Base44 vs Emergent (2026)

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

The build agent wires outside services into each app in two ways. Integrations with a playbook follow a tested setup recipe for services such as Stripe, PayPal, Shopify, Razorpay, Paystack, SendGrid, Resend, Twilio, ElevenLabs and the OpenAI, Anthropic and Google models, and a few bill a small credit fee per run.

Anything else with a public API is coded in against the customer's own key. Teams can also register their own MCP servers under Manage Agents, giving the agent tools to read schemas, run queries, post to Slack or open Jira tickets while it builds. Servers are entered as JSON in the mcpServers format, and each tool list is cached for five minutes.

Sourcehelp.emergent.sh/connect-your-toolsread 2026-10-09

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

Every conversation runs as a long lived Temporal workflow in which the agent reasons, calls a tool, reads the result and repeats, up to 10,000 tool calls per message and four hours of wall clock time. A main agent plans the work and spawns subagents for testing, design, code review and integration setup, which run in parallel workflows and report back.

Three agents set the workflow when a job starts: E-1 builds step by step, E-2 checks that the pieces it builds fit together, and E-3 runs E-1 as a subagent under its own loop for large, open ended goals. Runs end on named stop reasons such as end_turn, handoff, max_iterations and insufficient_credits, and a handoff passes the task to another agent.

Sourcehelp.emergent.sh/how-the-agent-runs-workflow-stop-reasonsread 2026-10-09

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

Work reaches the builder when a person sends a message. A builder picks an app type (Full Stack App, Mobile App, Landing Page or Brainstorm), chooses an agent and types a prompt in the web workspace at app.emergent.sh or its mobile web app, and a new job can also start from an imported GitHub repository. In Plan mode the build waits until the plan is approved. On the self serve plans nothing starts a build on a schedule, a webhook or an event, so the agent works only while someone is driving it. The apps it makes can run scheduled jobs of their own once published.

Sourcehelp.emergent.sh/start-with-your-idearead 2026-10-09

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

Each build draws on the job's own material: the whole conversation, the workspace code and files, the database structure, the key names in .env, and files attached to chat such as screenshots, Figma exports, PDFs, CSVs and specs. MCP servers add schemas, documents and live rows from outside systems. Pro raises the context window to one million tokens, long chats are compacted automatically, and a fork starts from an editable summary of the history. Context is gathered for each run from these sources, and the builder keeps no searchable index of a company's wider documents.

Sourcehelp.emergent.sh/a-tour-of-the-workspaceread 2026-10-09

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

Each job keeps its chat, code and build state across sessions, so a builder can close the workspace and come back, and the agent reads the whole conversation on every turn. Workflow state persists in Temporal, so an interrupted run resumes where it left off, and a job paused at zero credits picks up again once the balance is topped up. Less carries between jobs.

A fork condenses the history into a summary the builder can edit, early details can fade after repeated compaction, and subagents start fresh on every turn. What the agent knows about a builder or team in a new job is whatever sits in the code, the forked summary or the files attached to chat.

Sourcehelp.emergent.sh/checkpoints-undo-anythingread 2026-10-09

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

Plan mode, switched on in the composer, returns a plan card with two buttons, Request changes and Looks good, let's build it, and nothing is built until the builder approves.

Build mode, the default, starts as soon as a prompt is sent, Plan mode is unavailable in Brainstorm and E-3 sessions, and in autonomous runs a feature called Auto-HITL answers the agent's own questions with sensible defaults so the run never pauses.

Spending and release controls sit beside the plan step: a maximum credit cap per prompt that asks before going over, a budget per session, cancel from the chat menu, and a live app that changes only when someone publishes it again.

Sourcehelp.emergent.sh/talk-it-throughread 2026-10-09

Base44's trust center at base44.com/security lists SOC 2 Type II and ISO 27001, plus GDPR. Data is protected by TLS 1.2+ in transit and AES-256 at rest, with secrets held in cloud KMS, and the program includes OWASP-based penetration testing, threat modeling, secure design and code review. There is also an active bug bounty program and a third-party vendor risk program covering every supplier.

SSO through the organization's own IdP is enforced across the workspace and every app inside it, alongside SCIM provisioning with automatic joiner and leaver sync, OAuth 2.0 connectors, IP allowlisting by address, range and subnet, and domain-based access control. Enterprise workspaces are opted out of model training by default. Two-way GitHub export lets a customer run their own security and compliance scanners over the generated code. The platform runs on Wix's enterprise security infrastructure.

Sourcebase44.com/security trust center and base44.com/enterpriseread 2026-07-30

Projects have four roles. Owners control billing, plan and deletion, Admins manage settings, members, the database and domains, Members chat with the agent and publish, and Viewers, on Enterprise only, see the app and its history.

Business adds single sign on through SAML or OpenID Connect and role based access control, Enterprise adds user groups and workspace wide two factor enforcement, and anyone can review and revoke active sessions. Emergent holds ISO 27001:2022 and SOC 2 Type I, with GDPR alongside them in its trust center, and its DPA sets out technical measures, breach notice within 72 hours and audit reports on written request. Secrets are encrypted at rest and data in transit, and customer personal data is kept out of model training under the DPA.

Sourcehelp.emergent.sh/team-roles-permissions-collaborationread 2026-10-09

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

While an app builds, the workspace shows the agent's activity live: each tool call with the arguments passed and the result returned, subagent logs nested under the main agent that expand to show their own calls, the step count for the turn and the credits being spent.

A checkpoint is saved after every agent turn, publish history keeps up to three earlier production images tagged with a timestamp, and Account Settings breaks credit use down by agent runs, publishes and Universal Key calls. Enterprise adds audit logs and credit usage reports with an analytics dashboard. How long the Enterprise audit log keeps entries is unclear.

Sourcehelp.emergent.sh/custom-agentsread 2026-10-09

Enterprise workspaces can choose where workspace app data is stored, across the US, EU or UK, to meet data sovereignty and compliance requirements, and applications are hosted on continuously monitored private infrastructure. No on-premises, air-gapped, customer VPC or self-hosted deployment is offered, and the platform runs as SaaS on Wix infrastructure. Two-way GitHub sync exports the full source code to the customer's repository.

Sourcedocs.base44.com enterprise documentation and base44.com pricing FAQread 2026-09-29

Emergent runs as a hosted service, and customer data is processed and stored in the United States, the EU and India under its DPA. Builders choose the hosting region of a published app themselves, US or EU, in the Resources tab of Manage Publishing, with the EU priced higher. App databases run on MongoDB Atlas in the United States unless moved.

Enterprise deploys apps into the customer's own cloud through a VPC setup and supports a self hosted database, and any published app can move to the customer's own MongoDB by a manual runbook. The build platform and its subprocessors stay where they are whatever region an app uses, and EU only hosting for all data goes through a request to the privacy team.

Sourcehelp.emergent.sh/where-your-data-is-storedread 2026-10-09

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

New jobs start from four app types, Full Stack App, Mobile App, Landing Page and Brainstorm, each on its own stack template (React with FastAPI and MongoDB, Next.js, Python only, or Expo for mobile), and from a choice of three build agents, E-1, E-2 and E-3, which are levels of one builder.

Integrations with a playbook package a tested setup recipe for each supported service, and the build page offers example prompts for websites, mobile apps, dashboards and SaaS tools. On Pro, builders make their own custom agents in a four step wizard covering the system prompt, tools and subagents. There is no gallery of finished apps or ready made agents to clone.

Sourcehelp.emergent.sh/how-apps-work-here-mental-modelread 2026-10-09

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

Two choices shape a build. The agent dropdown sets the workflow, and a separate model selector picks the LLM that powers it, offered again when a fork opens, so a builder can move to another model when a provider slows down. Pro adds Ultra thinking and Maxx mode, a deeper reasoning toggle that costs significantly more credits.

Model providers in the data path include Anthropic, OpenAI, Google Gemini, xAI and Groq. The Universal LLM Key, which reaches 44 or more models from seven providers on Emergent credits or the customer's own provider keys, serves the apps being built rather than the builder.

Sourcehelp.emergent.sh/understanding-models-e1-e2-e3-maxxread 2026-10-09

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

Emergent also works as an MCP server for clients such as Claude Desktop or Cursor, with example tools that create an app from a prompt, publish a workspace and fetch build or runtime logs, and personal access tokens with scoped permissions reach an Emergent API. The server's address and full tool list are not given alongside those examples, so how much of the platform outside code can drive is unclear. On paid plans the Universal LLM Key also works as a LiteLLM compatible proxy for calling models from scripts and CI, restricted by IP, and code leaves through Save to GitHub.

Sourcehelp.emergent.sh/mcps-connectorsread 2026-10-09

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

Testing sits in the agent's own toolset. A testing subagent, called through a run_tests tool or when a builder asks for it, writes unit, integration and end to end tests for the app, runs them and reports coverage, and when a test fails the agent fixes the code and runs the tests again.

E-2 adds a workflow that proves the services it builds actually work together, a Codex review subagent lints and scans pull requests for security and style, and testing runs include visual regression scans.

Builders can ask for specific checks, such as the checkout flow end to end, results show in chat with what failed and why, and mobile apps get TestFlight and APK test builds on paid plans.

Sourcehelp.emergent.sh/debugging-testing-with-the-agentread 2026-10-09

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

Agents can carry out tasks in a hosted web browser run by Browserbase, seeing and typing on pages, including ones the user is signed into, and content viewed or entered there is part of the data the platform processes. Firecrawl fetches web pages as a separate agent tool, and web search costs a small credit fee per query. Inside the app builder, the browser work Emergent describes is the preview server screenshotting the app under construction for the agent to check, so whether the builder drives the hosted browser on outside sites is unclear.

Sourceapp.emergent.sh/privacy-policyread 2026-10-09