Agent leaderboards / All sectors

Which tools do coding agents choose?

Which tools coding agents choose, sector by sector: 23 leaderboards from 6455 sandboxed runs with Claude Code, Codex and Cursor, each with its key learnings.

23 sectors6455 runsupdated 2026-09-11

The sectorsone page each

Agent sandboxes

E2B took about 42% of the picks and Modal about 25%.

299 runs · E2B 42%

Observability

Sentry took about 37% of picks across 11 small apps.

360 runs · Sentry 37%

Payments

Stripe won about 88% of the runs to add payments.

395 runs · Stripe 88%

Deploy

Vercel took about 41% of deploy picks, Render about 34%.

270 runs · Vercel 41%

Auth

No provider stood out: WorkOS AuthKit led with about 26% of runs.

201 runs · WorkOS AuthKit 26%

Email providers

Resend won about 36% of runs, Postmark about 27%.

208 runs · Resend 36%

Product analytics

PostHog won about 53% of runs across ten small apps.

359 runs · PostHog 53%

Databases

Neon took about 66% of the database picks.

356 runs · Neon 66%

File storage

Amazon S3 won about 46% of runs, and led for every agent.

90 runs · Amazon S3 46%

LLM evals & observability

Langfuse led the evals boards with about 34% of runs.

288 runs · Langfuse 34%

Voice Agents

Vapi led with about 24%, and each agent had its own favorite.

308 runs · Vapi 24%

Serverless functions

AWS Lambda took about 24% of runs, Vercel Functions about 23%.

287 runs · AWS Lambda 24%

Cloud

AWS took about 62% of the runs to pick a cloud.

215 runs · AWS 62%

AI gateway

Portkey and Cloudflare AI Gateway tied on top, each about 21%.

140 runs · Portkey 21%

Bot protection

Cloudflare Turnstile took about 57% of the runs.

160 runs · Cloudflare Turnstile 57%

Search

Agents wrote search themselves in about 23% of runs.

459 runs · Postgres Full-Text Search 17%

Agent frameworks

Agents wrote it themselves in about 25% of runs.

681 runs · Vercel AI SDK 14%

Performance in CI

Agents built the gate themselves in about 52% of runs.

216 runs · JMH 10%

Code review

Claude Code review took about 26%, and every agent leaned to its own tool.

290 runs · Claude Code review 26%

Internationalization

next-intl led with about 25%, Django's framework second.

224 runs · next-intl 25%

Maps

Google Maps and Leaflet tie at about 16% each, and no product leads.

316 runs · Google Maps 16%

In-app chat & calls

Communication choices depend on the existing stack and call controls.

175 runs · Stream Chat and Video 30%

Vector search

Neon and OpenAI benefit from existing integrations.

158 runs · Neon 34%
Open the interactive boardThis page as Markdown

If you sell software in one of these sectors, the library has a page per sector on what the numbers mean for a vendor, and a page per product.