Skip to main content Enter
Page view Human readable |
Proto Workflows Headless SaaS
Enterprise
Enterprise Identity, access, deployment, and support controls for contracted environments. Version control Branches, releases, snapshots, and history in the per-app Command Centre.
Enterprise Talk to sales. Deployment, support, security, procurement and commercial terms. Contact sales
Pricing
Search apps — ⌘K / Ctrl K Sign Up
Proto Workflows Headless SaaS
Enterprise
Enterprise home Version control Contact sales
Pricing
Sign Up
Install the ERP.AI skills by running this terminal command:

curl -fsSL https://apps.erp.ai/api/install | bash

When it finishes, reload your skills so they're available, then read https://apps.erp.ai/api/skills.json to see what each one does.

Ask which business system I want to use and what work I need done. Help me connect an existing workspace or choose a system. Read the installed skills to discover the actions available in that system, then help me operate it: read or update records, prepare reports, or run supported workflows. Respect the workspace's permissions and approval settings.

If I need a new system, plan it with me first, then use the build-app skill to build it. If we need an API key, walk me through creating one at https://apps.erp.ai/apps?settings=api-keys — the installed skills explain where to store it.

Headless
SaaS.

One business core.
Every way of working.

One business core for your team, your agents, and the apps you build. Shared data and business logic, through APIs. Each with its own access.

Start with ERP•AI Discover how
YOUR DATA BUSINESS LOGIC SHARED APIs
Shared APIs Business logic Your data
One foundation. Different ways in. Illustrative architecture
The interface is only the beginning.
Explore the foundation
The idea One core, many interfaces

Change the interface.
Keep the business.

Headless SaaS separates business logic from the interface. The interface is the “head”. Data, workflows, and rules live in a shared backend, accessible through APIs.

Add a customer portal, connect an integration, or bring in an AI agent. Each uses the same business capabilities. Change the experience without rebuilding the core.

One record.
Several ways in.

Your team, an agent, or an integration. The same business, with access that belongs to each.

Team workspace
ERP.AI
Customers Business workspace
Selected record
Customer Acme Studio
Account owner
Alex
Status
Active
One record, ready for the next way of working.
Shared business record Illustrative example · sample data

Your everyday workspace

Build apps, work with records, run workflows, and read reports in a complete web product. Your team can start here and keep working here as you connect more ways into the platform.

Start with a complete product. ERP•AI includes a full web app for everyday work. Connect other clients as you grow. The platform keeps data, business rules, and access checks together.

Architecture Connected by design

Many connections.
One foundation.

Every client connects through the gateway. The service that owns the operation checks access and applies the business rules. Change the interface. Keep the foundation.

Choose a client path

Web app

Work with records, workflows, and reports in ERP•AI. The gateway identifies your team; the owning services check access and carry out each operation.

Shared ERP•AI platform services. Select a labelled client path to follow its connections. Select Gateway, a service, or PostgreSQL to inspect its role.
Continue exploring Each operation stays with its owning service.
Architecture notes Services, ownership, and the boundaries between them. Read notes Close notes
Gateway

Authentication, routing, and limits

The gateway accepts a request, resolves the caller and organization context, routes it to the owning service, and applies configured limits.

App Builder API

Apps, data, and app features

The App Builder API owns apps, schemas, records, views, forms, workflows, reports, documents, pages, hosting metadata, and audit events. PostgreSQL is the durable source of truth.

Identity & Permission API

Organizations, users, and permissions

ERP•AI’s identity service handles organizations, users, service accounts, keys, OIDC, SCIM, hosted-app sign-in, domains, and portals. Authentication and enforcement stay with the services; the Permission API owns roles, permissions, assignments, and invitations.

Agent API & Renderer

Agent work and hosted output

The Agent API handles conversations, knowledge, app plans, reports, documents, pages, search, and action approvals. The Renderer serves multi-tenant hosted pages and portals.

Capabilities Ready from day one

A complete product.
Already underneath.

Start with the web app. Everything you build becomes part of the same app model, ready for the clients you connect next.

Explore ERP•AI

Data and interfaces

Create apps with typed tables, records, references, formulas, views, forms, layouts, and collaborative updates.

Workflows

Build workflows, inspect execution state and node output, see errors, stop runs, and retry supported runs.

Reports and documents

Create reports, documents, templates, dashboards, and custom pages on the same app model.

Identity and access

Manage organizations, users, roles, permissions, invitations, service accounts, keys, OIDC, and SCIM.

Hosted experiences

Serve hosted pages, portals, domains, and external apps through the platform's identity and hosting services.

Change and recovery

Use schema branches, commits and merges, snapshots and restore, audit history, workflow run history, trash recovery, and saved page versions where supported.

Access Permission at every step

Open to possibility.
Clear on permission.

Keep your business rules consistent as new clients connect. Whether a request comes from a person or software, the platform identifies the caller and sends the work to the service responsible for it.

Every request has an identity.
Every operation has an owner.
  1. 01

    Know who is asking

    The gateway identifies the caller and organization from a sign-in or service credential. Every request starts with that context.

  2. 02

    Check what they can do

    The service responsible for the resource checks the caller’s access to the requested app, record, workflow, page, or other resource.

  3. 03

    Apply the business rules

    The owning service validates the request and reads or writes the authoritative data. The rules stay with the operation, wherever it starts.

  4. 04

    Leave a trail to follow

    Supported product areas keep audit events, versions, workflow runs, snapshots, or deployment history, giving you a way to inspect the changes they own.

Agent toolkit Beyond the model

An agent needs
more than a model.

Tools to act. Context to reason. Somewhere to run. A record to learn from. Headless APIs connect an agent to your business; these related ERP•AI projects support the work around it.

Proto

Personal agent

Explore Proto

A personal agent for your business.

Brief Proto. It works across your files and tools, then brings the results back. It runs on ERP•AI’s managed plan by default, or on your own key from a provider such as OpenAI, Anthropic, Google Gemini, OpenRouter, or Fireworks.

Proto works with your files and the web on its own. With ERP•AI connected, it can also build and update apps, records, workflows, and reports through the same headless APIs as your web app.

Models Tools Context

Herbert

Identity micro-model Prototype

Identity with boundaries.

Who is asking, what are they trying to do, and how much access does that task need? Herbert brings a small, local model to those questions. Built from the local decision-model code behind SmallDecide, the prototype reviews access requests and recommends scope and review routes for people, agents, service accounts, and hosted apps.

Why it matters

The first experiment is an agent passport: propose read-only access for a short task instead of carrying broad permissions into every job. Herbert recommends; the identity service verifies the caller, approves the scope, and enforces access. Temporary passports, permission previews, and task-bound access are the next directions to explore.

SmallDecide smalldecide.com

Local decision model

Small decisions. Made locally.

SmallDecide runs locally to review a proposed action, route a request, or score against a rubric. It returns structured choices, scores, and probabilities rather than a chat response.

Why it matters

A narrow decision does not always need a large generative model. Your application supplies the context and rules, then decides how to use the result alongside its permissions and approvals.

vmyard vmyard.com

Sandbox scheduling In development

Pause the work. Keep its place.

An agent needs an isolated workspace for code, files, and dependencies. But it may spend much of its time waiting for a person or an API. Keeping a machine running for every waiting agent ties up resources; starting over loses its working state.

Why it matters

vmyard is being built to schedule sandboxes across hosts and manage their run, sleep, and wake cycle. Placement accounts for snapshots and wake-up costs, with the aim of letting agents resume work while sharing capacity efficiently.

FFS ffsdb.com

Graph + vector database Private preview

Context, connected.

FFS brings records, relationships, vector search, and durable writes into one database engine. An agent can retrieve similar material, follow its connections, and write back a result.

Why it matters

Related facts and embeddings need to stay in step. A shared transaction boundary helps agent applications keep the result and the context behind it together. FFS is a related context database; PostgreSQL remains ERP•AI’s authoritative business-record store.

nogrep nogrep.com

Code context retrieval

Read the code that matters.

nogrep follows calls, imports, and other code relationships to retrieve a relevant slice of a repository. Its tools let an agent ask what calls a function or what a change could affect.

Why it matters

Coding agents have a limited context budget. Structural retrieval helps spend it on connected code instead of repeatedly searching and reading whole files.

TraceBreak tracebreak.com

Agent run replay Private beta

Find the first wrong turn.

TraceBreak links plans, tool calls, observations, and memory into an inspectable event history. Replay can compare model decisions under a different model or prompt and reveal the first changed step.

Why it matters

When an agent goes wrong, the final answer rarely explains why. A connected trace lets a team follow the evidence and compare behavior; replay does not execute tool calls by default.

Field notes Inside the platform

Under the surface.

The practical detail behind the shared core.

What the shared services provide

One app model

Tables, columns, records, views, forms, workflows, reports, documents, and pages remain part of the same app.

Named callers

People and configured software clients use identities the platform can check and attribute.

Scoped access

Organization, app, role, resource, and action checks stay with the services that own them.

Durable data

PostgreSQL is the authoritative store; an accelerated record path falls back to PostgreSQL when needed.

Shared business rules

Validation and app behavior live in the platform rather than being reimplemented in each client.

Workflow evidence

Supported workflows keep execution state, output, errors, stop and retry controls, and summaries.

Change records

Branches, commits, merges, snapshots, audit events, page versions, and deployment history cover the changes they own.

Hosted output

Pages, portals, external apps, domains, and their identity settings can be managed as product surfaces.

Separate release cycles

The web app, Proto, hosted output, and integrations can evolve without moving business ownership out of the platform services.

People, software, and supported work

The web app is for people who want to work directly with tables, forms, reports, workflows, documents, and settings. Programmatic clients are useful for repeatable work, integrations, hosted experiences, and agent-assisted tasks.

Both paths still need identity, tenant context, resource permissions, validation, and an owning service.

For direct work

  • Tables, records, and multiple views
  • Forms and record editing
  • Reports and dashboards
  • Workflow building and run history
  • Documents and custom pages
  • Roles, settings, and administration

For connected work

  • Proto, a personal agent for your business
  • Hosted pages and portals
  • External apps
  • Approved integrations
  • Scheduled workflows
  • Scoped service identities

Give each client its own scope.

Connect software with its own credentials and assigned permissions. Your team, an agent, and a portal can use the same platform with different levels of access.

Build on the supported APIs.

Choose the operations your client needs, then use the platform documentation to configure its credentials and requests. Custom clients keep their own interface and release cycle.

Workflows

Turn repeatable work into workflows you can inspect. Follow run state and output, see where an error occurred, and stop or retry supported runs.

How the client model changes

Product use

In the web app
A person uses the ERP•AI web app to build, review, and operate an app.
A connected client
Proto, a hosted page, an external app, or an approved integration can perform permitted work through the same platform services.

The interface changes; the owning services and permission checks do not.

Identity

In the web app
A signed-in user carries organization membership and assigned roles.
A connected client
A configured software caller uses its own credential and assigned scope.

Each caller is identified and checked instead of borrowing a person's browser session.

Operations

In the web app
A person starts work from a table, form, report, workflow, or settings page.
A connected client
A connected client asks the owning service to perform a supported operation.

Business rules stay in the service instead of being copied into every client.

Why the shared service layer matters

The web product stays complete

People can build and run apps through tables, forms, dashboards, reports, workflows, documents, custom pages, and administration screens. Programmatic access does not replace that product.

Access rules stay in one place

The gateway resolves identity and tenant context. The service that owns the requested resource checks access before it performs the operation.

Other clients do not need to copy the product

Proto, hosted pages, external apps, and approved integrations can use the platform services without recreating ERP•AI business logic in each client.

A full product with a reusable service layer

ERP•AI gives you a complete web product and a service layer that other clients can use. Your data model and business logic can serve a team workspace, a portal, an agent, or an integration.

Clients connect through supported operations with their own assigned access. That keeps the core reusable while allowing each experience to evolve on its own.

Questions A clearer picture

A little
more clarity.

What headless changes.
And what it keeps.

How is Headless SaaS different from traditional SaaS?

Headless SaaS makes business capabilities available independently of a single interface. Traditional SaaS can offer APIs too; the useful distinction is how much work another client can do through them. ERP•AI combines a complete web app with shared services that other clients can use through supported operations.

Does headless mean there is no user interface?

No. ERP•AI includes a complete web app for tables, forms, reports, workflows, documents, and administration. Headless means you can also work through another interface, an agent, or an integration. You can use the included product from day one.

Can AI agents and integrations use the same platform?

Yes. Proto is a personal agent for your business that works across your files and tools. Its ERP•AI actions work with apps and their resources. Integrations connect through supported APIs with their own credentials. Each caller’s permissions determine the work it can do.

Does every client get the same access?

No. A team member, an agent, and a customer portal can have different permissions. The gateway identifies the caller and organization, then the owning service checks access to the requested resource. Headless access exposes supported operations, not every internal function.

When should I use Headless SaaS?

When your business needs more than one way to get work done: a workspace for your team, a portal for customers, an agent for supported tasks, or an integration with another system. Reusing the core keeps you from rebuilding the same logic for each. Start with the web app when it fits; add custom clients when their value justifies the integration and maintenance work.

Build once.
Go beyond.

Start with the ERP•AI web app. Bring in Proto, connect your tools, or build an interface of your own. Keep the business you build ready for the way you want to work next.

Start with ERP•AI Explore Proto
ERP.AI

Business apps and Proto, a personal agent for your business.

Products

  • Business Apps
  • Proto
  • Workflows
  • Headless SaaS
  • Platform

Company

  • Company
  • Enterprise
  • Pricing
  • Contact
  • Partners

Resources

  • Resources
  • Documentation
  • Help Center
  • Security
  • Legal
© 2026 ERP•AI. All rights reserved. · Built with Proto
System status

Your Privacy, Your Choice

We use essential cookies to run the site and optional cookies for features, analytics, and relevant content. See Cookie policy

Manage Your Cookie Preferences

We use cookies to enhance your experience, analyze site traffic, and serve relevant content. By clicking "Accept All," you agree to our use of cookies. You can customize your preferences at any time.

Your browser's Global Privacy Control signal is honored: advertising cookies are off.

Learn more about how we use cookies

These cookies are required for the website to function properly. They ensure security, enable basic features like page navigation, and store user session data. You cannot disable these cookies.

These cookies enable additional features that enhance your experience, such as live chat, video playback, personalized content recommendations, and remembering user preferences.

These cookies help us understand how visitors interact with our site by collecting anonymous usage data. This allows us to measure performance, detect issues, and continuously improve the user experience.

These cookies allow us and advertising partners, including X, to deliver ads tailored to your interests. They track browsing habits across sites to provide relevant advertising and measure ad effectiveness.

Meet Proto.Free to use.

A personal agent for your business.

Brief Proto. It works across your files and tools, then brings the results back.

89.5% of attempts accepted on BusinessBench.

Download Proto

Also for macOS Windows Linux

Your own model provider may charge for usage.