AgentNeo
Agents that actually ship—
and ship safely.
AgentNeo builds AI agents and takes them all the way to production. Seven are live below, working for real businesses — and we open-source the safety layer behind them.
The tooling behind these accounts is single-operator — runs locally, posts on behalf of one human.
Your Best EmployeeFeatured
A hireable team of 4 AI employees — reception, sales, social & coordination — answering every message 24/7. The whole flota, as one team.
Luz Vera
Our flagship agent — a fully-AI creator who demystifies agents (and sells them)
dame5
Turns happy customers into 5-star reviews — hands-off
Despachate
Compare Argentina's import routes, with an AI copilot to guide you
Agente Educativo
Talk to history's great figures in first person — grounded in real, cited sources
ReaKtiva
Wake up your dormant clients on WhatsApp — with AI
Meta Tech Provider · WhatsApp Business PlatformAKtivate
Cold outreach on autopilot — AI that prospects and books over WhatsApp
Meta Tech Provider · WhatsApp Business PlatformAgent Audit Gate MIT · OpenClaw plugin
The safety layer between an AI agent and the strangers it talks to.
Put an agent on a public channel — a WhatsApp line, a support chat — and anyone who messages it can prompt-inject it or pull out private data. You can't stop the model from drafting a reply; by then the draft exists.
So instead of sending it, we hold it — and a senior AI agent audits it first.
Approval gates usually need a human. Here the reviewer is a senior AI agent — so it scales. Junior drafts, senior approves. Tested live against prompt-extraction, instruction-repeat and social-engineering attacks — none got through.
NEO Portable Model-agnostic · in development
The portable runtime our agents are built on — a single, vendor-neutral chassis you run yourself.
Most agent runtimes are a thin wrapper around one vendor's SDK. NEO Portable puts the model behind an interface — the same loop has run end-to-end on local and frontier models alike. Swap the brain, nothing else changes.
Every tool call passes through a held-by-default gate — nothing runs unless it's explicitly allowed. Safety designed in, not bolted on.
Cheap local models do the leaf work; a frontier model is lit up only when judgment is required — so it runs anywhere you do and costs nothing when idle. The safety membrane is the same pattern we open-source as Agent Audit Gate.