⌨️ Vibe coding
Ship apps by describing them. Editors, agents, and prompt-to-app builders.
Cursor
AI code editor with agents that work across your whole repo.
Best when you already have code and want an agent that edits many files, runs commands, and keeps context.
BEST FOR: BUILDERS WHO READ CODEFree plan · paid tiers
Claude Code
Terminal-first coding agent from Anthropic.
Strong at long, multi-step changes from the command line. Pairs well with any editor.
BEST FOR: TERMINAL PEOPLENeeds a paid Claude plan or API
Codex
OpenAI's coding agent for CLI, IDE, and cloud tasks.
Hand off a task, let it run in the background, and review the diff.
BEST FOR: PARALLEL BACKGROUND TASKSIncluded with ChatGPT plans · check site
Lovable
Prompt-to-app builder with hosting and a database baked in.
Fastest path from idea to a working, shareable web app if you never want to see a terminal.
BEST FOR: NON-CODERS SHIPPING MVPSFree plan · paid tiers
Bolt.new
Full-stack apps in the browser from a prompt.
Instant in-browser dev environment. Great for prototypes and demos.
BEST FOR: QUICK PROTOTYPESFree plan · paid tiers
v0
Vercel's app and UI builder.
Clean React/Next.js UI that deploys straight to Vercel.
BEST FOR: FRONTEND + NEXT.JSFree plan · paid tiers
New in vibe coding this week
Recursive Flint: The first model from Richard Socher's Recursive: a free, Apache 2.0 coding model that runs on a laptop. It's a mixture-of-experts with 40B parameters but only 2.5B active, so it clocked about 131 tokens a second on an M4 Pro MacBook Pro, roughly twice similar models. It beats other sub-50B models on SWE-Bench Verified, and the company says its automated research system helped build almost every part of it. Weights are on Hugging Face. Recursive admits it needs more hand-holding than the big paid agents, so break big tasks into smaller steps. source ↗
Ornith-1.5-122B: An MIT-licensed 122B mixture-of-experts model, built on Qwen3.5 and Gemma4 and then trained with a self-improvement loop that writes its own practice tasks. It has a 262K context, serves on a single 80 GB GPU through vLLM or SGLang, and comes in FP8, GGUF, and MLX builds, plus a quantized mobile variant. source ↗
buddylist: A free desktop app for Mac (Apple Silicon), Windows, and Linux that puts Claude Code, Codex, Gemini, and OpenCode in an MSN-style buddy list. Give each agent its own Git worktree, or drop several into one group chat on a shared folder so they take turns or hand off unfinished work. Diffs, terminals, app preview, and PR checks sit beside the chat. Bring your own agent accounts. source ↗
MiniMax M3.1 Flash: MiniMax unmasked "Space Bunny," the stealth model that sat at the top of OpenRouter, as an early build of M3.1 Flash. It's a fast, cheap agent and coding model with a 1M-token context that reads text, images, and video. It's $0.15 in and $0.60 out per million tokens, free on OpenRouter for the first 72 hours, and open weights are promised for Oct 23. source ↗
DeepSeek V4.1 Flash (1017 update): DeepSeek pushed a fresh snapshot of its cheap, fast open model and swapped it into its app, site, and API. Open weights, MIT license, with better coding and agent benchmark scores than the last Flash. source ↗
Reflection AI Beam: A big open-weight model aimed at coding and long agent runs, with a 1M-token context window and day-one support in Ollama and vLLM. It ships alongside Mirror, an open-source agent harness. source ↗
Rankings are editorial and can't be bought. Sponsored placements are always labeled. How we rank →