How much does AgentUI cost?

Free plan with pay as you go credits at $0.30 each and 3 projects. Solo is $22.50 a month billed yearly ($25 monthly) with 90 credits, Builder $45 ($49.99) with 200 credits and 2 members, and Team $88 ($99.99) for 10 members with 400 credits, SQL integration and unlimited apps, scaling to 25 and 50 member tiers. Enterprise is custom with private deployment and SSO. Credits are spent only while building.

Does AgentUI support MCP and tool calling?

Full under the Agentic Index verification standard. AgentUI publishes public evidence of Model Context Protocol (MCP) support, tool calling, and API or SDK extensibility for connecting agents to external tools. Evidence basis: An interface to the vendor's own platform: the AgentUI CLI returns JSON for every command so an outside agent such as Claude Code or Cursor can query an app's database, invoke a function and ship, and the help center has an API and Database. Graded from public evidence only against the Agentic Index 14 point capability taxonomy. No vendor pays for placement.

Does AgentUI have SOC 2, SSO and role based access control?

Full under the Agentic Index verification standard. AgentUI publishes public evidence of enterprise security and identity controls, covering a compliance posture such as SOC 2 or ISO 27001, single sign on (SSO or SAML), and role based access control (RBAC). Evidence basis: AgentUI shows a SOC 2 certified badge, states a GDPR posture and encryption, and runs a trust center; users carry specific roles, including a compliance officer role, with shared secrets and audit logs, and SSO on Enterprise. The limit: the. Graded from public evidence only against the Agentic Index 14 point capability taxonomy. No vendor pays for placement.

Can AgentUI be self hosted or run in a private VPC?

Partial under the Agentic Index verification standard. AgentUI publishes some public evidence on deployment and data residency, but narrower than a documented self hosted or private VPC option. Evidence basis: Managed hosting with an undefined private option: apps run on AgentUI's built in hosting, and Enterprise lists private deployment. Where or how private deployment runs is not described, and no region choice or self hosted install is documen. Graded from public evidence only against the Agentic Index 14 point capability taxonomy. No vendor pays for placement.

Back to vendors

AgentUI

Q: Who is AgentUI for?

SMB, operations teams, freelancers, agencies, retail and distribution

Also known as: AgentUI, Agent UI, agentui.ai, AgentUI CLI

Visit site

Coding agentindependentVerified 2026-10-02

Entry price$22.50/mo yearly ($25 monthly), Solo · free planFull pricing detail

Managed AI app builder for operations teams that generates and hosts internal tools with a human support team behind them, audit logs, role based access, a SOC 2 badge and a JSON CLI for outside coding agents.

AgentUI is a managed AI app builder for operations teams that pairs its AI with a human support team. A builder describes the operation, such as inventory, approvals, reporting or multi location control, and the AI generates the screens, workflows, logic and database. The app goes live on AgentUI's hosting right away, and AgentUI's staff review the tool, connect the customer's systems and help as requirements change.

The platform's governance features are aimed at teams leaving spreadsheets: global audit logs of every edit, role based users, a compliance officer role, an internal portal that lists every tool, shared databases and shared secrets. AgentUI shows a SOC 2 badge, states GDPR compliance and runs a trust center, and Enterprise adds private deployment, SSO and security dashboards.

For developers, an AgentUI CLI returns JSON to outside coding agents so they can query an app's database, invoke a function and ship without relaying output by hand. AI credits are spent only while building; live apps run without consuming them.

Public documentation is thin. The help center covers chat best practices, users, domains, environments, databases and skills, but no page documents how the AI acts in outside systems, which model it uses, or any testing or approval controls for the AI's changes.

Vendor details

Canonical URL

https://www.agentui.ai

Subcategory

Managed AI app builder for operations

Funding status

Private. Funding is not stated on AgentUI's own pages.

Company status

independent

Use cases & customers

Primary use cases

inventory and stock control appsapproval workflows with audit trailsoperational reporting dashboardsmulti location operations toolsclient portals built by freelancers and agencies

Target customers

SMBoperations teamsfreelancersagenciesretail and distribution

Deployment options

AgentUI managed hostingprivate deployment (Enterprise)

Integrations

Generated apps send email, use WhatsApp, call any external API and read and write existing SQL databases, with Shopify, Google Sheets, Odoo and Salesforce pages on the site. An AgentUI CLI returns JSON so outside coding agents such as Claude Code or Cursor can query an app's database, invoke a function and ship.

In practice

A distribution company describes its stock process and gets an inventory app with low stock alerts and movement history, then AgentUI's team connects it to the existing SQL database.

An operations manager replaces a spreadsheet of purchase approvals with an approvals app whose every edit lands in the global audit log.

A developer points Claude Code at the AgentUI CLI to query an app's database and ship a change.

Sources & related URLs

Related / legacy domains

https://help.agentui.ai https://trust.agentui.ai https://www.agentui.ai/en/agentui-cli/

Research sources

https://www.agentui.ai https://www.agentui.ai/en/pricing/ https://help.agentui.ai/

Agentic Index coverage score

6.0 / 14 capabilities · 43%

Integrations & Tool Calling	Partial
Integrations wired into generated apps: the AI builds screens, workflows, logic and database wired to the customer's data, and apps send email, use WhatsApp, call external APIs and read and write SQL databases. No page documents the builder AI executing actions in outside systems itself. AgentUI homepage FAQ and pricing table, 2 Oct 2026. Sourceagentui.airead 2026-10-02
Workflow Orchestration	Partial
Multi step generation inside one builder: the AI produces screens, workflows, logic and database for an app, and apps can include backend functions. No multi agent execution or orchestration of the AI within workflows is documented. AgentUI homepage and pricing table, 2 Oct 2026. Sourceagentui.airead 2026-10-02
Knowledge Grounding & RAG	Unable to verify
No retrieval or grounding layer for the AI is documented. The help center has a collection on using skills in AgentUI, which may hold reusable instructions rather than knowledge, so ask what skills contain. AgentUI help center index, 2 Oct 2026. Sourcehelp.agentui.airead 2026-10-02
Human Oversight & Guardrails	Partial
Human review by the vendor and environment separation: AgentUI's team reviews generated tools and connects systems, and Team plans add a second environment. No customer approve step before the AI's changes commit is documented. AgentUI homepage and pricing table, 2 Oct 2026. Sourceagentui.airead 2026-10-02
Security, Identity & Governance	Full
AgentUI shows a SOC 2 certified badge, states a GDPR posture and encryption, and runs a trust center; users carry specific roles, including a compliance officer role, with shared secrets and audit logs, and SSO on Enterprise. The limit: the attestation rests on a badge, so ask for the SOC 2 report through the trust center. AgentUI pricing page, homepage and help center index, 2 Oct 2026. Sourceagentui.ai/en/pricingread 2026-10-02
Observability & Auditability	Partial
Audit logs for user edits: global audit logs record who changed what and when, with 7 day retention on the 25 and 50 member Team tiers and unlimited on Enterprise, plus custom audit logs inside apps. A record of the builder AI's own steps is not documented. AgentUI pricing table and homepage, 2 Oct 2026. Sourceagentui.ai/en/pricingread 2026-10-02
Memory & State Persistence	Partial
Conversation state within a chat, with guidance on starting new chats for new tasks. No memory layer with a stated scope and lifetime is documented. AgentUI help center index (best practices for AI chat), 2 Oct 2026. Sourcehelp.agentui.airead 2026-10-02
Deployment & Data Residency	Partial
Managed hosting with an undefined private option: apps run on AgentUI's built in hosting, and Enterprise lists private deployment. Where or how private deployment runs is not described, and no region choice or self hosted install is documented. AgentUI pricing page and homepage FAQ, 2 Oct 2026. Sourceagentui.ai/en/pricingread 2026-10-02
Prebuilt Agents, Templates & Packs	Partial
The site links Blueprints and maintainable blueprints for consultants, and use case pages describe inventory, approvals and reporting apps. No blueprint catalog is described. AgentUI homepage navigation, 2 Oct 2026. Sourceagentui.airead 2026-10-02
Triggers & Channel Coverage	Partial
User initiated only: builders reach the AI through the chat in the app, and outside coding agents can work through the AgentUI CLI. Nothing starts the AI without a person. AgentUI homepage, 2 Oct 2026. Sourceagentui.airead 2026-10-02
Model Flexibility & Routing	Unable to verify
No model choice and no provider disclosure: the pricing page describes AI credits without naming the models behind them, and no selection or bring your own key option is documented. AgentUI pricing page and homepage, 2 Oct 2026. Sourceagentui.ai/en/pricingread 2026-10-02
APIs, SDKs & MCP Extensibility	Full
An interface to the vendor's own platform: the AgentUI CLI returns JSON for every command so an outside agent such as Claude Code or Cursor can query an app's database, invoke a function and ship, and the help center has an API and Database section. The limit: the CLI's coverage is described on the homepage rather than in a command reference, so ask for the reference. AgentUI homepage and help center index, 2 Oct 2026. Sourceagentui.airead 2026-10-02
Testing, Debugging & Optimization	Unable to verify
No testing, evaluation or self check capability for the AI is documented. AgentUI's human team reviews tools and makes sure they work, which is a support service rather than a product feature. AgentUI homepage, 2 Oct 2026. Sourceagentui.airead 2026-10-02
Browser & Computer Use	Unable to verify
No browser, desktop or remote computer control by the AI is documented. AgentUI homepage and help center index, 2 Oct 2026. Sourceagentui.airead 2026-10-02

The Agentic Index coverage score grades every vendor Full, Partial or Unable to verify 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

Pricing

$22.50/mo yearly ($25 monthly), Solo · free plan

flat plan by team size with monthly AI credits; pay as you go credits on Free

Free tierTrial available

Included quota

Solo: 90 credits, 5 projects, 1 member. Builder: 200 credits, 10 projects, 2 members. Team: 400 credits for 10 members, 1,000 for 25, 2,000 for 50, unlimited apps.

What is public

All plan prices, credit allowances, per credit rates, member caps and a feature comparison are published on 2 Oct 2026. Enterprise is custom.

Billing mechanics

Monthly or yearly (10 percent off) plan fees sized by internal members and projects, with an included monthly credit allowance; live apps do not consume credits.

Cost watchouts

Credits are spent whenever the AI generates screens, logic or workflows; the site estimates 90 credits at roughly 5 to 9 app screens. Audit log retention is only 7 days below Enterprise, and internal users are capped by tier.

Variable cost rationale

Plan fees are fixed and published, and credits are metered at published per credit rates, but consumption per build varies with app complexity.

Additional watchouts

Credits are spent only during building. Inference, not stated by the vendor: the cost profile front loads into the first months of a project.

Overage / add-ons

Per credit rates are listed per plan ($0.30 Free, $0.28 Solo, $0.25 Builder and Team).

Sales call required

Mixed (some tiers require a call)

Free / trial

Free plan with 1 member and 3 projects, AI credits pay as you go at $0.30 each

Lowest paid plan

Solo at $22.50 a month billed yearly ($25 monthly)

Commercial notes

Self serve through Team; Enterprise through sales with a dedicated support engineer. White glove onboarding is included.

Key ambiguities

Whether extra credits on paid plans are bought at the listed per credit rates is implied but not stated outright.

Missing data

Enterprise pricing is not published.

Agentic Index verified 2026-10-02

Official pricing page

Data confidence: low