VxAI
Home Contact Us
Beta

7 AI engineers.
One prompt.

Supercharge your SDLC with AI agents. They plan, design, code, test, secure, deploy and maintain. You stop prompting. The work just lands.

Install in 60 seconds Watch a 12-second demo
7
Specialist agents
10+
Models · Anthropic + OpenAI
4
Doc formats auto-extracted
$0
To install & try
12-second demo

One prompt in.
A shipped feature out.

Type a request. Watch agents do the work. Real files, real tests, real cost. Same flow that runs in your terminal.

~/projects/payments-api — vxai
running
Orchestrator
Master
idle
PLAN
writes the spec
DESIGN
picks architecture
DEV
writes the code
TEST
runs the tests
SEC
scans for issues
SHIP
sets up deploy
MAINT
adds monitoring
Event stream +0.0s
Tokens
0
Cost
$0.000
Files changed
0
Tests

Looping preview. Your terminal runs the same chain.

The problem

One AI cannot ship
a whole feature.

A single chatbot writes a function then stops. You become the project manager. VxAI fixes that.

Generalist AI skips the boring parts

You ask for a feature. You get a function.

No spec. No tests. No security check. You spend the rest of the day prompting it into shape.

VxAI: Seven specialists run end to end. Plan, design, code, test, secure, deploy, maintain. Each with a workflow it cannot skip.
The AI forgets your project

Same context, pasted into every chat.

Your spec PDF, your conventions, your domain notes. Every new session starts from zero.

VxAI: Pin docs (PDF, Excel, Word, CSV) and rules per project. Every agent reads them on every turn.
One model for every job

You pay flagship rates for trivial tasks.

Most CLIs lock you to one model. So you either overpay on cheap work, or underperform on hard work.

VxAI: Pick a different model per agent. Claude or GPT. Opus for design, Haiku for tests, GPT-4.1 for code.
Cost only shows up on the invoice

You burn $50 on a chat and find out next month.

Most tools hide tokens behind a one-line summary. You cannot budget what you cannot see.

VxAI: Live per-query tokens and cost in your terminal. Prompt caching on by default to cut repeat input ~10x.
What you get

Six things that
actually move the needle.

A real chain, not a chat

Master breaks your request into phases and runs each specialist with its own workflow. No skipped steps, no "I forgot the tests".

01

Mix any model, any vendor

Claude Opus for design. GPT-4.1 for code. Haiku for tests. Both Anthropic and OpenAI in one tool. Pick per agent.

02

Project memory, built in

Rules, pinned docs and notes per project. PDF, Excel, Word and CSV extracted to text. Every agent reads them every turn.

03

See the cost while you work

Live tokens and dollars per query in your terminal. Prompt caching on by default. No invoice surprises.

04

Real tools, real artifacts

Agents read, write, grep, and run shell commands inside your working directory. Real diffs, real test runs, real CI files.

05

Local first

Your keys, code and history stay on your machine. Tool calls sandboxed to the working directory. Only prompts go to the model.

06
Project context

Curated context.
Carried on every run.

Nothing is auto-scanned. You pin the docs, you write the rules, you save the facts. VxAI carries that curated context into every agent run, so your security policies and conventions never drift.

Read the detailed Context study →

Rules you enforce

Hard constraints applied on every turn. "Never log secrets or PII." "Use Prisma, never raw SQL." Written once, enforced on every run.

Documents you approve

Nothing auto-ingested. You pin a PDF, Excel, Word or CSV and VxAI extracts the text once. The team reads only what you approve. Nothing silent.

Facts you save

Project truths the team carries forward. "Prod DB is read-only." "All endpoints require JWT auth." Saved once, never re-explained.

~/projects/payments-api — /context
Used by VxAI · 3 files · 5,842 tokens · ~$0.018 per query
Documents
01. PDF stripe-checkout-spec.pdf 84 KB 14 pages
02. XLSX pricing-tiers.xlsx 12 KB 3 sheets
03. MD ARCHITECTURE.md 6 KB live read
Rules
1.Always run typecheck before finishing a task
2.Use Prisma for DB queries, never raw SQL
3.Keep responses under 10 lines unless asked
Memories
01Prod DB is read-only, writes go through /orders only
02Stripe webhook secret lives in STRIPE_WEBHOOK_SECRET
The team

Eight roles.
One terminal.

Orchestrator

Master

The agent you talk to. Reads your request, splits it into phases, and routes each one to the right specialist. Then puts the answer together.

Phase 01

Planning

Turns a fuzzy ask into a real spec. User stories, acceptance criteria, scope. Saves it to docs/planning/.

Phase 02

Design

Architecture, file tree, APIs, data shapes, trade-offs. The blueprint the developer follows.

Phase 03

Developer

Reads files before editing them. Writes real code, no TODO stubs. Runs typecheck before saying done.

Phase 04

Testing

Picks the test runner, writes happy-path and edge cases, and iterates until everything passes.

Phase 05

Security

OWASP scan, secret leaks, dep audit, compliance cues for SOC 2 and friends. Returns severity, file, line and fix.

Phase 06

Deployment

GitHub Actions, Dockerfiles, release scripts. Pinned versions. No hardcoded secrets. Rollback plan included.

Phase 07

Maintenance

Bug triage with root cause and smallest fix. Or tech-debt audits, ranked by priority and effort.

How it works

Three steps. That's it.

01
Set up

Paste your key. Pick your models.

Open /settings, drop in an Anthropic or OpenAI key (or both), pick a model per agent. Saved locally at ~/.vxai/settings.txt.

02
Ask

Type what you want, in plain English.

"Add Stripe checkout." "Audit for SOC 2." "Fix the failing test." Master decides if it's a chat or a chain.

03
Ship

Watch seven agents finish the work.

Tool calls visible live. Real files, real tests, real cost on screen. Press Esc to cancel anytime.

Bring your own model

Multiple providers.
Zero lock-in.

Pick any model per agent. Switch any time. Forget your key for a model? VxAI tells you in plain English instead of crashing.

Anthropic

All current Claude models with prompt caching on by default. One key, every Claude-routed agent.

Opus 4.6 Sonnet 4.6 Sonnet 4.5 Haiku 4.5 Haiku 3.5

OpenAI

GPT-4.1, GPT-4o, o4-mini and their mini variants. Tool calls translated under the hood. Same agent workflow either way.

GPT-4.1 GPT-4.1 mini GPT-4o GPT-4o mini o4-mini

Try it in your
next terminal session.

Local install. Your keys, your machine, your code. Beta

$npm install -g @venex/vxai
$vxai launch

No credit card · Bring your own Anthropic / OpenAI key · Settings stay local in ~/.vxai/