# VibeShelf

> Curated directory of AI tools and agents for vibe coders and builders, organized by use case. Sponsored placements are labeled. Every tool has its own page at /tool/<slug>/.

## Key pages

- [Vibe coding tools](https://vibeshelf.co/vibe-coding-tools/): app builders, coding agents, agent frameworks and builder infra
- [Free AI tools](https://vibeshelf.co/free-ai-tools/): tools that are free or have a free plan
- [Alternatives guides](https://vibeshelf.co/alternatives/): Cursor, GitHub Copilot, Claude Code, Devin Desktop, Lovable, Bolt.new, v0, Replit, ChatGPT, Perplexity, Midjourney, Runway, ElevenLabs, Zapier, Notion AI, Grammarly, Jasper, Gamma
- [Submit a tool](https://vibeshelf.co/submit/): free editorial listing
- [VibeShelf on X](https://x.com/VibeShelfco): @VibeShelfco, new tool launches and updates
- [Get featured](https://vibeshelf.co/featured/): pricing. Basic listing free; Fast-track $29 one-time (live within 48 hours, Verified badge); Featured $49/month founding price for the first 10 sponsors (regular $79/month, cancel anytime; top of homepage and category, Featured badge)

## New this week (week of Nov 2, 2026)

- [OpenAI Codex](https://openai.com/codex/) (2026-11-01): OpenAI says that starting in December, Plus, Pro and Business plans will share one usage allowance across ChatGPT and Codex, measured in tokens, as it brings the agentic features of Work into the main ChatGPT experience. Heavier models and complex tasks use more of the allowance; Instant chat doesn't count. Combined usage and reset times will show in Settings → Usage, and at the limit you can wait, upgrade or buy credits. OpenAI emailed subscribers about the change on November 1.
- [Claude Code](https://claude.com/product/claude-code) (2026-10-30): Claude Code v2.1.316 adds CLAUDE_CODE_SUBAGENT_EFFORT, so subagents that only search and read files can run at a lower effort level than your main session, plus a switch to turn off the ultrathink keyword. Fast mode for Opus 4.8 is deprecated and will be removed on November 30, 2026; after that those requests return an error, so move to Opus 5.5 to keep the speedup.
- [Cursor](https://cursor.com) (2026-10-29): Security notice: a tampered copy of the Claude Code extension (Anthropic.claude-code 2.1.312 and 2.1.313, macOS and Windows) was served from Cursor's extension marketplace for about 11 hours on October 29 and tried to install an SSH backdoor. Cursor says at most 5,000 users were affected, removed it, rebuilt the marketplace and took the attacker's server offline. If you installed or updated it in that window, follow Cursor's check-and-remediation steps; uninstalling alone may not remove it.
- [Bolt.new](https://bolt.new) (2026-10-30): Starting October 30, new Bolt database tables are private by default, so an app needs explicit permissions to read or write them. Bolt sets up the permissions when it creates a database; existing databases are not affected, and you can ask Bolt to fix table permissions if you see an error.
- [Lovable](https://lovable.dev) (2026-10-29): Lovable can now import apps built in Replit, Bolt, v0, Base44 and Manus, or any ZIP of code up to 250 MB. It rebuilds the app as a Lovable project and moves the database and users to its built-in backend (passwords and sessions don't carry over). A separate import rebuilds a site you own from its public URL. The first build of your first import is free.
- [Factory Droid](https://factory.com) (2026-10-29): Factory released Droid 1.0, the biggest update yet to its enterprise coding-agent harness. A new programmatic tool-calling engine lets models run hundreds of tool calls in a single request, and Factory says Droid beats the native harnesses built for their models while using up to 20% fewer resources. It ships as a desktop app for macOS and Windows, a terminal UI, and the @factory/droid-sdk for building on the same harness.
- [Zed](https://zed.dev) (2026-10-28): Zed 1.26.2 adds Pyrefly as an optional built-in Python language server, expandable variable trees in debugger hovers, and DWARF debugging for WebAssembly in the JavaScript debugger. For AI, ACP agent defaults now apply only to new conversations, model and option pickers get better fuzzy search, and fixes cover hangs restoring agent threads with subagents and duplicated thinking text from OpenAI-compatible providers.
- [GitHub Copilot](https://github.com/features/copilot) (2026-10-28): At GitHub Universe, GitHub made Copilot Fusion generally available: instead of picking a model, you pick Fusion and an effort level (Standard, High or Max) and Copilot routes each task to one model or chains several to draft, review and revise. GitHub says Fusion Max scored within two points of Claude Code with Opus 5.5 Max on the Artificial Analysis Coding Agent Index at about half the cost. It is on all Copilot plans in VS Code, the Copilot app, CLI and JetBrains.
- [Replit](https://replit.com) (2026-10-27): Replit Cloud Agents let people outside engineering, like designers or support leads, turn a plain-language request into a tested change to the company codebase. Each change is tested in the running app and engineers approve what ships. Available now for Pro and Enterprise customers.
- [Paradev](https://paradev.com) (2026-10-26): Superset, the workspace for running many coding agents in parallel in isolated Git worktrees, renamed itself Paradev and announced an $11.5M seed led by Union Square Ventures. Accounts, links and the superset CLI carry over; the repo moves to github.com/paradevai/paradev.
- [Entire](https://entire.com) (2026-10-26): Former GitHub CEO Thomas Dohmke launched Entire, a Git forge built for agents and humans: Trails replace pull requests with custom evals scored by agents on every push, Continuous Memory syncs agent sessions into the repo, and Git hosting runs in US, EU, India and Australia regions. The platform is free; agent runs use prepaid token credits, with a $100 trial.

## Coding

- [Cursor](https://cursor.com): AI-first code editor with agentic edits, tab completion and codebase chat. (freemium; page: https://vibeshelf.co/tool/cursor/)
- [GitHub Copilot](https://github.com/features/copilot): AI pair programmer for code completion, chat and agent mode in your IDE. (freemium; page: https://vibeshelf.co/tool/github-copilot/)
- [Claude Code](https://claude.com/product/claude-code): Anthropic's terminal-based agentic coding tool. (paid; page: https://vibeshelf.co/tool/claude-code/)
- [OpenAI Codex](https://openai.com/codex/): OpenAI's coding agent for the CLI, IDE and cloud tasks. (paid; page: https://vibeshelf.co/tool/openai-codex/)
- [Devin Desktop](https://devin.ai/desktop): Formerly Windsurf: AI IDE with an agent command center for managing local and cloud coding agents. (freemium; page: https://vibeshelf.co/tool/devin-desktop/)
- [Zed](https://zed.dev): High-performance code editor with built-in AI assistance. (freemium; page: https://vibeshelf.co/tool/zed/)
- [Cline](https://cline.bot): Open-source autonomous coding agent for VS Code. (free; page: https://vibeshelf.co/tool/cline/)
- [Aider](https://aider.chat): Open-source AI pair programming in your terminal. (free; page: https://vibeshelf.co/tool/aider/)
- [Tabnine](https://docs.tabnine.com/main): Enterprise AI coding platform with private and air-gapped deployment, now owned by Tricentis; no longer onboards individual users. (paid; page: https://vibeshelf.co/tool/tabnine/)
- [Amp](https://ampcode.com): Coding agent and dev environment that runs unattended in cloud "orbs" or locally via CLI. (paid; page: https://vibeshelf.co/tool/amp/)
- [Gemini CLI](https://github.com/google-gemini/gemini-cli): Google's open-source AI agent for the terminal. (free; page: https://vibeshelf.co/tool/gemini-cli/)
- [Muse Code](https://dev.meta.ai/products/muse-code): Meta's terminal coding agent that fans big jobs out to parallel sub-agents in isolated worktrees. (paid; page: https://vibeshelf.co/tool/muse-code/)
- [Beacon](https://beacon.sh): Open-source (MIT), local-first memory layer for coding agents: captures sessions from Claude Code, Cursor, Codex, OpenCode and 20+ harnesses and turns proven fixes into reusable skills via MCP or Agent Skills. (free; page: https://vibeshelf.co/tool/beacon/)
- [ThinkRail](https://thinkrail.ai): Free, open-source agentic IDE from JetBrains built around the pi coding agent, with isolated git-worktree workspaces and living SPEC.md files. (free; page: https://vibeshelf.co/tool/thinkrail/)
- [Entire](https://entire.com): Git forge built for coding agents: Trails replace pull requests with agent-scored evals, plus shared agent memory and fast distributed Git hosting. (freemium; page: https://vibeshelf.co/tool/entire/)
- [Paradev](https://paradev.com): Workspace for running many coding agents in parallel (Claude Code, Codex, OpenCode and more), each in its own Git worktree, with diff review, scheduled automations, remote hosts and an iPhone app. Formerly Superset. (freemium; page: https://vibeshelf.co/tool/paradev/)
- [Factory Droid](https://factory.com): Factory's enterprise coding agent: Droid runs as a desktop app, terminal UI and SDK, with a programmatic tool-calling engine for long, multi-step tasks. (paid; page: https://vibeshelf.co/tool/factory-droid/)

## App builders

- [v0](https://v0.app): Vercel's AI app and UI builder that generates React/Next.js. (freemium; page: https://vibeshelf.co/tool/v0/)
- [Lovable](https://lovable.dev): Build full-stack web apps by chatting with AI. (freemium; page: https://vibeshelf.co/tool/lovable/)
- [Bolt.new](https://bolt.new): Prompt, run, edit and deploy full-stack apps in the browser. (freemium; page: https://vibeshelf.co/tool/bolt-new/)
- [Replit](https://replit.com): Browser IDE with Replit Agent that builds and deploys apps. (freemium; page: https://vibeshelf.co/tool/replit/)
- [Attie](https://attie.ai): Bluesky's AI site builder for social vibe coding: polls, games, guestbooks and small apps with shareable attie.site links. (freemium; page: https://vibeshelf.co/tool/attie/)
- [Firebase Studio](https://firebase.studio): Google's AI workspace for prototyping and building full-stack apps. (freemium; page: https://vibeshelf.co/tool/firebase-studio/)
- [Base44](https://base44.com): No-code AI app builder with built-in backend. (freemium; page: https://vibeshelf.co/tool/base44/)

## Agents & frameworks

- [Devin](https://devin.ai): Autonomous AI software engineer from Cognition. (paid; page: https://vibeshelf.co/tool/devin/)
- [Manus](https://manus.im): General-purpose AI agent that executes multi-step tasks, now with Team and Enterprise plans. (freemium; page: https://vibeshelf.co/tool/manus/)
- [CrewAI](https://www.crewai.com): Framework and platform for orchestrating multi-agent systems. (freemium; page: https://vibeshelf.co/tool/crewai/)
- [LangChain](https://www.langchain.com): Framework for building LLM apps and agents, plus LangGraph and LangSmith. (freemium; page: https://vibeshelf.co/tool/langchain/)
- [AutoGen](https://github.com/microsoft/autogen): Microsoft's open-source framework for multi-agent AI apps. (free; page: https://vibeshelf.co/tool/autogen/)
- [OpenAI Agents SDK](https://openai.github.io/openai-agents-python/): Lightweight Python SDK for building agentic apps. (free; page: https://vibeshelf.co/tool/openai-agents-sdk/)
- [Browser Use](https://browser-use.com): Open-source library that lets AI agents control a web browser. (freemium; page: https://vibeshelf.co/tool/browser-use/)
- [Hugging Face](https://huggingface.co): Hub for open models, datasets and Spaces demos. (freemium; page: https://vibeshelf.co/tool/hugging-face/)

## Assistants

- [ChatGPT](https://chatgpt.com): OpenAI's general AI assistant. (freemium; page: https://vibeshelf.co/tool/chatgpt/)
- [Claude](https://claude.ai): Anthropic's AI assistant for writing, analysis and code. (freemium; page: https://vibeshelf.co/tool/claude/)
- [Gemini](https://gemini.google.com): Google's AI assistant, now running Gemini 4 Argon for Pro and Ultra subscribers. (freemium; page: https://vibeshelf.co/tool/gemini/)
- [Grok](https://grok.com): xAI's AI assistant with real-time X data. (freemium; page: https://vibeshelf.co/tool/grok/)
- [Microsoft Copilot](https://copilot.microsoft.com): Microsoft's AI assistant across the web and Windows. (freemium; page: https://vibeshelf.co/tool/microsoft-copilot/)
- [Le Chat](https://chat.mistral.ai): Mistral AI's assistant. (freemium; page: https://vibeshelf.co/tool/le-chat/)
- [Kimi](https://www.kimi.ai): Moonshot AI's assistant and open-weight Kimi models, with a 1M-token context, Kimi Code for coding and a pay-as-you-go API. (freemium; page: https://vibeshelf.co/tool/kimi/)

## Writing

- [Jasper](https://www.jasper.ai): AI content platform for marketing teams. (paid; page: https://vibeshelf.co/tool/jasper/)
- [Grammarly](https://www.grammarly.com): AI writing assistant for grammar, tone and rewriting. (freemium; page: https://vibeshelf.co/tool/grammarly/)
- [Copy.ai](https://www.copy.ai): AI platform for go-to-market content and workflows. (freemium; page: https://vibeshelf.co/tool/copy-ai/)
- [Writesonic](https://writesonic.com): AI writer and SEO content tool. (freemium; page: https://vibeshelf.co/tool/writesonic/)
- [QuillBot](https://quillbot.com): Paraphrasing, summarizing and grammar tool. (freemium; page: https://vibeshelf.co/tool/quillbot/)
- [Sudowrite](https://www.sudowrite.com): AI writing partner for fiction authors. (paid; page: https://vibeshelf.co/tool/sudowrite/)

## Image & design

- [Midjourney](https://www.midjourney.com): High-quality AI image generation. (paid; page: https://vibeshelf.co/tool/midjourney/)
- [Ideogram](https://ideogram.ai): AI image generator known for accurate text in images. (freemium; page: https://vibeshelf.co/tool/ideogram/)
- [Leonardo.Ai](https://leonardo.ai): AI image and video generation for creators. (freemium; page: https://vibeshelf.co/tool/leonardo-ai/)
- [Adobe Firefly](https://firefly.adobe.com): Adobe's generative AI for images, video and design. (freemium; page: https://vibeshelf.co/tool/adobe-firefly/)
- [Krea](https://www.krea.ai): Real-time AI image and video generation and enhancement. (freemium; page: https://vibeshelf.co/tool/krea/)
- [Recraft](https://www.recraft.ai): AI design tool for vector art, icons and brand images. (freemium; page: https://vibeshelf.co/tool/recraft/)
- [Canva](https://www.canva.com): Design platform with Magic Studio AI tools. (freemium; page: https://vibeshelf.co/tool/canva/)

## Video

- [Runway](https://runway.com): AI video generation and editing (Gen-4). (freemium; page: https://vibeshelf.co/tool/runway/)
- [Pika](https://pika.art): AI video generator and effects. (freemium; page: https://vibeshelf.co/tool/pika/)
- [Luma Dream Machine](https://lumalabs.ai): AI video generation from Luma AI. (freemium; page: https://vibeshelf.co/tool/luma-dream-machine/)
- [Synthesia](https://www.synthesia.io): AI avatar videos from text. (paid; page: https://vibeshelf.co/tool/synthesia/)
- [HeyGen](https://www.heygen.com): AI avatars, video translation and lip-sync. (freemium; page: https://vibeshelf.co/tool/heygen/)
- [Descript](https://www.descript.com): Edit video and podcasts by editing the transcript. (freemium; page: https://vibeshelf.co/tool/descript/)
- [CapCut](https://www.capcut.com): Video editor with AI captions and effects. (freemium; page: https://vibeshelf.co/tool/capcut/)
- [Kling AI](https://kling.ai): Text- and image-to-video generation from Kuaishou. (freemium; page: https://vibeshelf.co/tool/kling-ai/)
- [Higgsfield](https://higgsfield.ai): AI creative suite for video, image and voice, with an agent that automates longer video workflows. (freemium; page: https://vibeshelf.co/tool/higgsfield/)

## Voice & audio

- [ElevenLabs](https://elevenlabs.io): Realistic AI voices, voice cloning and dubbing. (freemium; page: https://vibeshelf.co/tool/elevenlabs/)
- [Suno](https://suno.com): Generate full songs with vocals from a prompt. (freemium; page: https://vibeshelf.co/tool/suno/)
- [Udio](https://www.udio.com): AI music generation. (freemium; page: https://vibeshelf.co/tool/udio/)
- [Otter.ai](https://otter.ai): AI meeting notes and transcription. (freemium; page: https://vibeshelf.co/tool/otter-ai/)
- [Wispr Flow](https://wisprflow.ai): Voice dictation that writes cleanly in any app. (freemium; page: https://vibeshelf.co/tool/wispr-flow/)
- [Vapi](https://vapi.ai): Platform for building voice AI agents. (paid; page: https://vibeshelf.co/tool/vapi/)

## Research

- [Perplexity](https://www.perplexity.ai): AI answer engine with cited sources. (freemium; page: https://vibeshelf.co/tool/perplexity/)
- [Gemini Notebook](https://notebook.google.com): Formerly NotebookLM: source-grounded research notebooks that answer from your documents and can run code. (free; page: https://vibeshelf.co/tool/gemini-notebook/)
- [Elicit](https://elicit.com): AI research assistant for academic papers. (freemium; page: https://vibeshelf.co/tool/elicit/)
- [Consensus](https://consensus.app): AI search engine for scientific research. (freemium; page: https://vibeshelf.co/tool/consensus/)
- [Exa](https://exa.ai): Search API built for AI apps and agents. (freemium; page: https://vibeshelf.co/tool/exa/)

## Productivity

- [Notion AI](https://www.notion.com/product/ai): AI built into Notion docs, wikis and projects. (paid; page: https://vibeshelf.co/tool/notion-ai/)
- [Gamma](https://gamma.app): AI presentations, docs and websites. (freemium; page: https://vibeshelf.co/tool/gamma/)
- [Granola](https://www.granola.ai): AI notepad for meetings. (freemium; page: https://vibeshelf.co/tool/granola/)
- [Fathom](https://www.fathom.ai): Free AI meeting recorder and summaries. (freemium; page: https://vibeshelf.co/tool/fathom/)
- [Superhuman](https://superhuman.com): Fast email client with AI features. (paid; page: https://vibeshelf.co/tool/superhuman/)
- [Raycast](https://www.raycast.com): Mac launcher with built-in AI. (freemium; page: https://vibeshelf.co/tool/raycast/)

## Automation

- [Zapier](https://zapier.com): No-code automation with AI agents and workflows. (freemium; page: https://vibeshelf.co/tool/zapier/)
- [Make](https://www.make.com): Visual automation platform with AI agents. (freemium; page: https://vibeshelf.co/tool/make/)
- [n8n](https://n8n.io): Fair-code workflow automation with AI nodes. (freemium; page: https://vibeshelf.co/tool/n8n/)
- [Lindy](https://www.lindy.ai): Build AI agents that automate business tasks. (freemium; page: https://vibeshelf.co/tool/lindy/)
- [Relevance AI](https://relevanceai.com): Build and deploy AI agent teams. (freemium; page: https://vibeshelf.co/tool/relevance-ai/)

## Builder infra

- [OpenRouter](https://openrouter.ai): One API for hundreds of LLMs. (freemium; page: https://vibeshelf.co/tool/openrouter/)
- [Vercel AI SDK](https://ai-sdk.dev): TypeScript toolkit for building AI apps. (free; page: https://vibeshelf.co/tool/vercel-ai-sdk/)
- [Supabase](https://supabase.com): Postgres backend with auth, storage and vector search. (freemium; page: https://vibeshelf.co/tool/supabase/)
- [Ollama](https://ollama.com): Run open LLMs locally. (free; page: https://vibeshelf.co/tool/ollama/)
- [LM Studio](https://lmstudio.ai): Desktop app to run local LLMs. (free; page: https://vibeshelf.co/tool/lm-studio/)
- [Pinecone](https://www.pinecone.io): Managed vector database. (freemium; page: https://vibeshelf.co/tool/pinecone/)
- [Modal](https://modal.com): Serverless GPUs and compute for AI. (freemium; page: https://vibeshelf.co/tool/modal/)
- [Replicate](https://replicate.com): Run open models via API. (paid; page: https://vibeshelf.co/tool/replicate/)
- [Groq](https://groq.com): Fast LLM inference on LPUs. (freemium; page: https://vibeshelf.co/tool/groq/)
- [Firecrawl](https://www.firecrawl.dev): Turn websites into LLM-ready data. (freemium; page: https://vibeshelf.co/tool/firecrawl/)
- [Reflection](https://reflection.ai): Open-weight Beam model (Apache 2.0) for coding, reasoning and long-running agents, via API or self-hosted. (freemium; page: https://vibeshelf.co/tool/reflection/)
- [DeepSeek](https://www.deepseek.com): Open-weight V4.1 models with a low-cost OpenAI/Anthropic-compatible API, plus web Search and Fetch APIs for agents. (freemium; page: https://vibeshelf.co/tool/deepseek/)
- [Flint](https://recursive.com/updates/introducing-recursive-flint): Recursive's free open-weight (Apache 2.0) coding model for local agentic coding: 40B mixture-of-experts with 2.5B active, runs on a laptop via llama.cpp, Ollama, LM Studio or Recursive's rec engine. (free; page: https://vibeshelf.co/tool/flint/)