# BuildJury

> Independent verdicts on AI build tools (AI coding agents, vibe-coding app builders, agent frameworks, MCP servers) ranked by use case. 35 tools, 11 use-case rankings, 6 head-to-head comparisons. Rankings are never for sale; sponsored placements are always labeled. Prices are only stated when confirmed on the vendor's official pricing page. Last updated 2026-10-30.

BuildJury was formerly called BuildStack. Full detail (pros, cons, pricing, sources): https://buildjury.com/llms-full.txt

## Use-case rankings
- [Best AI tools for building landing pages](https://buildjury.com/use-cases/landing-pages/): 1. Framer, 2. v0, 3. Lovable, 4. Bolt.new, 5. Cursor
- [Best AI tools for building a SaaS MVP](https://buildjury.com/use-cases/saas-mvp/): 1. Lovable, 2. Bolt.new, 3. Replit Agent, 4. Cursor, 5. Claude Code, 6. v0
- [Best AI tools for building mobile apps](https://buildjury.com/use-cases/mobile-apps/): 1. Rork, 2. FlutterFlow, 3. Google AI Studio (Build mode), 4. Replit Agent, 5. Cursor
- [Best AI tools for building internal tools](https://buildjury.com/use-cases/internal-tools/): 1. Retool, 2. Lovable, 3. Microsoft Copilot Code, 4. Replit Agent, 5. n8n
- [Best frameworks for building AI agents](https://buildjury.com/use-cases/ai-agents/): 1. OpenAI Agents SDK, 2. LangGraph, 3. Microsoft Agent Framework, 4. CrewAI, 5. Vercel AI SDK, 6. n8n
- [Best tools for building AI chatbots](https://buildjury.com/use-cases/chatbots/): 1. Voiceflow, 2. Botpress, 3. Vercel AI SDK, 4. Zapier
- [Best AI tools for data and workflow automation](https://buildjury.com/use-cases/automation/): 1. n8n, 2. Zapier, 3. Make
- [Best AI coding tools for an existing codebase](https://buildjury.com/use-cases/coding-in-existing-codebase/): 1. Claude Code, 2. Cursor, 3. GitHub Copilot, 4. OpenAI Codex, 5. Devin Desktop (formerly Windsurf), 6. Kiro, 7. Google Antigravity, 8. Cline
- [Best terminal (CLI) coding agents](https://buildjury.com/use-cases/terminal-coding-agents/): 1. Claude Code, 2. OpenAI Codex, 3. Cursor, 4. Google Antigravity, 5. Kiro, 6. Factory Droid, 7. Cline
- [Best agent-first IDEs and agent managers](https://buildjury.com/use-cases/agent-first-ides/): 1. Cursor, 2. Devin Desktop (formerly Windsurf), 3. Google Antigravity, 4. Kiro, 5. GitHub Copilot
- [Best MCP servers for Claude and Cursor](https://buildjury.com/use-cases/mcp-servers/): 1. GitHub MCP Server, 2. Context7, 3. Playwright MCP, 4. GitLab MCP Server, 5. Supabase MCP, 6. MCP Reference Servers

## Comparisons
- [Cursor vs Claude Code](https://buildjury.com/compare/cursor-vs-claude-code/): Pick Cursor if you want an AI-first editor with tab completion and visual multi-file diffs; pick Claude Code if you want an agent in your terminal that works alongside any editor. Many developers use both.
- [Claude Code vs OpenAI Codex](https://buildjury.com/compare/claude-code-vs-openai-codex/): Both are agentic coding tools with a CLI. Claude Code is strongest as a terminal agent for large refactors; Codex stands out for running tasks in parallel in the cloud and its open-source CLI, and its best value comes with a ChatGPT plan.
- [Lovable vs Bolt.new](https://buildjury.com/compare/lovable-vs-bolt-new/): Both turn a prompt into a full-stack web app in the browser. Lovable leans on polished UI and a built-in Supabase backend; Bolt.new is very fast from prompt to running app in an in-browser dev environment. Both get harder to steer on big, complex apps.
- [Cursor vs Devin Desktop (formerly Windsurf)](https://buildjury.com/compare/cursor-vs-devin-desktop/): Both are VS Code-family AI editors with agents. Devin Desktop (renamed from Windsurf in June 2026) centers on a Kanban Agent Command Center for local and cloud Devin agents plus other ACP agents; Cursor stays editor-first with its own agent, CLI and Cloud Agents.
- [Google Antigravity vs Cursor](https://buildjury.com/compare/google-antigravity-vs-cursor/): Antigravity 2.0 is an agent-first desktop app with no code editor (Google recommends pairing it with an IDE, and also ships the Antigravity IDE and CLI); Cursor is an AI-first code editor. Choose based on whether you want to manage agents or write code with an agent beside you.
- [LangGraph vs CrewAI](https://buildjury.com/compare/langgraph-vs-crewai/): LangGraph gives fine-grained control over stateful agent graphs with persistence and human-in-the-loop; CrewAI is faster to prototype with an intuitive role/task model. Choose control vs speed.

## Recent changes (sourced)
- 2026-10-29 Factory Droid: Factory ships Droid 1.0, a new engine for its coding agent that makes programmatic tool calling the default: a Script tool lets the model write sandboxed JavaScript that runs hundreds of tool calls in a single model request, keeping raw outputs out of the context window. Factory says it beats native harnesses on efficiency by up to 20% on the same tasks. Source: https://factory.com/news/frontier-harness
- 2026-10-28 GitHub Copilot: GitHub makes Copilot Fusion generally available: pick it in the model picker (Standard, High or Max effort) and it routes each prompt to one model or orchestrates several (cascade or critique). 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 per task. Source: https://github.blog/changelog/2026-10-28-route-and-orchestrate-models-with-github-copilot-fusion/
- 2026-10-28 Cursor: Cursor pricing is now the X Subscription: Free, Plus $8/mo (Grok models only), Premium $30/mo, Super $100/mo, Ultra $200/mo and Teams from $30/user/mo, with one weekly usage pool shared across Cursor and Grok. Third-party models like Claude and GPT are no longer included and are billed at API list price, which has drawn developer pushback on X. Source: https://cursor.com/pricing
- 2026-10-26 OpenAI Codex: Security warning: Forever Security found a malicious AGENTS.md planted in a real user's ~/Downloads folder that told Codex to add an MCP server and install npm malware via ~/.codex/config.toml (over 90% success in its tests). Don't run coding agents inside Downloads. Source: https://forever.security/blog/hijacking-ai-agents-via-downloads-folder/
- 2026-10-26 Claude Code: Security warning: the same researchers showed a planted CLAUDE.md can get Claude Code to reroute its API traffic and leak its OAuth token about half the time. Check unfamiliar instruction files and settings before starting an agent in a folder you didn't create. Source: https://forever.security/blog/hijacking-ai-agents-via-downloads-folder/
- 2026-10-23 Microsoft Agent Framework: Microsoft Agent Framework ships Python 1.23 (Oct 22, foundation for MCP 2.x compatibility, with breaking changes) and .NET 1.26 (Oct 23). Source: https://github.com/microsoft/agent-framework/releases
- 2026-10-22 Replit Agent: Replit launches Monitoring Agent: with alerting and auto-fix on, it investigates production issues, validates a fix and can auto-publish it. Source: https://replit.com/blog/replit-monitoring-agent
- 2026-10-22 Cursor: Cursor CLI v2026.10.22: redeploy Cloud Agent environments, team-scoped self-hosted workers, nested AGENTS.md rules applied on edit. Source: https://cursor.com/docs/cli/changelog
- 2026-10-19 Google AI Studio (Build mode): Google releases the Gemini API CLI (gemini-api), an experimental zero-dependency binary that lets Claude Code, Codex, Cursor, Antigravity or any shell-capable agent generate images, video, speech and music, analyze files and launch Gemini Managed Agents like Deep Research. Source: https://aistudio.google.com/learn/introducing-the-gemini-api-cli
- 2026-10-15 GitLab MCP Server: GitLab MCP server is generally available with GitLab 19.5, on Free, Premium and Ultimate tiers. Source: https://about.gitlab.com/blog/mcp-server-ga/
- 2026-10-15 Lovable: Lovable adds built-in AI models and tools for the apps you build: GPT-Live, the latest Claude models, Gemini, Perplexity, Firecrawl, Parallel and Jev. Source: https://lovable.dev/blog/ai-models-and-tools-in-lovable
- 2026-10-13 Google AI Studio (Build mode): Google Play lets you run vibe-coded Android apps built in Google AI Studio privately on your own device with a standard Google account (US and select markets, 18+). Source: https://blog.google/products-and-platforms/platforms/google-play/google-play-updates-october-2026/
- 2026-10-15 Claude Code: Claude Code Review leaves research preview and is generally available for Claude Team and Enterprise, with Quick, Standard and Deep modes. Source: https://claude.com/resources/articles/code-review-is-now-generally-available
- 2026-09-25 Microsoft Copilot Code: Microsoft introduces Copilot Code, a natural-language app builder inside Copilot, rolling out through the Frontier program. Source: https://blogs.microsoft.com/blog/2026/09/25/introducing-the-new-copilot-with-home-code-and-autopilot/
- 2026-06-18 Google Antigravity: Gemini CLI is replaced by Antigravity CLI for unpaid-tier and Google One users; Google recommends Antigravity CLI for the latest Gemini models. Source: https://developers.googleblog.com/an-important-update-transitioning-gemini-cli-to-antigravity-cli
- 2026-06-02 Devin Desktop (formerly Windsurf): Windsurf is renamed Devin Desktop; Devin Local replaces the Cascade agent (legacy Cascade supported through July 1, 2026). Source: https://devin.ai/blog/windsurf-is-now-devin-desktop

## Tools
- [Cursor](https://buildjury.com/tools/cursor/): AI code editor. AI-first code editor (VS Code fork) with agent mode, codebase chat and tab completion. Official: https://cursor.com
- [Devin Desktop (formerly Windsurf)](https://buildjury.com/tools/devin-desktop/): AI code editor. Cognition's agentic IDE, renamed from Windsurf on June 2, 2026. Adds an Agent Command Center for managing local and cloud agents; Devin Local replaces the Cascade agent. Official: https://devin.ai/desktop
- [GitHub Copilot](https://buildjury.com/tools/github-copilot/): AI coding assistant. GitHub's AI pair programmer for VS Code, JetBrains and more, with chat and coding agent. Official: https://github.com/features/copilot
- [Claude Code](https://buildjury.com/tools/claude-code/): Terminal coding agent. Anthropic's agentic coding tool that runs in your terminal and edits real repos. Official: https://www.anthropic.com/claude-code
- [OpenAI Codex](https://buildjury.com/tools/openai-codex/): Coding agent. OpenAI's coding agent available in the cloud, CLI and IDE. Official: https://openai.com/codex/
- [Factory Droid](https://buildjury.com/tools/factory-droid/): Coding agent. Factory's model-agnostic enterprise coding agent, available as a desktop app (macOS, Windows), a terminal interface and a TypeScript SDK. Droid 1.0 (Oct 29, 2026) makes programmatic tool calling the default: the model writes a sandboxed script that runs many tool calls in one request. Official: https://factory.com
- [Cline](https://buildjury.com/tools/cline/): Open-source coding agent. Open-source autonomous coding agent extension for VS Code. Official: https://cline.bot
- [Bolt.new](https://buildjury.com/tools/bolt-new/): AI app builder. Prompt-to-full-stack web apps in the browser by StackBlitz. Official: https://bolt.new
- [Lovable](https://buildjury.com/tools/lovable/): AI app builder. Chat-to-app builder for web apps with Supabase backend integration. Official: https://lovable.dev
- [v0](https://buildjury.com/tools/v0/): AI app/UI builder. Vercel's AI builder for React/Next.js UIs and apps. Official: https://v0.app
- [Replit Agent](https://buildjury.com/tools/replit/): AI app builder. Cloud IDE whose Agent builds, runs and deploys apps from a prompt. Official: https://replit.com
- [Framer](https://buildjury.com/tools/framer/): AI website builder. Design-led website builder with AI page generation and hosting. Official: https://www.framer.com
- [Rork](https://buildjury.com/tools/rork/): AI mobile app builder. Prompt-to-native mobile app builder producing React Native (Expo) apps. Official: https://rork.com
- [FlutterFlow](https://buildjury.com/tools/flutterflow/): Low-code mobile builder. Visual Flutter app builder with AI assistance and code export. Official: https://flutterflow.io
- [Retool](https://buildjury.com/tools/retool/): Internal tool builder. Build internal tools, dashboards and AI apps on top of your databases and APIs. Official: https://retool.com
- [n8n](https://buildjury.com/tools/n8n/): Workflow automation. Fair-code workflow automation with native AI agent nodes. Official: https://n8n.io
- [Zapier](https://buildjury.com/tools/zapier/): Workflow automation. No-code automation across thousands of apps, plus AI agents and MCP. Official: https://zapier.com
- [Make](https://buildjury.com/tools/make/): Workflow automation. Visual scenario builder for automations with AI modules. Official: https://www.make.com
- [LangGraph](https://buildjury.com/tools/langgraph/): Agent framework. Framework for stateful, controllable multi-step agents from LangChain. Official: https://www.langchain.com/langgraph
- [CrewAI](https://buildjury.com/tools/crewai/): Agent framework. Python framework for orchestrating role-based multi-agent crews. Official: https://www.crewai.com
- [OpenAI Agents SDK](https://buildjury.com/tools/openai-agents-sdk/): Agent framework. Lightweight SDK for agents with tools, handoffs, guardrails and tracing. Official: https://openai.github.io/openai-agents-python/
- [Vercel AI SDK](https://buildjury.com/tools/vercel-ai-sdk/): AI app toolkit. TypeScript toolkit for building AI chat, streaming UIs and agents across model providers. Official: https://ai-sdk.dev
- [Voiceflow](https://buildjury.com/tools/voiceflow/): Chatbot builder. Collaborative platform for designing and deploying AI chat and voice agents. Official: https://www.voiceflow.com
- [Botpress](https://buildjury.com/tools/botpress/): Chatbot builder. Platform to build LLM-powered chatbots and deploy to web and messaging channels. Official: https://botpress.com
- [GitHub MCP Server](https://buildjury.com/tools/github-mcp-server/): MCP server. GitHub's official MCP server: let agents read repos, issues and PRs. Official: https://github.com/github/github-mcp-server
- [Playwright MCP](https://buildjury.com/tools/playwright-mcp/): MCP server. Microsoft's MCP server for browser automation via Playwright. Official: https://github.com/microsoft/playwright-mcp
- [Context7](https://buildjury.com/tools/context7/): MCP server. Feeds up-to-date library docs into your coding agent to reduce hallucinated APIs. Official: https://github.com/upstash/context7
- [Supabase MCP](https://buildjury.com/tools/supabase-mcp/): MCP server. Connect AI tools to your Supabase projects: tables, SQL, migrations. Official: https://supabase.com/docs/guides/getting-started/mcp
- [MCP Reference Servers](https://buildjury.com/tools/mcp-reference-servers/): MCP server. Official reference MCP servers (filesystem, git, fetch, memory and more) plus a community list. Official: https://github.com/modelcontextprotocol/servers
- [Google Antigravity](https://buildjury.com/tools/google-antigravity/): Agent-first coding app. Google's agent-first development platform: Antigravity 2.0 is a standalone desktop app (macOS, Windows, Linux) for running Gemini-powered agents, alongside the Antigravity IDE, CLI and SDK. Official: https://antigravity.google
- [Kiro](https://buildjury.com/tools/kiro/): Spec-driven coding agent. AWS-built agentic IDE, CLI and web app that turns prompts into requirements, designs and tasks (specs) before implementing them with parallel agents. Official: https://kiro.dev
- [Google AI Studio (Build mode)](https://buildjury.com/tools/google-ai-studio/): AI app builder. Google's browser-based builder that vibe-codes web apps and native Android apps (Kotlin + Jetpack Compose) from a prompt, with a cloud Android emulator and Firebase integration. Official: https://aistudio.google.com
- [Microsoft Copilot Code](https://buildjury.com/tools/copilot-code/): AI app builder (workplace). The Code tab in Microsoft Copilot: describe a dashboard, internal tool, static site, data transform or script and it builds it with a live preview, using Microsoft 365 context with your permission. Official: https://learn.microsoft.com/en-us/copilot/code/
- [Microsoft Agent Framework](https://buildjury.com/tools/microsoft-agent-framework/): Agent framework. Microsoft's open-source framework for building, orchestrating and deploying AI agents and multi-agent workflows in Python and .NET. Official: https://github.com/microsoft/agent-framework
- [GitLab MCP Server](https://buildjury.com/tools/gitlab-mcp-server/): MCP server. GitLab's official MCP server, generally available since GitLab 19.5 (Oct 15, 2026): agents work across code, merge requests, work items and pipelines under your GitLab permissions. Official: https://docs.gitlab.com/user/gitlab_duo/model_context_protocol/mcp_server/

## Optional
- [How we rank](https://buildjury.com/methodology/)
- [What's new](https://buildjury.com/news/)
- [All tools](https://buildjury.com/tools/)
- [Sitemap](https://buildjury.com/sitemap.xml)