Bolt.new

Converts natural language prompts into complete, runnable full-stack web applications by parsing user intent, generating React/Next.js frontend code, Node.js backend logic, and database schemas, then immediately executing the generated code in a WebContainer sandbox to validate functionality. Uses Claude Agent or Opus 4.7 models with filesystem-aware context management to understand project structure and maintain coherence across multi-file generation tasks.

Executes Node.js code and React applications directly in the browser using StackBlitz's WebContainers technology, which provides a complete Linux-like filesystem and npm package management within the browser sandbox. Supports hot module reloading for instant feedback on code changes, allowing developers to see application behavior changes in real-time without manual restart or local environment configuration.

Supports integration with external APIs (Stripe for payments, Supabase for databases, Google SSO for authentication) with managed credential storage and secure API key handling. The agent can generate code that uses these APIs and manage authentication flows without exposing credentials in generated code. Supports MCP (Model Context Protocol) servers for generic integration extensibility.

Implements a token-based pricing model with tiered consumption limits (300K tokens/day free, 10M tokens/month Pro, custom Enterprise) and per-interaction token tracking. Users can monitor token consumption, understand cost drivers (project size, model selection, interaction frequency), and optimize usage. Unused tokens roll over monthly on Pro tier, incentivizing efficient usage.

Supports generating React Native mobile applications using Expo, allowing developers to build iOS and Android apps from natural language prompts. The agent generates Expo-compatible code, manages dependencies, and can deploy to Expo Go for testing or build production APK/IPA files. Integrates Expo as a first-class deployment target alongside web applications.

Provides 'Plan Mode' and 'Discussion Mode' features that enable iterative refinement of applications through conversation. Users can discuss design decisions, ask the agent to plan features before implementation, and refine requirements through dialogue. The agent maintains conversation context and can adjust implementation based on feedback without losing project state.

Stores generated and edited Bolt projects in Bolt Cloud infrastructure, providing persistent storage across browser sessions and device access. Projects are associated with user accounts and can be accessed from any browser. Storage limits are 10MB (free tier) and 100MB (Pro tier). Projects can be shared publicly or privately (private sharing requires Pro tier). No documented export format or data portability mechanism; projects are locked into Bolt's infrastructure.

Provides a 'Plan' mode that allows users to discuss and refine application requirements before code generation begins, and a 'Discussion' mode for iterative refinement after generation. The agent can break down complex requirements, ask clarifying questions, and validate understanding before committing to code generation. This reduces iteration cycles by ensuring requirements are clear before implementation.

Integrates design system knowledge (Material UI, Chakra UI, Shadcn UI, Washington Post Design System, custom Figma designs) into the code generation process, allowing the AI agent to generate UI components that match specified design systems without manual component mapping or style configuration. Supports importing design tokens, component libraries, and visual guidelines from Figma or GitHub repositories, which are then referenced in generated code.

Implements an autonomous feedback loop where generated code is automatically tested, errors are detected, and the agent refactors code to fix failures without user intervention. The agent runs test suites, analyzes console errors and runtime failures, and iteratively modifies code until tests pass or the application runs without errors. Claims to reduce errors by 98% through this automated correction mechanism.

Allows users to select and switch between different AI models (Claude Agent, Opus 4.7, and other frontier coding agents) on a per-project or per-request basis, enabling experimentation with different model capabilities and cost-performance tradeoffs. The agent architecture abstracts model selection, allowing seamless switching without re-prompting or losing project context.

Integrates with GitHub for version control, allowing users to import projects from GitHub repositories, commit changes back to GitHub, and deploy applications directly to Netlify or custom domains. The agent can read GitHub repository structure as context for code generation and push generated code back to GitHub as commits, enabling CI/CD integration and collaborative workflows.

Analyzes existing project structure and codebase to understand architectural patterns, then refactors code to improve scalability, performance, or maintainability. The agent can identify technical debt, suggest architectural improvements, and implement refactoring across multiple files while maintaining functional equivalence. Supports handling projects 1,000 times larger than previous versions through improved context management and token efficiency.

Provides team-based project management with shared workspaces, granular permission controls (Teams+ feature), and user provisioning. Multiple team members can access and edit the same project, with admin controls for managing access levels, user roles, and project visibility. Supports real-time collaboration features (mechanism undocumented) and private project sharing on Pro+ tier.

Generates static websites with built-in SEO optimization, including metadata generation, sitemap creation, Open Graph tags, and structured data markup. The agent understands SEO best practices and applies them automatically during code generation, ensuring generated websites are search-engine friendly without manual configuration.

Provides AI-powered image editing capabilities (Pro+ feature) integrated into the development workflow, allowing users to generate, edit, or optimize images without leaving Bolt. Supports image generation from text descriptions, background removal, and other image transformations, with generated images automatically integrated into projects.