Lovable
Also known as: GPT Engineer
Natural-language full-stack app builder with MCP integrations, no-training data posture, regional hosting, and a collaboration-friendly surface for product builders and startups.
Lovable is an AI app builder from the wave of vibe coding tools that turns a plain language description into a working, deployed full stack web application. You describe what you want in a chat, or drop in a screenshot, and Lovable generates the interface, a backend with a database and sign in, API integrations and the hosting to run it, then lets you refine the result by continuing the conversation. It was built for the large majority of people who have product ideas but cannot write code, while still being useful to developers who want to skip boilerplate.
Under the hood, Lovable produces TypeScript and React code, runs its backend on Lovable Cloud for database, sign in and storage, and connects to Stripe so that describing a pricing model yields working checkout flows and the tables behind them. The whole codebase syncs both ways with GitHub or GitLab, so a developer can take over at any point. For finishing touches, Visual Edits let you click an element to change it, a Themes panel holds colors and typography, and image generation is built into the builder. A gallery of more than 200 templates, most of them by Lovable, can be remixed into a new project.
Build mode, formerly Agent Mode, is the default. The agent explores the existing codebase, searches the web for solutions, debugs errors on its own and tests its changes in a real browser, clicking and filling forms, before showing them. A complex feature gets broken into pieces, built, tested and fixed without constant back and forth. Plan mode lets the user review and edit a plan before any code is written, and connector actions that write to another system wait on an approval card.
Lovable connects to about ninety services, including Stripe, Notion, Shopify and Slack, supports custom APIs and MCP servers, and offers a mobile app for building from a phone by voice or text while the agent runs in the background. In 2026 it expanded beyond app building toward general work such as analysis and presentations. It is SOC 2 and ISO 27001 certified, and offers SAML single sign on from Business up, with SCIM and audit logs on Enterprise. It suits going from idea to a working prototype or MVP quickly, with larger production systems benefiting from engineering review.
Vendor details
Canonical URL
https://lovable.dev
Category
Coding agent
Subcategory
Natural-language app builder producing React and TypeScript applications the customer owns
Company status
independent
Use cases & customers
Primary use cases
Target customers
Deployment options
Integrations
Roughly ninety individually documented integrations in a single connector catalog, spanning CRM (Salesforce, HubSpot, Pipedrive, Zoho), data warehouses (Snowflake, BigQuery, Databricks, Redshift, ClickHouse, Microsoft Fabric, dbt semantic layer), ecommerce (Shopify, WooCommerce, PrestaShop, Lightspeed, Wix), payments and accounting (Stripe, Chargebee, QuickBooks, Xero, sevDesk, Lexware), communications (Slack, Twilio, Telegram, Resend, Mailgun, Brevo), HR (Workday, Ashby), security scanning (Aikido, Wiz), analytics (PostHog, Google Analytics), storage (AWS S3) and CMS (Notion, Contentful, Storyblok, WordPress). Connectors attach in three modes: app connectors, chat connectors, and app user connectors where each end user of the published app connects their own account. An any-API route, a create-connector path, custom MCP servers and MCP registries cover anything unlisted. Outbound surfaces are a documented Lovable API and a Lovable MCP server, plus agent integrations that turn a published app into an MCP server for ChatGPT and Claude. Two-way Git sync covers GitHub and GitLab including self-managed and dedicated.
In practice
You have a SaaS idea and no technical co-founder. You describe it to Lovable in plain language and get a deployed full-stack app, with a frontend, a Supabase database, authentication, and Stripe checkout wired up.
You've proven the concept and want a developer to take it further. Lovable syncs the entire TypeScript and React codebase two-way with GitHub, so your engineer can pick it up with no lock-in.
You want to add a dashboard, a settings page, and email notifications in one go. Lovable's Build mode, formerly Agent Mode, breaks the request into pieces, builds each, debugs on its own, and validates the changes before showing you.
Sources & related URLs
Related / legacy domains
Research sources
Agentic Index coverage score
12.0 / 14 capabilities · 86%
| Integrations & Tool Calling | Full |
|---|---|
|
Connectors sit in a single catalog, with Lovable handling authentication, credentials and requests. There are three connection types, app connectors, chat connectors and app user connectors, where each person using the published app connects their own account, and each connector's page says which types it supports. About ninety integrations have their own pages, spanning Salesforce, HubSpot, Pipedrive and Zoho CRM, Snowflake, BigQuery, Databricks, Redshift, ClickHouse and Microsoft Fabric, Shopify, WooCommerce, PrestaShop and Lightspeed, Stripe, Chargebee, QuickBooks and Xero, Slack, Twilio, Telegram and Resend, Workday and Ashby, Aikido and Wiz, Notion, Airtable and Contentful, and AWS S3. An any API route, a create connector path, custom MCP servers and MCP registries cover anything not listed. Sourcedocs.lovable.dev integrations introduction, app-connectors, chat-connectors, app-user-connectors, any-api, create-connector and integration catalogread 2026-08-31 |
|
| Workflow Orchestration | Full |
|
Build mode, formerly Agent mode, works on its own and takes a task end to end. It understands intent, explores the codebase for context, applies changes across files and resolves issues during development, with visible tasks showing progress and results reviewed before moving on. Plan mode handles decisions, and the user can switch between the two at any time. Subagents are a separate feature, and cross project referencing lets one project draw on another. Skills apply reusable instructions, code mode and the project editor expose generated files for direct editing, and drafts and project history support iteration. Sourcedocs.lovable.dev agent-mode, plan-mode, subagents, cross-project-referencing, skills, code-mode, projects/editor, drafts and projects/history pagesread 2026-08-31 |
|
| Knowledge Grounding & RAG | Partial |
|
Knowledge holds persistent instructions and context for the agent, defined once and always included, at two levels. Workspace knowledge holds shared rules across all projects, such as coding standards, preferred libraries and naming conventions, and project knowledge holds the app's purpose, database schema, architecture decisions and domain terminology. Workspace knowledge is a text field, unlike Skills, which load on demand. Project and workspace knowledge plus the customer's code and components are the main context sources, and Lovable does not describe reading instruction files from the repository or from outside sources. Design systems are Lovable projects that export reusable components, colors, fonts and styling rules, which other projects connect to and inherit, with immediate propagation, an order of precedence across several connected systems, and no versioning. Cross project referencing and about ninety integrations supply more material for each request. Sourcedocs.lovable.dev features/knowledge, design systems FAQ and knowledge context-sources FAQread 2026-08-31 |
|
| Human Oversight & Guardrails | Full |
|
Before a chat connector tool that can write runs, Lovable shows an approval card, and the user approves it once or chooses always allow per tool or per connection. Plan mode writes a plan the user approves before code is written. Since 16 October, Enterprise workspace policies can block publishing or require admin approval, and Business and Enterprise get an action center for publish requests. Sourcedocs.lovable.dev integrations/chat-connectors and changelogread 2026-10-25 |
|
| Security, Identity & Governance | Full |
|
Platform controls include a trust center, SAML single sign on, SCIM provisioning, two factor authentication, workspace identity and identity reuse, groups and people access controls, integration admin controls, project visibility settings and Enterprise audit logs. Enterprise materials describe centralized identity, granular access controls and security oversight across the workspace. Business tier has a data opt out setting, and secrets and build secrets are kept separate from generated code. Security scanning of the generated app is separate, through a security center, security insights, sensitive data scanning and Aikido and Wiz integrations. Sourcedocs.lovable.dev trust-center, saml-sso, business/sso, business/scim, two-factor-authentication, workspace-identity, groups, people, admin-controls, business/data-opt-out and secrets pagesread 2026-08-31 |
|
| Observability & Auditability | Full |
|
Enterprise audit logs record actions taken by workspace members and which client each came from (Web, Desktop, iOS or Android), filterable by client or by member, with earlier entries marked Unknown. Dedicated pages cover project monitoring, logs, project usage, analytics and security insights. Build mode shows tasks as work proceeds, and project history records changes to a project. Audit logs are listed among Enterprise workspace capabilities, alongside security oversight across the workspace. Sourcedocs.lovable.dev audit-logs, project-monitoring, logs, project-usage, analytics and security-insights pages, changelog and lovable-for-enterpriseread 2026-08-31 |
|
| Memory & State Persistence | Partial |
|
Projects are durable objects with a history page recording changes, drafts keep unfinished work, and project chat persists. A Knowledge feature holds project configuration, and cross project referencing lets one project draw on another. Build mode explores the codebase for context on each task instead of carrying learning between tasks, and skills apply reusable instructions the customer writes, which the agent does not update. Sourcedocs.lovable.dev projects/history, drafts, projects/chat, knowledge, cross-project-referencing, agent-mode and skills pagesread 2026-08-31 |
|
| Deployment & Data Residency | Full |
|
A default hosting region is set in Settings, under Security and compliance, Privacy and security, choosing Americas, Europe or Asia Pacific. On Business and Enterprise workspaces, admins can require a default region for every new project, after which members cannot choose a different one, and existing projects keep their original region. Country regions including Germany, Japan and United States East are available on Enterprise by request, and Enterprise materials list regional code hosting. Lovable Cloud hosts apps with custom, verified and transferable domains, and two way GitHub sync and external deployment guidance let the app be hosted elsewhere. Sourcedocs.lovable.dev privacy-and-security-settings, cloud, hosting, custom-domain, github and external-deployment-hosting pages, lovable-for-enterpriseread 2026-08-31 |
|
| Prebuilt Agents, Templates & Packs | Full |
|
Lovable runs a template gallery of 228 templates, 81 of them apps, authored by Lovable and adoptable with a Use template button that remixes the template into the customer's own project. Business adds design templates, and a prompting library, skills and design systems support building. Sourcelovable.dev/templates and docs.lovable.dev features/projects/remixread 2026-10-25 |
|
| Triggers & Channel Coverage | Full |
|
Lovable can check a project on a schedule, daily or weekly at a chosen time and optionally only after a minimum number of edits, reviewing the app code for broken functionality and recent visitor errors, then alerting by email and listing findings to fix in the project chat. So the builder agent wakes on a schedule without anyone asking. Other routes in are the web chat, a Slack app, mobile and desktop apps, a Telegram route, the Lovable API and the Lovable MCP server. Monitoring is in beta, on Pro, Business and Enterprise. Sourcedocs.lovable.dev project-monitoring page and llms.txt indexread 2026-09-29 |
|
| Model Flexibility & Routing | Not documented |
|
The builder has no model selection, model picker, bring your own key or provider setting, including in advanced settings, workspace admin settings and account settings. The model related integrations, Fireworks, Replicate, Perplexity and Gemini Enterprise, and an AI feature among the Cloud backend pages give model access to the app being built, not a choice over the model that powers Lovable. Sourcedocs.lovable.dev sitemap inventory, advanced-settings, workspace-admin-settings, lovable-account-settings and features/ai pagesread 2026-08-31 |
|
| APIs, SDKs & MCP Extensibility | Full |
|
Lovable has its own API and MCP server. Agent integrations turn a published Lovable app into an MCP server that ChatGPT, Claude and other assistants can use, with configurable tools, sign in, permissions and access. Custom MCP servers, MCP registries, a create connector path and an any API route cover other services. Two way Git sync with GitHub and GitLab, including self managed and dedicated GitLab, exports the full codebase, and desktop, mobile and Slack surfaces extend access to the platform. Sourcedocs.lovable.dev lovable-api, lovable-mcp-server, agent-integrations, custom-mcp, mcp-registries, create-connector, any-api and git-sync-overview pagesread 2026-08-31 |
|
| Testing, Debugging & Optimization | Full |
|
Browser testing has the platform use the customer's app in a real browser running in a virtual environment, clicking buttons, filling forms, navigating pages and checking real user behavior with screenshots across screen sizes. It returns a verdict. A Details view shows the steps taken and summarizes what worked and what did not, and the pattern is reproduce, fix, then verify. Where test and live environments are turned on, it runs against the project preview in the test environment, so the check happens before the change reaches anyone. The check is Lovable's own, run against the customer's app before release. Sourcedocs.lovable.dev browser-testing page and test-and-live-environments documentationread 2026-08-31 |
|
| Browser & Computer Use | Full |
|
Browser testing has the agent use the app it built in a real browser running in a virtual environment. It clicks buttons, fills forms and navigates pages, and takes screenshots across screen sizes. Firecrawl and Apify integrations retrieve web content over HTTP, and other outside actions run through connectors and MCP. Sourcedocs.lovable.dev/features/browser-testingread 2026-10-25 |
|
The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded
Product updates
Dreaming is a new background process on paid Lovable plans that checks project memory and the rules in AGENTS.md files against the code and the project chat, then rewrites or removes what no longer applies. Rules a user asked for stay as written and app code never changes, while AGENTS.md edits show in the project chat and in version history. Dreaming does not use credits.
Bears on: Memory / state
View sourceErrors that happen in visitors' browsers now feed into project monitoring on paid plans. Lovable looks for their cause in the project's code, shows what it finds in the editor, and emails the project owner about important findings. Browser errors are collected only while Visitor analytics is on.
Bears on: Observability / auditability
View sourceA software bill of materials can now be downloaded for any project from the dependency list in the Security view, in SPDX 2.3 or CycloneDX 1.5 format. The file lists production dependencies and their known vulnerabilities, and downloading it is free.
Bears on: Security / enterprise
View sourcePricing
Pro at $25/mo for 100 credits. A free plan gives 5 credits/day.
Credits. One balance pays for building, Cloud hosting and in app AI, plans are priced by the size of the monthly credit allotment, and every plan allows unlimited collaborators with no per seat charge.
Included quota
Every plan includes unlimited workspace collaborators, with no per seat pricing. Free gives 5 daily build credits, up to 30 a month, plus 20 Cloud credits monthly. Pro scales linearly from 100 credits at $25 to 10,000 credits at $2,250, with plan credits expiring two months after issue and top ups (Stripe one time) valid 12 months. Business follows the same ladder at roughly double the rate per credit.
What is public
Lovable publishes full pricing. A free plan gives 5 daily build credits (30 a month cap) and 20 Cloud credits, Pro runs from $25 a month for 100 credits to $2,250 for 10,000, Business starts at $50 with SSO and data training opt out at roughly double the per credit rate, and Enterprise is custom. All plans allow unlimited collaborators. Credits cover building, hosting and in app AI from one balance.
Billing mechanics
Credit based consumption across building, Cloud hosting and in app AI from one balance. Messages cost a variable number of credits by complexity. Plan credits are granted monthly and expire after two months, daily bonus credits expire the same day, and top ups last 12 months. Auto top up with a monthly spend cap is available. Billing is by workspace with unlimited collaborators, not per seat.
Cost watchouts
Credits burn by complexity (roughly half a credit for small tweaks to 3 for multi file generations), so heavy iteration or debugging loops can exhaust the 100 credit Pro allotment in days. Runtime costs (Lovable Cloud hosting and in app AI features) draw from the same credit balance once traffic grows. Business plan credits cost roughly double Pro per credit, with the premium buying SSO, data training opt out and per user limits.
Variable cost rationale
Lovable meters credits. Each message costs a variable number of credits by its complexity, and Lovable Cloud hosting and in app AI draw on the same balance once an app has traffic, so heavy iteration, debugging loops and a busy live app all grow the bill. The plan's monthly credits set the base, and the Pro ladder runs from 100 credits at $25 to 10,000 at $2,250. Top ups extend the balance, and auto top up carries a monthly spend cap. Plan credits expire two months after issue, daily bonus credits the same day and top ups after 12 months. Collaborators add no cost, since every plan allows unlimited collaborators.
Additional watchouts
Iteration on the last stretch of a build consumes credits fast, and top ups and runtime usage add to the plan price for a production app. Projects can be exported to GitHub and finished in a code editor.
Sales call required
No, self serve available
Free / trial
Free plan, no card (5 daily build credits up to 30 a month, 20 Cloud credits a month)
Lowest paid plan
Pro at $25 per month for 100 credits, about 16% less billed annually, with 50% off for students
Commercial notes
Roughly 8M registered users and a $6.6 billion valuation, and named to TIME's most influential companies list. Lovable generates React apps on Lovable Cloud, which runs on Supabase (database, auth, storage). GitHub sync on all plans and code export let a project move off the platform.
Key ambiguities
Effective cost per app is unpredictable because per message credit costs vary with complexity. Runtime Cloud and AI usage add a second consumption stream that only matters at meaningful traffic.
Missing data
Enterprise per credit pricing and minimums are not published.
Related vendors
- Cognition — Maker of Devin, an autonomous AI software engineer
- 10Web — Agentic website platform whose AI agents build, host and manage…
- AgentUI — Managed AI app builder for operations teams that generates and hosts…
- Aider — Open source, model agnostic terminal coding agent that edits your…
- Amp — Amp is a coding agent from Amp Frontier Corporation that runs each…
- Anthropic Claude Code — Anthropic's agentic coding system across terminal, desktop, IDE, web…
Alternatives to Lovable
The closest documented capability profiles to Lovable among coding agents tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.
- Anthropic Claude Code12.5 / 14Fuller documented coverage on Memory & State PersistenceLovable vs Anthropic Claude Code →
- Baz13.0 / 14Adds documented Model Flexibility & Routing
- Capy12.5 / 14Adds documented Model Flexibility & Routing
- Cursor12.5 / 14Adds documented Model Flexibility & Routing
- Google Antigravity12.5 / 14Adds documented Model Flexibility & Routing
- OpenHands13.5 / 14Adds documented Model Flexibility & Routing
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded