$ buildwith --task "ship a SaaS"
→ editor: Cursor · agent: Claude Code · db: Supabase
→ auth: Clerk · pay: Stripe · deploy: Vercel
What should I build with?
Ranked AI tools for vibe coders and builders. Pick a job, get the shortlist, ship.
$ ls ./categories
AI Code Editors/
IDEs with AI built in, for when you want to stay hands-on with the code.
Coding Agents/
Agents that take a task and do the multi-file work for you.
App Builders/
Describe it, get a working app. Fastest path from idea to URL.
Backend & Database/
Where your data lives. Postgres-first picks that play well with AI tools.
Auth/
Sign-in, users and orgs without rolling your own.
Deploy & Hosting/
Get it live. Git push to production.
Payments/
Take money for the thing you built.
Design & UI/
Make it look good, from mockups to components.
Email/
Transactional and product email for builders.
Agent Ops/
Run, supervise and scale your agents: orchestrators, runtimes and always-on agents.
Context & Indexing/
Hand an agent the right code and docs, cheaply, instead of rereading the whole repo.
$ buildwith --top 1 --all
- #1visit ↗CursorFreemium
use this if you want a VS Code-style editor with AI deeply woven into every edit.
- #1visit ↗Claude CodePaid
use this if you live in the terminal and want an agent that works across your whole repo.
- #1visit ↗LovableFreemium
use this if you're non-technical or want a polished full-stack app from a chat.
- #1visit ↗SupabaseFreemium
use this if you want Postgres plus auth, storage and realtime in one backend.
- #1visit ↗ClerkFreemium
use this if you want drop-in sign-in UI and user management for React/Next.js.
- #1visit ↗VercelFreemium
use this if you're shipping Next.js or any frontend and want git-push deploys with previews.
- #1visit ↗StripeUsage-based
use this if you want the default for payments and subscriptions with great APIs.
- #1visit ↗FigmaFreemium
use this if you want the standard for collaborative UI design and prototyping.
- #1visit ↗ResendFreemium
use this if you want developer-first transactional email with React Email.
- #1visit ↗Hermes AgentFree / OSS
use this if you want an always-on, model-agnostic agent that learns skills over time and lives in your terminal and chat apps.
AI Code Editors
Coding Agents
App Builders
Backend & Database
Auth
Deploy & Hosting
Payments
Design & UI
Agent Ops
$ tail -n 3 ./new
2026-11-21 #
Cline 4.1.27 ↗With no saved model, the Cline provider now starts on the first free model instead of Claude Sonnet 5.5. read_files results are no longer cut to 8k characters (now up to 2,000 lines or about 48k characters), LM Studio gets an API key field, MCP tools declared read-only get a badge, the model catalog adds 94 providers from models.dev, and reasoning-effort fixes stop GPT-6 on Azure and custom gpt-5.6/gpt-6 endpoints from rejecting tool calls.
2026-11-21 #
OpenVorld ↗Free, local, MIT-licensed harness for AI agents shown as a pixel-art village: each project is a "vorld" with named agents, roles and houses, and each agent can run on Claude Code, Codex or any OpenAI-compatible API (OpenRouter, Ollama). Agents act only on goals you give them and ask before touching a folder, command or website, with per-agent permissions ("writs") you can grant or revoke. No account needed. Launched on Product Hunt on Nov 21.
2026-11-20 #
Currents for Claude and Codex ↗Currents, which records every Playwright test run in CI, now has a plugin in the Claude and ChatGPT/Codex directories. Sign in and ask your agent why CI failed: it gets the failure, the test's history across runs and branches, and the trace, plus skills that tell it to fix the cause rather than add retries or timeouts. Works on every Claude plan; Currents has a 14-day free trial.
$ subscribe --weekly
One email a week: new tools worth your time and ranking changes. No spam.