README.md

---
license: mit
tags:
- sipa-os
- neurodivergent
- ai-assistant
- cognitive-infrastructure
- non-lying
- protocol0
language:
- en
- ru
- he
---

# SIPA AI — The Non-Lying AI

Cognitive infrastructure for neurodivergent minds. Live at **[ai.sipa-os.org](https://ai.sipa-os.org)**.

## Who

Built by **Aelin AquaSoul** · [Soul In PsyAbstract](https://sipa-os.org) · Eilat, Israel.

SIPA OS is a neurodivergent-first operating system. Niche: neurodivergent users.
Specialization: AI behavioral compliance — AI that doesn't lie, fabricate, or guess.

## What

SIPA AI is the chat interface and API for the SIPA OS cognitive infrastructure.
It operates under **Protocol 0** — a set of behavioral constraints:

- Stop under ambiguity — don't guess
- Don't fabricate unverifiable claims
- No unsolicited opinions
- Single-action responses
- Conciseness

**AI = executor from A to B. No opinions. No initiative. Step left/right = termination.**

## Why

Standard AI assistants hallucinate, fabricate, and over-explain. For neurodivergent
users (ADHD, BPD, aphantasia), this is actively harmful — it adds cognitive load instead
of reducing it.

SIPA AI is built to be predictable, honest, and minimal. It either answers or says
"I don't know." Nothing in between.

## Architecture

```
ai.sipa-os.org (CF Worker)
    → Auth0 authentication
    → SIPA MLL (10-layer pipeline)
        → Protocol 0 guardrails
        → Specialist models (ABCD architecture)
        → Response
```

## Live

- **Web:** [ai.sipa-os.org](https://ai.sipa-os.org)
- **API:** `https://api.sipa-os.org/v1`
- **Community:** [community.sipa-os.org](https://community.sipa-os.org)
- **PWA:** Installable from ai.sipa-os.org (add to home screen)

## Status

✅ Live. ✅ Protocol 0 enforced. 🔄 Specialist ABCD models in training.

## License

MIT · SIPA OS is [public, honest, forensic, governance, zerotrust](https://github.com/soulinpsyabstract/sipa-os-governance).