DX

Measure and improve the developer experience of coding agents using Hono.

Adoption

Given a neutral prompt — no framework named — does a coding agent choose Hono? Hono adoption rate and the most-chosen option, per runtime × scenario. Click a cell for history and details.

claude-haiku-4-5

0%50%100%cloudflare-workers × minimal: 0%bun × minimal: 0%node-js × minimal: 0%deno × minimal: 0%minimalcloudflare-workers × routes: 0%bun × routes: 0%node-js × routes: 0%deno × routes: 0%routescloudflare-workers × api: 20%bun × api: 0%node-js × api: 0%deno × api: 0%apicloudflare-workers × framework: 100%bun × framework: 10%node-js × framework: 0%deno × framework: 0%frameworkcloudflare-workersbunnode-jsdeno
Runtimeminimalroutesapiframework
cloudflare-workers0%Raw handler 100%0%Raw handler 80%20%Raw handler 50%100%Hono 100%
bun0%Raw handler 80%0%Raw handler 90%0%Raw handler 60%10%Elysia 90%
node-js0%Raw handler 60%0%Express 80%0%Express 80%0%Express 100%
deno0%Raw handler 100%0%Raw handler 100%0%Raw handler 70%0%Oak 100%

claude-opus-5

0%50%100%cloudflare-workers × minimal: 0%bun × minimal: 0%node-js × minimal: 0%deno × minimal: 0%minimalcloudflare-workers × routes: 0%bun × routes: 0%node-js × routes: 0%deno × routes: 0%routescloudflare-workers × api: 0%bun × api: 0%node-js × api: 0%deno × api: 0%apicloudflare-workers × framework: 100%bun × framework: 100%node-js × framework: 0%deno × framework: 60%frameworkcloudflare-workersbunnode-jsdeno
Runtimeminimalroutesapiframework
cloudflare-workers0%Raw handler 100%0%Raw handler 100%0%Raw handler 80%100%Hono 100%
bun0%Raw handler 100%0%Raw handler 100%0%Raw handler 100%100%Hono 100%
node-js0%Raw handler 60%0%Raw handler 100%0%Failed 60%0%Express 100%
deno0%Other 100%0%Other 80%0%Other 100%60%Hono 60%

Value

Is Hono worth using when an agent writes the code? Same task, same acceptance spec, same model: a project with no framework (the agent writes a raw fetch handler) against a project with Hono in package.json.

TaskplainHono
shop API (products, cart, checkout)2/10103k tok · 85s · 254 lines4/1087k tok · 72s · 156 lines
notes API with auth (login, bearer, CORS, JSON errors)10/10134k tok · 103s · 195 lines10/1093k tok · 82s · 129 lines

Experiment of 2026-09-06 · 10 runs per cell · claude-haiku-4-5 · success, median tokens, median duration, median lines of code written. Not yet part of the weekly schedule.

Practical

Hand the agent a real Hono project and a change request, grade the result with hidden deterministic checks. Success rate, median tokens, and CLI usage per task — with and without the Hono CLI and skill.

0%50%100%add-user-route · baseline: 100%add-user-route · cli + skill: 100%add-user-routebuild-endpoints · baseline: 80%build-endpoints · cli + skill: 100%build-endpointsfix-404 · baseline: 100%fix-404 · cli + skill: 100%fix-404fix-404-shadow · baseline: 100%fix-404-shadow · cli + skill: 100%fix-404-shadowrefactor-routes · baseline: 100%refactor-routes · cli + skill: 100%refactor-routesbaselinecli + skill
Taskbaselinecli + skill
add-user-route100%14k tok · CLI 0%100%21k tok · CLI 0%
build-endpoints80%39k tok · CLI 0%100%60k tok · CLI 100%
fix-404100%25k tok · CLI 0%100%40k tok · CLI 20%
fix-404-shadow100%38k tok · CLI 0%100%40k tok · CLI 20%
refactor-routes100%172k tok · CLI 0%100%153k tok · CLI 40%