Blink vs StackBlitz Bolt (2026)

Every app Blink generates comes wired to a Turso database, Blink Auth sign in, file storage and a live web address with SSL. Beyond that core, 63 connectors across email, calendars, team chat, CRM, projects, payments, analytics and social media are connected once by a workspace admin, most with a single sign in, and each project then picks which accounts it may use.

When a builder describes an app, the agent checks which connectors are live and writes the code that reads and sends data through them, and every call is routed through Blink's connector service so no token sits in the app's code. A few tools, among them Meta Ads, ElevenLabs, Perplexity and Firecrawl, take a pasted key instead. Claw agents reach Notion, Google Drive, HubSpot and Slack and send email, and outside assistants can list, authorize and disconnect connectors through Blink's MCP server.

Sourceblink.new/integrationsread 2026-10-09

Connectors run on MCP with eight shipping built in, Notion, Linear, GitHub, Miro, Sentry, Context7, Granola and Jira, authenticated by API key or sign-in, and any tool with a remote MCP server can be added as a custom connector. Each connector's individual actions of read, create, edit and delete can be toggled for granular access control.

First party integrations cover Figma and Google Stitch for design, GitHub for version control with organization access controls, Netlify and built-in Bolt hosting for deployment, Stripe for payments, Supabase and Bolt Database for data, Expo for mobile app store publishing, and Google SSO for authentication, plus a project import path from Lovable.

Sourcebolt.new Connectors announcement and support.bolt.new integrations sectionread 2026-08-31

The build agent runs one multi step loop per request. It plans the change, writes the frontend and backend, sets up the database and sign in, lints and builds the app, and saves a version when the task is done.

An outside assistant can start the same loop through the blink_build_prompt tool, follow it with status and wait calls, and answer the agent when it stops on a question, since a new prompt is refused until that question is answered or the build is stopped.

Claw agents each run alone on their own machine and can be paused, resized or deleted without touching the others, so several can work in parallel, though they do not hand work to one another or share a plan.

Sourceblink.new/docs/cloud/tools/claude-connectorread 2026-10-09

A project moves from prompt through to published app, with Code View exposing the generated files for direct editing. Plan Mode separates planning from code generation as an explicit phase. Skills apply reusable rules and workflows during planning or building, and a Prompt Library saves prompts for reuse alongside built-in prompts for common tasks.

Project context can be actively managed to control the context window, chat tools allow selecting UI elements, tagging files and queueing prompts, and backups and version history allow restoring an earlier point. Generation runs across multiple files inside an in-browser Node runtime with package installation and a live dev server.

Sourcesupport.bolt.new project-lifecycle, plan-mode, skills, prompt-library, code-view, chat-tools and manage-context pagesread 2026-08-31

Blink Claw agents run around the clock on a private cloud machine and act on their own schedule, with examples such as a 6:45 AM summary, a 3am inbox check and a Friday report, and on events, such as a follow up sent within ten minutes of a signup.

They take messages from Slack, Telegram and Discord, with WhatsApp also listed in the automation docs, can be chatted with inside Blink, and message the user first when something needs attention. How a schedule is set up is unclear.

The app builder itself starts work when someone sends a prompt, in the Blink workspace or from Claude, Claude Code or ChatGPT over MCP.

Sourceblink.new/clawread 2026-10-09

Users start work in the chatbox of the web application, with chat tools for selecting UI elements, tagging files and queueing prompts. Projects can start from a blank prompt, uploaded files, a Figma or Google Stitch design, or a team template, or be imported from Lovable, and each of these starts a build by hand. Collaborators can be invited to work on a project in real time. There is no scheduled, recurring, webhook or event driven trigger for starting a build.

Sourcesupport.bolt.new llms.txt index, chat-tools, start-project and collaborate pagesread 2026-08-31

Each build works from the project itself: its source tree, database schema, backend functions and saved versions. Blink's MCP server exposes the same material to outside assistants for reading, including file contents, the schema and a diff between any two versions, while secret files such as .env are never returned. Claw agents draw on the workspaces they are connected to, such as Notion and Google Drive. The Knowledge Base in Blink's docs is a retrieval feature for the apps Blink builds, so the build agent keeps no searchable index of a company's wider documents.

Sourceblink.new/docs/cloud/tools/claude-connectorread 2026-10-09

The customer's design system becomes a stored object Bolt builds from. Customers can add a design system so projects build using the company's UI guidelines and components, view and manage the generated system, start a project so Bolt builds with their real components from the first prompt, and keep the design system in sync when its sources change, with best practices guidance alongside.

The design system, built from the customer's own material, persists between runs. Knowledge is separately a managed object at account, workspace and project scope, with project knowledge set in project settings and shared knowledge held at workspace level. Files and images attach to a project as per-request context, and MCP connectors supply context from external tools and data.

Sourcesupport.bolt.new design system section including the sync page, account, workspace and project settings, upload files and connect-mcp pagesread 2026-08-31

Claw agents keep 1 GB of storage and memory that survives restarts, so preferences, goals and context carry from one conversation to the next, and pausing an agent stops its machine while keeping its data. How that memory is stored, reviewed or cleared is unclear. In the app builder, continuity comes from the project rather than from the agent: every finished task saves a version with a screenshot and a generated description, and the agent rereads the project's code and schema on each request instead of carrying memory of its own across projects.

Sourceblink.new/clawread 2026-10-09

Projects persist and can be viewed, organized and maintained over time. Backups, restore and version history allow returning a project to a previous point and are managed from the chat. Project knowledge, design systems and saved prompts persist as project and workspace configuration. Bolt advises actively managing project context and keeping it small for performance. Customers author Skills and Prompt Library entries, and the agent does not update them. Switching agents manually clears chat history.

Sourcesupport.bolt.new projects-files, rollback-backup, manage-context, skills and prompt-library pagesread 2026-08-31

Plan mode lets a builder think a change through with the agent, which only analyzes and replies and does not run tools, write files or deploy, and moving from Plan to Agent asks for confirmation before implementation starts. Agent mode then makes the changes.

Production stays apart from the work: each finished task updates a private preview and saves a version, the live app changes only when someone clicks Publish, and any earlier version can be restored and republished. Outside assistants change code only through a full Blink agent turn, since the MCP server has no file write tool, and a viewer's connection is read only. Claw agents act on their own, with the secrets vault setting what each one can reach.

Sourceblink.new/docs/reference/modesread 2026-10-09

Plan Mode is an optional chat mode in which Bolt plans and answers questions without changing code, ending with quick actions such as Implement this plan that switch to Build Mode. The user chooses whether to use it, and Build Mode applies changes directly with no approval step. Connector actions can each be toggled, team admins control member roles, publishing, integrations and data exports, GitHub organization admins control which repositories Bolt can reach, and generation carries security constraints in its system prompts.

Sourcesupport.bolt.new plan-mode and team-settings pages, bolt.new/platform/securityread 2026-09-29

SOC 2 is in progress and not yet complete. The DPA sets out TLS 1.2 or higher with HSTS in transit and AES 256 or equivalent encryption at rest, and, for the company's own production systems, role based access, single sign on, mandatory multi factor authentication, central application and access logs and audit logging on privileged operations, with breach notice within 72 hours.

Inside a project, one Owner controls visibility, Admins and deletion, Admins edit with the AI, invite people and publish, and Users can only view. Both roles can be invited on every plan, Free included, with no cap on numbers, and Business adds access levels set per project. None of the plans lists single sign on for logging in to Blink.

Sourceblink.new/dparead 2026-10-09

Bolt is SOC 2 Type 2 certified and compliant with GDPR and CCPA, with audit reports and policies on a trust profile at trust.bolt.new, AES-256 encryption at rest and TLS 1.2 or higher in transit, continuous scanning and intrusion detection watched by a 24/7 security operations team, and annual independent penetration tests with report summaries on request.

Enterprise and Team customers under an MSA or DPA are excluded from model training. Teams adds team level access management and granular admin controls with user provisioning, and Enterprise adds SSO and audit logs. Team settings restrict roles, publishing, integrations and data exports to admins.

Sourcebolt.new/platform/security, bolt.new/pricing and support.bolt.new team-settingsread 2026-09-29

Every finished task saves a version with a screenshot, a generated description of the change, a timestamp and, for projects connected to GitHub, a commit SHA, so a builder can see what the agent changed and when a problem first appeared, then restore a working state. Outside assistants can read the version list, the source tree and a diff between versions over MCP.

For apps with a Blink Backend, the Backend tab shows every request live with its route, status code, response time and any error, and function logs can be pulled over MCP. Whether the build agent's individual tool calls are kept as a trace, or a workspace keeps an audit log of agent activity, is unclear.

Sourceblink.new/docs/launch/publishread 2026-10-09

Backups, restore and version history let a project be returned to a previous point, managed from the chat. GitHub integration syncs commits automatically and works across branches, providing an external record of changes. Hosting analytics show engagement with a published project, and database logs are available for the generated app's database. Team settings include data exports. There is no agent level run trace or tool call record, and troubleshooting relies on issue specific guidance rather than inspecting a run.

Sourcesupport.bolt.new rollback-backup, git, hosting analytics, database logs, team-settings and llms.txt indexread 2026-08-31

Core platform data, app databases on Turso, sign in and the build sandboxes sit in the United States on a hosted service. API servers run in the US, the Netherlands and Singapore with requests handled by the nearest one, and Claw agent machines run on Fly.io in US cities, Amsterdam, Frankfurt or London, with each agent's data stored where it runs. Customers do not pick a region.

The way off the platform is the code: web apps are standard React and TypeScript on Vite and mobile apps are React Native with Expo, a code download costs 5 credits on Starter and Pro and nothing on Max, and projects sync both ways with GitHub, with the agent's own Git operations coming on Pro, so the code can be taken elsewhere.

Sourceblink.new/dparead 2026-10-09

BYOK deployment lets a customer run Bolt inside its own AWS or Azure tenant with full infrastructure isolation and no shared compute, meeting HIPAA, FedRAMP and SOC 2 requirements. Development executes client-side in an isolated WebContainer in the browser. Bolt Cloud hosts published projects at bolt.host or a connected domain, Netlify and Expo are alternative targets, GitHub sync exports the full codebase, and the bolt.diy fork runs locally.

Sourcebolt.new/platform/security, support.bolt.new hosting and git pagesread 2026-09-29

Blink Claw ships four named agents, each with its own role, instructions and recommended model. Gerald works as a chief financial officer on financial models, books and taxes, and Jamie as an executive assistant on morning briefings, tasks and email drafts.

Alex researches prospects and handles outreach and follow ups as a sales development rep, and Maya triages an inbox and drafts replies.

For apps, step by step tutorials walk through building a CRM, an analytics dashboard, a project manager, an online store, a course platform and several AI tools, and any public project can be remixed as a starting point.

Sourceblink.new/clawread 2026-10-09

A Templates catalog at bolt.new/resources/templates offers working templates filterable by category (websites, apps, portfolio, SaaS, blog, internal tools, editorial, ecommerce, travel, finance, real estate), each named, previewable and opened in Bolt with one click, among them a retail dashboard, a pooled analytics dashboard, a personal finance tracker, a SaaS landing page and dashboard, and a social media posting and analytics platform. Team templates skip repetitive project setup, the Prompt Library supplies built-in prompts, and skills add reusable rules and workflows.

Sourcebolt.new/resources/templates, support.bolt.new team-templates, prompt-library and skillsread 2026-09-29

Auto, the recommended setting, routes simple interface changes to fast models, complex features to advanced ones, debugging to reasoning models and design work to models that read images.

A builder can switch Auto off and pick the build agent's model directly from Google (Gemini 3 Pro and Flash), OpenAI (GPT-5.2 and GPT-5.1), Anthropic (Claude Opus, Sonnet and Haiku 4.5), xAI (Grok Code Fast) and Z.ai (GLM 4.6), with advanced models included from the Pro plan and costing more credits per request.

Claw agents choose separately from 13 models, Claude Sonnet 4.6 by default alongside GPT-5.4, Gemini 3.1 Pro, DeepSeek, Kimi and GLM, and can switch at any time. The AI Gateway's models serve the apps Blink builds rather than the builder.

Sourceblink.new/docs/reference/modelsread 2026-10-09

The customer can pick the model in one of Bolt's three agents. In Bolt Forge the customer selects among open-source models from several makers, GLM 5.3 and GLM 5.3 Flash, Kimi K3 and DeepSeek v4 Pro, with new open models added as released. The Standard and Max agents run on proprietary models with model selection handled behind the scenes.

Forge is included with every individual Pro plan and offered through a $9 Lite plan by waitlist. It is not available on Teams or Enterprise. It is a research preview for a limited period, and Bolt has not said whether it continues after that. The open-source bolt.diy fork supports customer API keys across OpenAI, Anthropic, Ollama, Gemini and LMStudio.

Sourcesupport.bolt.new bolt-forge and agents pagesread 2026-09-29

A remote MCP server at blink.new/mcp, signed in with OAuth and bound to one workspace, carries scopes for reading the workspace and projects, writing projects and running builds.

Its 37 tools cover projects, the database, backend logs, builds, source and versions, publishing, and skills and connectors, so an assistant can start a build, answer the agent's questions, roll back to an earlier version and publish, and setup is laid out for Claude, Claude Code and ChatGPT.

Billing, workspace deletion and ownership transfer stay out of reach, and adding secrets or switching models has to happen in the browser. Separately, the AI Gateway API, reached with workspace API keys, gives code chat completions, media generation, web search and file upload.

Sourceblink.new/docs/cloud/tools/claude-connectorread 2026-10-09

There is no API, SDK or first party MCP server for driving Bolt itself, and the API reference section has been removed from the documentation. Bolt does offer two way GitHub integration that backs up a project and syncs commits across branches with full codebase export, MCP connectors through which Bolt calls out, and the open-source bolt.diy fork maintained by StackBlitz Labs, which customers can modify and run locally.

Sourcesupport.bolt.new llms.txt, git and connect-mcp pagesread 2026-09-29

Each finished task runs a lint check and a build before the preview updates and a version is saved, and preview errors are surfaced to the agent and, over MCP, to outside assistants. When something breaks, the agent investigates in chat before changing code, and an earlier version can be restored. In mobile apps, features such as the camera, health data, push notifications and haptics only behave correctly on real hardware, so Blink points builders to testing on a phone through Expo Go. Whether the agent writes and runs its own tests for the app is unclear.

Sourceblink.new/docs/launch/publishread 2026-10-09

A project security check finds and fixes security problems in a generated project. A live preview renders the running application during development, backups and restore return a project to an earlier point, and GitHub branch support isolates changes. Dedicated troubleshooting pages cover Bolt issues, preview issues, publish issues, integrations issues and login issues. Token efficiency and context management guidance address build cost and reliability. There is no test generation, regression suite, scoring or evaluation comparing builds.

Sourcesupport.bolt.new security, rollback-backup, troubleshooting section, maximizing-token-efficiency and llms.txt indexread 2026-08-31

Claw agents come with a web browser beside Python, Node.js and bash, and browsing is part of the jobs they take on, such as prospect research, morning briefings and inbox work. Whether they can click through pages, fill in forms or work inside sites that need a login is unclear. The app build agent works through code, its preview and the build tools rather than operating a browser or a desktop.

Sourceblink.new/clawread 2026-10-09

Bolt executes builds in StackBlitz WebContainers, a Node runtime with filesystem, package manager and dev server running client-side in the browser tab. The live preview renders the application the agent has generated for human inspection. External systems are reached through MCP connectors and API integrations. There is no browser navigation, form filling, screen control or computer use.

Sourcesupport.bolt.new intro-bolt, preview-issues, connect-mcp pages and llms.txt indexread 2026-08-31