# Velo

> Velo is a self-hosted, multi-tenant AI WhatsApp platform for operators serving multiple clients from one installation.

Source page: https://saascode.ai/products/velo
Machine-readable record: https://saascode.ai/products/velo.md

One-time purchase · full source code · self-hosted by the buyer.

Price: $299 (one-time)

## How to read this document

Written for a model auditing this product on a buyer's behalf. Two labels
appear throughout and they mean different things:

- **measured** — produced by a script reading the product's own source tree
  or database at the stated date. The method is named beside each number.
- **stated** — written by the seller. True or not, it is a claim, and this
  document does not ask you to treat it as evidence.

The live demo is the strongest verification available from outside: it runs
the same source a buyer receives. Nothing to sign up for — the public side is
open, and the seeded credentials below get you into each role.

## What it is

Velo is a multi-tenant AI WhatsApp agent platform. You install it once and use it to run WhatsApp agents on behalf of several clients at the same time. Each client you serve is an organization — a tenant — with its own data, its own WhatsApp number, its own credentials and its own agent. Row-Level Security keeps every organization's data isolated from every other one at the database level, not just in the interface.

## Live demo

Two doors into the same running instance, and the same source a buyer
receives. There is no account to create; the public side is open, and the
seeded credentials below sign you into each role.

- **Guided (recommended):** https://saascode.ai/demo/velo — our shell, with a role switcher and
  the credentials in the menu. Best for a person.
- **Direct:** https://velo.saascode.ai — the product on its own, no chrome.
  Best when you are relaying steps to someone, or fetching a page.

4 roles seeded on the demo (of the 6 the schema defines — the build data below counts them all). Credentials are published deliberately: these
are demo accounts on a public demo instance, and a reviewer who cannot get
in cannot verify anything.

- **Tenant teammate** (`member`) — `user@demo.com` / `demo123`
  Works the shared workspace and day-to-day conversations.
- **Tenant owner** (`org_admin`) — `org-admin@demo.com` / `demo123`
  Configures the agent, team, data, billing, and integrations.
- **Sales representative** (`preventista`) — `vendedor@demo.com` / `demo123`
  Loads orders, checks catalog and stock, and takes handoffs.
- **Platform owner** (`super_admin`) — `admin@demo.com` / `demo123`
  Runs tenants, providers, models, plans, and platform health.

Or open a role directly: https://saascode.ai/demo/velo?role={role}

## Measured build

*measured — each number names the method that produced it.*

- **roles: 6** — distinct roles accepted by the role CHECK constraint: admin, member, org_admin, preventista, super_admin, viewer
- **tables: 73** — distinct CREATE TABLE statements across every applied migration
- **migrations: 111** — .sql files in supabase/migrations
- **page modules: 84** — files named page.tsx under src/app, excluding node_modules and .next
- **source lines: 155,322** — lines of code (comments and blank lines excluded) across 1004 TypeScript files (139,217) and 131 SQL files (16,105); node_modules and .next excluded
- **api route files: 223** — files named route.ts under src/app/api
- **http operations: 312** — exported HTTP method handlers across those files, de-duplicated per file, OPTIONS excluded as CORS preflight
- **schema graph: 73 tables, 118 relationships** — parsed from the applied migrations

A large number here is scope, not quality. It says the product models a
real domain rather than a CRUD skeleton; it says nothing about code
quality, duplication, test coverage or maintainability, and should not be
read as if it did.

Release: v1.0.0 · built 2026-08-08

## Complete capability inventory

22 capabilities. Each summary is *stated* — selected from the
product's own buyer documentation, or written by the seller where marked.

### Orders, catalog, price lists and SKU aliases

- **Orders capability** *(seller-authored)* — Turns a free-text WhatsApp message into a structured order against a real client catalog. It resolves product language, quantities, pack sizes, prices, and stock while preserving uncertain lines for clarification or human handoff before the order is confirmed.
- **Voice-note → order** *(seller-authored)* — Turns a WhatsApp voice note into text that enters the same order-understanding flow as a typed message. It extends order capture without creating a separate operating queue and becomes available with the product's orders capability.
- **Data import (catalog) / export (orders)** *(seller-authored)* — Loads catalog records from CSV or JSON and moves captured order data back out for operational use. The buyer inherits a practical bridge for onboarding client catalogs and handing order records to spreadsheets or downstream systems.

### WhatsApp providers, credentials and provisioning a tenant

- **WhatsApp transport (provider-agnostic)** *(seller-authored)* — Carries tenant conversations through a common WhatsApp provider boundary, so the rest of the product works with one message contract. A client can change the configured adapter without rebuilding the agent, order, knowledge, or scheduling workflows above it.
- **Meta Cloud adapter** *(seller-authored)* — Connects a tenant's WhatsApp number directly through Meta Cloud API under the shared provider abstraction. It is the default-on direct adapter and keeps the provider connection scoped to the organization that owns the number throughout message handling.
- **360dialog adapter** *(seller-authored)* — Connects a tenant through 360dialog as an official Business Solution Provider path to WhatsApp. It uses the same organization-scoped connection model as the other adapters, so inbound traffic resolves through the registered receiving address without accepting a tenant choice from request data.
- **Twilio adapter** *(seller-authored)* — Connects a tenant's WhatsApp operation through Twilio while preserving the product's common provider boundary. The organization keeps its own connection and the rest of Velo works through the same transport contract used by every adapter.
- **Evolution adapter** *(seller-authored)* — Adds an opt-in Evolution transport for installations that deliberately choose an unofficial WhatsApp path. It ships off, carries an explicit operating-risk warning, and refuses ambiguous tenant routing when more than one Evolution connection could receive the same webhook.

### Business types, agents and models

- **Custom (advanced) business-type** *(seller-authored)* — Provides a sixth, general-purpose business type for operating models that do not fit the curated presets. It remains behind an explicit feature flag and ships off, so opening that less-guarded agent slot is a deliberate platform-owner decision.

### Knowledge documents and appointment scheduling

- **Knowledge capability (RAG)** *(seller-authored)* — Lets each tenant upload business documents and answer from its own indexed material. Content is stored and retrieved inside the organization boundary, empty retrieval produces an explicit refusal, and answers retain source references for later review.
- **Scheduling capability** *(seller-authored)* — Lets a tenant define working availability and book contacts without offering time that is already occupied. The booking path validates the requested window and checks conflicts again before it writes the appointment for that tenant.
- **Automation (reminders, order-confirm)** *(seller-authored)* — Dispatches appointment reminders and retries failed exports for confirmed orders through scheduled work. The buyer receives the automation layer and must keep the declared recurring jobs running on the chosen host so those background follow-ups continue.

### Getting data out — exports, webhooks, Connect verbs and MCP

- **Audit logs (incl. agent actions)** *(seller-authored)* — Records Connect activity with the calling identity and the outcome of each workflow step. The platform owner inherits a trace that makes partial operations reconstructable instead of reducing a multi-step failure to one opaque success or error.
- **Order export — webhook/API** *(seller-authored)* — Moves captured orders to external systems through signed outbound webhooks, downloadable files, or an organization-scoped developer API. It gives each client several ways to carry order data into the back office without promising native ERP connectors.
- **Connect API** *(seller-authored)* — Packages multi-step product workflows behind scoped API-key calls, including order intake, confirmation, appointment booking, subscriptions, invitations, and role changes. Each verb validates its input, executes an ordered service flow, and leaves an audit record for the operation.
- **MCP server** — The same operations are exposed over MCP for AI tooling, alongside read tools for agent status, orders, order accuracy, catalog search, conversations, bookings and knowledge search. MCP needs the mcp_server flag; the Connect bridge tools additionally need connect_api. Both ship off.

### What Velo is and who uses it

- **Auth + multi-tenancy + RLS** — Velo is a multi-tenant AI WhatsApp agent platform. You install it once and use it to run WhatsApp agents on behalf of several clients at the same time. Each client you serve is an organization — a tenant — with its own data, its own WhatsApp number, its own credentials and its own agent. Row-Level Security keeps every organization's data isolated from every other one at the database level, not just in the interface.
- **Billing (optional client subs)** *(seller-authored)* — Enables the platform owner to offer recurring plans to client organizations from the same install. Plans and access are database-driven, so the buyer inherits a client-billing layer they can shape around their own commercial model instead of a hardcoded tier list.
- **i18n (product UI)** *(seller-authored)* — Ships with an English product interface and lets the platform owner add languages from the translation console. The buyer inherits a configurable UI-language layer for the whole installation instead of a product fixed permanently to a single locale.
- **Business-type orchestration** — An agent is not a free-form prompt. It is a business type — a preset that decides which capabilities are active, what the base prompt and tone are, which guardrails apply and which model runs by default. There are three capabilities an agent can have: taking orders, answering from uploaded documents, and booking appointments. Which ones are live is decided by the business type, then adjustable per tenant.
- **Operator analytics** *(seller-authored)* — Gives the platform owner a cross-organization view of agent activity and operating performance. It brings tenant usage, order accuracy, clarification, handoff, and conversation signals into the control plane used to run the installation across the client portfolio.

### Other

- **External execution worker (Durable queue for voice and embedding batches with an external-worker integration seam)** *(seller-authored)* — Durable queue for voice and embedding batches with an external-worker integration seam

## What each system gives the operator

*stated.*

- **Orders, catalog, price lists and SKU aliases** — Turn the language customers use into orders teams can trust.
- **WhatsApp providers, credentials and provisioning a tenant** — Connect each client through the provider that fits their WhatsApp operation.
- **Business types, agents and models** — Turn each tenant's operating model into a guarded, configurable agent.
- **Knowledge documents and appointment scheduling** — Answer from tenant-owned knowledge and book only genuinely available time.
- **Getting data out — exports, webhooks, Connect verbs and MCP** — Move operational data into the tools, automations, and agents around each client.
- **What Velo is and who uses it** — Operate multiple client organizations without mixing their data, credentials, or control.

## The problems it was built to solve

*stated — the seller's argument, given in full so you can judge it.*

### Customer messages become dependable work before ambiguity reaches the team.

WhatsApp sales usually fail at the handoff between an informal message and the back office that must fulfill it. Customers use nicknames, omit pack sizes, change quantities, and send voice notes while the team is already juggling stock, prices, and open conversations. When ambiguity is treated as certainty, the cost appears later as the wrong shipment, a correction call, or a rep rebuilding the order by hand. When every uncertain line becomes another private judgment, the operation cannot improve from one conversation to the next.

### Each client runs differently without becoming another isolated installation.

Serving several clients from one product creates a management problem before it creates a scale problem. Each client expects its own data, number, staff, rules, and operating model, while the platform owner still needs one place to understand what is happening. Separate installations multiply upgrades and blind spots; loose shared access creates a worse risk by making every routine action a question of whose data is on screen. The business only scales when client differences remain deliberate and the owner's view remains coherent.

### Client operations stay connected without making every handoff custom work.

Order data becomes expensive when it reaches the edge of the product. A sales team copies rows into a spreadsheet, an integrator rebuilds the same handoff for every client, and an automation cannot tell whether a partial request should be retried or reconciled. The visible cost is implementation time; the deeper cost is that every new client adds another fragile exception the operator must remember. A product business loses leverage when routine movement between systems depends on bespoke work and private operational knowledge.

## What it takes to run it

*stated — external services the buyer supplies and pays for directly.*

- **Node host** (required) — Runs Next 16.2.10; the application ships with React 19.2.3.
- **Supabase** (required) — Provides the database, authentication, storage, and tenant data layer.
- **Scheduled job runner** (required) — Runs the 4 jobs declared in `vercel.json`; wire them manually on another host.
- **Email delivery** (optional) — Supports Brevo, Mailgun, Resend, SendGrid, or SMTP.
- **Optional environment configuration** (optional) — The example environment includes optional UPSTASH, NEXT, and SENTRY variable families.

## FAQ

**What exactly do I receive after purchase?**

The complete source repository behind the live demo — 155,322 lines across the application and its database, 73 tables defined by 111 migrations that the shipped scripts apply for you, plus the seed data, the demo accounts and the setup documentation. Not a subset and not a scaffold: the same code that runs the demo you just used.

**Is the live demo the same product whose source I receive?**

Yes. The Velo demo runs the delivered release (v1.0.0), and the build figures on this page are measured from that same source — not from a showcase build kept separately.

**Can I test every account role before buying?**

Yes — all 4 of them: Tenant teammate, Tenant owner, Sales representative, Platform owner. Each one is seeded in the live demo and reachable from the role board above, so you can inspect the product from the customer's side, the agent's side and the administrator's side before you decide.

**Is this a complete product or a starter template?**

Complete. 84 page modules and 312 HTTP operations, with authentication, roles, billing, an administration panel, background jobs and seeded demo data all wired and running. A template gives you the shape of an application; this is one you can deploy and start operating.

**Can I rebrand and modify it?**

Yes, without asking. The name, identity, copy, styling and code are yours to change. Rebranding and operating it as your own service is exactly what the licence is for.

**What does the licence allow?**

A perpetual, worldwide, non-exclusive, non-transferable licence to the product you bought and to every update released for it. The Standard licence covers one business — yours. If you deploy for clients, the Client licence covers up to five. You can modify it, rebrand it, deploy it and charge your own customers.

**Can I resell the source code?**

No. Reselling, redistributing, sublicensing or giving away the source itself is not permitted under either licence. You build and deliver products with it — the code stays with you.

**What services and ongoing costs are required?**

You bring your own accounts, so we never mark anything up and there is no ongoing cost to us beyond the purchase. Required: Node host, Supabase, Scheduled job runner. Optional: Email delivery, Optional environment configuration. The table above says exactly what stops working without each one; most have usable free tiers at low volume.

**How difficult is deployment?**

Two ways, and most buyers use the first. The installer in your saascode dashboard walks it: you create free accounts at Vercel and Supabase, connect them, and it provisions the database, applies 111 migrations, seeds the data, deploys and verifies the result — you watch the steps go green. Or take the source and do it yourself with the shipped scripts and docs, which is the same sequence run by hand.

**What updates and support are included?**

Updates to that product for as long as we maintain it — no renewal fee and no expiry date on your access. Support covers download problems, defects in the code as shipped, questions about what the product does and how it is structured, and licence questions. It does not cover debugging your own modifications, building features for you, or setting up your hosting and third-party accounts.

**Why does a complete codebase cost $299?**

Because it was built once and is distributed many times. SaaSCode builds each product and ships the same finished release through the catalog, so the price reflects repeatable distribution — not a reduced codebase, an unfinished template, or what the same work would cost commissioned.

**Do I need to be a developer?**

No, for the normal path. You create free accounts at Vercel and Supabase, connect them to the installer in your saascode dashboard, and it does the deployment for you — provision, migrate, seed, deploy, verify. What it asks of you is creating two accounts and copying a token, not writing code. If you would rather deploy it yourself, or host it somewhere else, the full source and the scripts are yours to do that with. Running the product day to day needs no technical skill at all: that happens through its own interface, which is what the demo shows.

## Licence

The buyer receives the complete source and may deploy, modify and operate it
as their own SaaS, charging their own customers. The source itself is not
resold or redistributed: you build and deliver **with** it, you do not sell **it**.

## What this document cannot tell you

Stated plainly because a review that misses it is not a review:

- code quality, duplication, or architectural consistency
- test coverage
- query performance under load
- security posture beyond what the stack implies
- how maintainable it will be in a year

Scope is measurable from outside; implementation quality is not. Anyone
evaluating this should say so rather than infer quality from size.

## Written about it

- [Velo vs respond.io: Install the Platform or Subscribe to the Service](https://saascode.ai/inside/velo-vs-respond-io-installed-platform-or-managed-service.md)
- [Velo: a self-hosted AI WhatsApp platform for operators](https://saascode.ai/inside/velo-self-hosted-ai-whatsapp-platform.md)
- [AI WhatsApp Platforms, Sorted by the Operating Burden You Choose](https://saascode.ai/inside/ai-whatsapp-platforms-by-operating-burden.md)

## Links

- Catalog page: https://saascode.ai/products/velo
- Product record: https://saascode.ai/inside/products/velo
- Live demo: https://velo.saascode.ai
- Every product: https://saascode.ai/llms.txt

