Base44
AI app builder (a Wix company) with built in database, auth and hosting, plus Superagents: autonomous agents built from a plain language description that run on schedules and events with persistent memory.
Base44 is an AI app builder with its own database, sign in and hosting. A builder describes an app in chat and Base44 generates it, previews it instantly on built in hosting, and lets the builder refine it by prompting again or by clicking on the page to change layout, copy and styling, while two way GitHub sync exports the full source code. Wix bought Base44 in June 2025, and it runs as a Wix company under its own name, sold directly and through the Wix App Market.
Superagents are the second half of the product. They are autonomous agents built from a plain language description that run workflows on a schedule or when something happens, such as an email arriving. They reach people on WhatsApp, Telegram, iMessage, Slack and LINE, remember facts across conversations when the owner turns memory on, split large requests across sub agents working in parallel, and complete tasks on the web in a cloud browser or the user's own Chrome. A Superagent asks for approval before it changes an app or installs a skill.
For organizations, the trust center lists SOC 2 Type II and ISO 27001. Single sign on is enforced across a workspace and every app inside it, SCIM keeps accounts in sync, and IP allowlisting limits where people sign in from. On new workspaces, SSO and a choice of data residency in the EU or the UK instead of the default US both need the Business or Enterprise plan. A CLI, a typed SDK, an Audit Logs API and App MCP give developers and assistants a way in. Paid plans start at $16 a month billed annually and climb through larger credit tiers to a Business plan, with custom Enterprise pricing above that.
It fits founders and business teams who want an app plus agents that keep running the business after launch, under enterprise controls. It fits less well where the app must run in the customer's own cloud, since Base44 runs only as a hosted service.
Vendor details
Canonical URL
https://base44.com
Category
Coding agent
Subcategory
App builder (vibe coding)
Funding status
Acquired. Base44 was bought by Wix in June 2025 and operates as a Wix company, running on Wix's enterprise security infrastructure while continuing to sell under its own name and domain. Reported to have reached $100m ARR. Distributed both directly at base44.com and through the Wix App Market, where installed Wix apps including Stores, Bookings, Blog, Events, Restaurants and CRM become context sources for generated applications.
Company status
acquired
Use cases & customers
Primary use cases
Target customers
Deployment options
In practice
You want to build a working app but don't want to wire up a database, auth, and hosting separately. Base44 includes all of them, so you describe the app and it comes together.
Vibe coding falls apart when the backend isn't there. Base44 is full-stack, handling data, authentication, and hosting behind the app you build.
Standing up a prototype usually means stitching services together first. Base44 is an all-in-one builder, so the foundation is built in and you start on the actual app.
Sources & related URLs
Related / legacy domains
Agentic Index coverage score
13.0 / 14 capabilities · 93%
| Integrations & Tool Calling | Full |
|---|---|
|
Prebuilt integrations cover AI, email, file storage, payments and messaging, with Airtable, Slack, Stripe and Zapier named in the documentation index. Beyond the first party set there is a community integrations list with a Create Integration flow and per integration approval status, so third parties publish connectors others can adopt (Explorium documents its own onboarding through it). Enterprise admins control which external services are available, manage shared versus app user credentials separately, and can block specific connectors across apps, Superagents and in app agents. Superagents themselves connect outward to third party applications and reach users over WhatsApp and Telegram. The Wix distribution adds Stores, Bookings, Blog, Events, Restaurants and CRM as context sources. Sourcedocs.base44.com developer documentation, base44.com enterprise pages and Wix App Market listingread 2026-07-30 |
|
| Workflow Orchestration | Full |
|
A Superagent splits a complex request into independent sub-agent tasks that run in parallel in the background, shows each in a task panel, lets the user stop the work while keeping finished results, and combines the outputs into one response. Superagent workflows are built from a chat description into scheduled or triggered multi-step runs managed from a Workflows page, and app workflows automate multi-step work on schedules, data changes or connector events. Sourcedocs.base44.com/superagents/subagents and setting-up-workflowsread 2026-09-29 |
|
| Knowledge Grounding & RAG | Partial |
|
Agents are grounded in the application's own data entities, with AI assistants defined with custom tools and data permissions, and each entity supporting granular create, read, update and delete permissions. On the Wix surface, agents answer using the merchant's live site data. Superagents additionally reach connected business systems. No document ingestion, embedding or vector store, retrieval augmented generation, knowledge base object or citation of sources is described. Sourcedocs.base44.com developer documentation and Wix App Market listingread 2026-07-30 |
|
| Human Oversight & Guardrails | Full |
|
Before a Superagent sends a change to an app it asks for the owner's approval and names the app it is about to change, it asks for approval before installing a skill (answerable Yes or No in WhatsApp), and other actions that need approval are handled in the Superagent in Base44. Security settings carry per-agent permission toggles, with Update data and Delete data advised only when the role needs them; interactive actions run under the chatting user's own permissions; and enterprise admins can block connectors and disable Superagents across the whole workspace. Sourcedocs.base44.com/superagents/customizing-your-superagent and enterprise documentationread 2026-09-29 |
|
| Security, Identity & Governance | Full |
|
The trust center at base44.com/security lists SOC 2 Type II and ISO 27001, plus GDPR. Data is encrypted with TLS 1.2+ in transit and AES-256 at rest, and secrets are held in cloud KMS. The security program covers OWASP based penetration testing, threat modeling, secure design and code review, an active bug bounty and a third party vendor risk program. SSO through the organization's own IdP is enforced across the workspace and every app inside it. SCIM provisioning keeps joiners and leavers in sync, while IP allowlisting and domain based access control limit who signs in and from where. Since October 2026, SSO on a new workspace needs the Business or Enterprise plan. Enterprise workspaces are opted out of model training by default. Sourcebase44.com/security trust center, base44.com/enterprise and docs.base44.com/changelog/productread 2026-10-25 |
|
| Observability & Auditability | Full |
|
Every Superagent workflow run is recorded, with an Activity tab listing each run's date, workflow, status and duration and per-workflow run history, success rate and average runtime, and the agent can be asked in chat what happened in a run; sub-agent tasks are shown in a task panel. An app Logs page records user activity and function calls through to schema and integration changes, an Audit Logs API offers filterable event types, and a Monitoring API with a workspace owned key serves enterprise admins. The app Logs page is described only briefly, and the Superagent run record shows each run's status without listing the actions taken. Sourcedocs.base44.com setting-up-workflows, llms.txt index and enterprise documentationread 2026-09-29 |
|
| Memory & State Persistence | Full |
|
The owner turns Superagent memory on or off and scopes it as separated, remembering facts and history within each conversation, or shared, remembering across all conversations so what the agent learns in one is available everywhere. Under Personalization the user can review what the Superagent has learned about them and delete memories they no longer want it to use, and the agent can change how it uses memory when the owner asks in chat. No retention period is stated. Sourcedocs.base44.com/superagents/customizing-your-superagentread 2026-09-29 |
|
| Deployment & Data Residency | Full |
|
Business and Enterprise workspaces choose where app data is stored: the US, the EU or the UK. Since October 2026 that choice also covers uploaded media. Apps run as a hosted service on continuously monitored private infrastructure at Wix. There is no on premises, air gapped, customer VPC or self hosted option, though two way GitHub sync exports the full source code to the customer's own repository. Sourcedocs.base44.com enterprise documentation and changelog/productread 2026-10-25 |
|
| Prebuilt Agents, Templates & Packs | Full |
|
A template marketplace at base44.com/templates offers more than one hundred ready-made app templates and design layouts built by the Base44 community, with category pages including community and creative tools, and users pick a template, customize it with AI and launch. Base44 suggests browsing the templates, finding one that shares similar workflows, cloning it and asking Base44 to modify it, with a worked example of reusing a project management template's task assignment flow for an event app. Skills are packaged reusable units, with up to ten attachable per agent and workspace skills shared across the workspace alongside app-level skills. These are app templates and reusable skills, and no prebuilt Superagents are offered, so agents are created by generation. Sourcebase44.com/templates and category pages, base44.com blog, docs.base44.com AI agents documentationread 2026-08-31 |
|
| Triggers & Channel Coverage | Full |
|
Superagent workflows run on a schedule, such as every morning or every Monday, or when a trigger happens, such as an email arriving in a connected Gmail account or a change to the agent's data, with Run Now, pause, archive and automatic pausing of repeatedly failing scheduled workflows; app workflows additionally react to data changes, publishes and payments. Superagents are reachable in Base44 chat and over WhatsApp (including groups), Telegram, iMessage, Slack channels with an agent handle, LINE and a Chrome extension, and a message sent on a channel mid-task joins the work in progress. Sourcedocs.base44.com/superagents/setting-up-workflows and customizing-your-superagentread 2026-09-29 |
|
| Model Flexibility & Routing | Full |
|
Users select the model that powers each agent under an AI Model setting, keeping Automatic for fast cost-effective responses or choosing a model from Google Gemini, OpenAI GPT or Anthropic Claude for more advanced reasoning, with the setting applied per agent and switchable at any time. Credit consumption is published per model tier, naming the Automatic default as based on Gemini 3.1 Flash Lite at approximately three credits per message, Gemini 3 Flash at a moderate increase, and higher-end models such as GPT-5.6 Sol for complex analysis. Users on Base44's public feedback forum report that model selection was removed from the builder chat used for coding, which is separate from the agent setting. Sourcedocs.base44.com AI agents for apps documentationread 2026-08-31 |
|
| APIs, SDKs & MCP Extensibility | Full |
|
Base44's developer platform includes a CLI (including agents and agent-skills pull and push), a typed SDK with an agents interface, backend functions, automations, an Apps API, Enterprise APIs, an Audit Logs API and a Monitoring API, personal access tokens, App MCP letting assistants such as Claude, ChatGPT and Cursor work with a published app's data, agents and tools, a documentation MCP and llms.txt index, and bring-your-own coding agent into the app editor. Superagents can be reached with a personal access token. Two-way GitHub sync now exports the full source code, where it once covered only the frontend. Sourcedocs.base44.com/llms.txt and base44.com/pricingread 2026-09-29 |
|
| Testing, Debugging & Optimization | Partial |
|
A real iteration loop exists for the app being built: generate, preview instantly on built in hosting, inspect, and refine either by prompting again or through a visual editor that allows direct click to change edits to layout, copy and styling, with real time collaboration and version control tracking changes. Two way GitHub export lets a team run their own external security tooling and specialized compliance scanners over the generated code. Agents themselves get no evaluation tools, with no harness or sandbox for rehearsing a Superagent against test inputs before it runs live on schedules and real events, no automated scoring and no regression testing when a prompt or integration changes. Third party reviews report that debugging uses build credits without always resolving the problem. Sourcedocs.base44.com, base44.com/security and third party platform reviewsread 2026-07-30 |
|
| Browser & Computer Use | Full |
|
Superagents complete tasks on the web from chat with no setup, in a cloud browser shown in a Live Browser view the user can follow, expand or close while the agent keeps working, with browser actions and data extractions metered per action and failed actions free. Base44's own Superagent Chrome extension lets the agent open tabs, click, type and read pages in the user's own Chrome, in its own tab group under Chrome's control banner and with the user's signed-in sessions, and falls back to the cloud browser when Chrome is not connected. Private network addresses are blocked. Sourcedocs.base44.com/superagents/browser-controlread 2026-09-29 |
|
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
Apps built on Base44 can now open a real browser in the cloud and work on other websites, for example to collect prices or event details, fill in forms or check that the live app still works. The builder asks for it in the AI chat, and the browsing runs in the app's backend functions, which need the Builder plan or higher. Developers can drive the same remote browser from code through a new SDK module, with sessions billed by the minute in workspace credits.
Bears on: Browser/computer use
View sourceA Superagent's browser now stops at a pay button instead of clicking it. Paying needs its own separate approval, and the click only goes through if the button, the amount and the site still match what the user approved.
Bears on: Human approval / guardrails
View sourceAustralia joins the EU and the UK as a region where a Base44 workspace can keep its apps' data, picked in workspace settings. Choosing a data region requires the Business or Enterprise plan.
Bears on: Deployment / data residency
View sourcePricing
From $16 a month billed annually on Starter, or $20 monthly.
Flat monthly or annual tiers, each carrying two monthly credit pools, message credits for building with the AI and integration credits for what the live app does.
Included quota
Starter, the entry paid plan at $16 a month billed annually, includes 100 message credits and 2,000 integration credits a month. Builder at $40 steps up to 250 message credits and 10,000 integration credits and adds custom domains, the GitHub integration with two way sync of the full source code, backend functions and a free domain for the first year.
What is public
Base44, a Wix company, publishes its tiers priced annual or monthly: Free ($0), Starter $16 or $20, Builder $40 or $50, Pro $80 or $100 and Elite from $160 or $200. Annual billing saves about 20%. The billing docs add larger Elite sizes and a Business plan above it, and Business or Enterprise is needed for SSO and data residency on new workspaces. A custom Enterprise option adds a dedicated architect and account support. The tiers are largely a credit ladder, and production features (custom domains, GitHub sync of the full source code, backend functions) unlock at Builder.
Billing mechanics
A flat monthly tier gated by two separate credit pools. Message credits are used when someone prompts the AI to build or edit, about 0.3 of a credit per prompt in discussion mode and more for builds. Integration credits are used at runtime when the live app calls an integration (an LLM call, file upload, email, SMS or image generation), at 1 credit each regardless of type. Neither pool rolls over. Credits cannot be bought separately, so the options are to upgrade or wait for the monthly reset.
Cost watchouts
There are two independent credit pools, and either can block work when it runs out. Credits do not roll over and cannot be topped up separately, error and retry loops burn credits, and third party services connected to apps are billed directly by those providers.
Variable cost rationale
Two things are metered, message credits when the AI builds or edits an app, and integration credits each time a live app calls an LLM, uploads a file, sends an email or SMS or generates an image. Heavier iteration or a busier live app uses more of each pool, and the bill grows by moving up a tier, from 100 message and 2,000 integration credits on Starter to 250 and 10,000 on Builder. The tiers are flat fees with no per credit overage and no top ups, so the bill never runs past the tier price. A pool that runs out stops new builds or live integration actions until the monthly reset or an upgrade, while existing apps keep running. Credits do not roll over, and services connected to an app are billed directly by those providers.
Additional watchouts
Apps depend on the managed backend, so its outages reach them, and browser rendered apps have SEO limits. The published tier is a starting point, and heavy live usage can force upgrades. Code is not locked in, since "Two-way GitHub sync exports the full source code to your own repo at any time."
Overage / add-ons
There is no per credit overage and no top up. Hitting either pool's monthly cap stops new builds (message credits) or live integration actions (integration credits) until the next billing cycle or an upgrade. Existing apps keep running.
Sales call required
Mixed (some tiers require a call)
Free / trial
Free plan at $0 with 25 message credits and 100 integration credits a month, for up to 5 apps
Lowest paid plan
Starter at $16 per month billed annually ($20 monthly), with 100 message credits and 2,000 integration credits a month.
Commercial notes
Annual billing saves about 20%. Education and nonprofit pricing is offered case by case. The backend, database and auth are managed, so there is no separate hosting or Supabase bill. Wix acquired Base44 in 2025 for about $80M.
Key ambiguities
The message credit cost of a build prompt varies with complexity. The Free plan includes 100 integration credits a month, though some listings give 500.
Cancellation / refund
Billed monthly or annually, with 20% off annual billing. Plans can be upgraded, downgraded or cancelled at any time from account settings, and changes take effect at the next billing cycle, so access runs through the paid term. No refund terms are published.
Support SLA / resale
Elite includes premium support, and Enterprise adds a dedicated architect and an account team. The other plans name no support level.
Missing data
Enterprise pricing is custom and quoted on contact. Per prompt message credit costs are not fixed. Paid tiers start at Starter at $16 a month billed annually, and $40 is the Builder tier.
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 Base44
The closest documented capability profiles to Base44 among coding agents tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.
- OpenAI Codex13.0 / 14Matches Base44 across all 14 documented capabilities
- Capy12.5 / 14A lighter documented profile than Base44
- Cognition13.5 / 14Fuller documented coverage on Knowledge Grounding & RAG
- Cursor12.5 / 14A lighter documented profile than Base44
- GitHub Copilot13.5 / 14Fuller documented coverage on Knowledge Grounding & RAG
- Google Antigravity12.5 / 14A lighter documented profile than Base44
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded