The directory for
vibe-coded things.
Browse apps, games, agents, MCP servers, browser extensions, and tools built with AI. Submit yours and get a public indexed page with a screenshot and outgoing link.
Free review in 3-7 days, or $10 instant publishing.
Latest directory entries.
Apps, agents, MCP servers, extensions, and products people ship with AI. User-submitted entries land here first after review.
- 01
→Atlas by World Labs
Turn text, pics, video, + 3D into camera-controlled HD video
Newweb - 02
→Omi
Ask your computer anything you saw or heard
Newweb - 03
→MagiCrew
Give everyone their own AI workforce in one platform
Newweb - 04
→Agent Builder by Airtop
Build agents that heal themselves.
Newweb - 05
→Nex
Claude Cowork for high-volume GTM workflows
Newweb - 06
→Stitch AI by Dynamic Mockups
The first embroidery digitizing agent
New
From the blog.
Playbooks for shipping and growing what you build with AI — plus side-by-side tool alternatives drawn from the directory.
- Maker Playbook
Vercel vs Netlify
Both rebuilt their pricing this year, and the old comparison is out of date. Vercel's free tier bans commercial use outright — a paid app breaks the rules on day one. Netlify's free tier gives you credits that a redeploy-happy AI workflow burns in about twenty production deploys. Here's what each actually costs, where the AI builders really deploy, and when Cloudflare quietly wins.
- Maker Playbook
Best Local LLMs for Vibe Coding (2026)
Yes — for the first time, honestly. The new 30–35B mixture-of-experts class (Qwen3.6, Qwen3-Coder, GLM-4.7-Flash, gpt-oss-20b) scores 59–73% on SWE-bench Verified, fits on real hardware, and every major agent harness — including Claude Code — now connects to a local server through an officially documented path. Here are the models by hardware tier, the apps that run them, and the honest ceiling where local still breaks.
- Maker Playbook
DeepSeek vs Claude for Vibe Coding (2026)
For vibe coding, Claude is still the stronger agent brain and DeepSeek is a shockingly capable one at a fraction of the price — but the comparison everyone writes is about chat, and the interesting answer isn't either/or. DeepSeek officially documents running inside Claude Code, which turns this from a rivalry into a stack: Claude plans and reviews, DeepSeek executes. Here's the setup, the honest numbers, and when mixing isn't worth it.
- Maker Playbook
Is Claude Max Worth It in 2026? The Real Cost Math — and When a Cheap-Model Stack Beats It
If you run Claude Code daily and keep hitting Pro's limits, Max is one of the best-subsidized deals in AI — community math puts its API-equivalent value at multiples of the $100–200 price. But the same math cuts the other way: most agent tasks don't deserve a premium model at all, and the same workload can cost $7 on a cheap model or $1,190 on the most expensive one. Here's the arithmetic, from the official price sheets.
- Maker Playbook
Supabase vs Firebase
For most vibe-coded web apps in 2026, pick Supabase: it's Postgres, it's what Lovable and Bolt wire in natively, and its open-source core leaves you an exit. Firebase still wins for mobile-first apps that need offline sync and Google's ecosystem — but its free tier lost storage, and its vibe-coding IDE is shutting down. Here's the honest head-to-head.
- Maker Playbook
AI Agent Frameworks
There are 200-plus AI agent frameworks and the listicles rank them like a leaderboard. That's the wrong lens. Underneath the branding they come in three shapes — a loop, a graph, or a crew — and the shape is what you're actually choosing. Here's each framework builders reach for in 2026, sorted by shape, with the exact command to start and the honest catch for each.
Vibe coding stack.
Editors, agents, app builders, and model-connected developer tools. This is the reference shelf, separate from submitted things.
By category
15 live categories- 3 →AI Code Editors
Desktop IDEs built around AI — Cursor, Windsurf, and forks that ship inline edits, multi-file refactors, and agent modes by default.
- 115 →AI Coding Agents
Autonomous agents that write, edit, run, and review code. Includes CLI agents, agentic IDE add-ons, and code-review bots.
- 7 →Code Completion
Inline AI suggestion extensions for existing IDEs — Copilot-style autocomplete, low-latency model servers, BYOK.
- 9 →AI App Builders
Natural-language-to-app platforms. Type a prompt, get a full-stack app with live preview and one-click deploy.
- 11 →No-code Builders
Visual drag-and-drop builders with AI assistance. Apps run on the vendor's platform; source is rarely exposed.
- 10 →MCP Servers
Implementations of the Model Context Protocol — file, database, API, and browser servers that LLM clients can plug into.
- 1 →AI Games
Games built with AI — browser games, AI-driven NPCs, procedurally generated worlds, and indie titles shipped by vibe-coders.
- 108 →AI Web Apps
Web apps with AI baked in — built for everything from journaling to research. Submitter-shipped products live here.
- 107 →AI Productivity
AI-powered task trackers, calendars, note tools, and meeting assistants. Helps you do more with less context-switching.
- 44 →AI Writing & Content
AI-assisted writing — long-form drafts, copywriting, ghostwriting, translation, and AI-aware editors.
- 20 →AI Image Generation
Text-to-image, image-to-image, inpainting, character LoRAs, and AI-enhanced editing tools.
- 18 →AI Video & Voice
AI video generation, lip-sync, voice cloning, podcast editing, and music synthesis.
- 4 →AI Chatbots & Assistants
Custom GPTs, Claude apps, niche assistants — chat interfaces aimed at a specific user, topic, or workflow.
- 23 →Browser Extensions
AI-powered Chrome, Arc, Edge, Firefox, and Safari extensions — overlays, sidebars, content augmentation.
- 20 →Mobile Apps
iOS and Android apps with AI as the core feature, not a sprinkled-on extra.
Built with AI? Show it here.
Drop a link. We screenshot your homepage, review free submissions, and offer a $10 instant path when you want the page live right away.
The vocabulary
Vibe coding has its own vocabulary — agents, MCP servers, context windows, hallucinations. Each entry is two sentences a model can quote, plus 150 more for humans.
Read all 50 terms →- Agentic codingA development style centred on coding agents — the human describes intent, the agent plans and executes the work, and the human reviews diffs or PRs rather than authoring code line by line. The umbrella term for vibe coding and adjacent practices.
- AI agentAn LLM-powered program that pursues a goal over multiple steps by calling tools, observing results, and replanning. Agents differ from single-turn chatbots in that they can take real actions (run shell commands, edit files, hit APIs) and iterate without human intervention between steps.
- AI OverviewGoogle Search's generative answer block that sits above the classic blue-link results. Powered by Gemini, it summarises top sources and links out to them. The biggest single AEO/GEO citation surface as of 2026.
- Autonomous codingLong-horizon, unattended coding sessions where an agent works for minutes or hours without human approval at each step. Contrasts with approval-gated modes where the user confirms each shell command or file edit.
- Chain of thoughtAsking an LLM to spell out intermediate reasoning steps before producing the final answer. Improves accuracy on multi-step problems by ~10-30 percentage points on most reasoning benchmarks.
- CitationWhen a generative-search system attributes part of its answer to a specific source URL, usually with a footnote-style number or an inline link. The visible signal that a brand was used to ground a model's answer.