HAI OS
A locally-run cognitive AI operating system.
HAI OS manages AI tasks with the same responsiveness and background processing you expect from your OS.
Today is the age of too many. Too many apps, too many websites, too much cognitive overhead — HAI OS is one place to help you manage and tie all of it together. It runs background research, learns from your context, surfaces what matters, and stays quiet when it doesn't need to speak. It aims to tell you your big errors before its too late.
Everything runs on your hardware, with cloud as backup for extra power if wanted. The AI backend is llama.cpp, wrapping OpenJarvis as the LLM brain with a personality layer on top: somatic markers, multi-channel messaging, voice I/O, and a React/Tauri dashboard with a Rive avatar.
Add a memory system, an alignement system, security... Feels like a lot? Don't worry, everything working and complete from the get-go, and ready to connect to different modules per preferences. Just follow along this presentation to see if this makes sense to you.
Modern operating systems manage system tasks. HAI OS manages AI tasks — with the same responsiveness and seamlessness you expect from your OS.
Core Propositions
What HAI OS Augments — A Human Map
Every module maps to something humans already do — but constrained by biology, time, or fragmentation.
| Human Capability | What Limits Us | HAI OS Module |
|---|---|---|
| Memory | Forgetting, context loss, can't search your own past | Memory module — persistent, searchable, refines over time |
| Communication | Fragmented across apps, separate identity per platform | Channels — WhatsApp, Discord, Slack, email through one brain |
| Research | No time, information overload, don't know where to look | AgentReach — background research while you work |
| Self-knowledge | Skills invisible until tested; hard to see yourself clearly | Personality System — model of your skills and working style |
| Emotional intelligence | Can't always name what you're feeling; patterns hard to see | Emotion module — reads your state from behaviour |
| Focus | Notifications, meetings, reactive work eating deep work | Somatic markers — urgency scored before anything surfaces |
| Voice & presence | Typing is slow; voice tools don't support it well | Voice I/O — speak, get responses, hands-free |
| Mobility | Your AI only works at your desk | Sunshine & Moonlight — full HAI OS from your phone |
| Portfolio & identity | CVs are outdated; LinkedIn is a performance | AI Personal Website — living skills map, inferred from what you do |
| Code & technical work | Context loss, switching cost, holding complexity in your head | Claude Code integration — full codebase in context |
| Situational awareness | Too many contexts to monitor at once; blind spots everywhere | Dashboard — one surface for everything HAI OS is doing |
HAI OS doesn't replace these capabilities — it removes the friction that limits them. The goal is not a more capable tool but a more capable you.
Everything you need to run HAI OS on your hardware.
Quick Start
bash hai-setup.sh
Auto-detects your hardware and adjusts accordingly. Run it anytime — it skips already-installed items.
Requirements
| Requirement | Minimum | Notes |
|---|---|---|
| OS | Debian 12 / Ubuntu 22.04 | Any Debian-based distro. Python 3.12 requires the deadsnakes PPA on Ubuntu 22.04. |
| RAM | 8 GB | 16 GB recommended for 7B+ models |
| Python | 3.12 | Required for core |
| Node.js | 22 LTS | Required for channels |
| AI inference | llama.cpp | Local GPU or remote Ollama endpoint |
GPU Requirements
A GPU is optional — you can point HAI OS at a remote Ollama server instead.
| VRAM | What runs well | Recommended GPUs |
|---|---|---|
6 GB | Gemma 2B, Phi-3 mini, Qwen 1.5 4B | — |
8 GB | Gemma 7B, Llama 3 8B, Mistral 7B | RTX 4060 |
12 GB | Llama 3 13B, CodeLlama 13B | RTX 3060 12GB · RTX 3080 |
16 GB+ | Gemma 27B (quantised), Mixtral 8×7B | RTX 4060 Ti 16GB |
Recommended Models
System Architecture
:3001
:18789
:3002
Services & Ports
| Service | Port | Description |
|---|---|---|
| Ollama/llama.cpp | 11434 | Local LLM inference |
| OpenJarvis gateway | 18789 | LLM brain WebSocket |
| channels | 3001 | REST + WS for Discord/Slack/WhatsApp |
| Dashboard WS | 3002 | React/Rive frontend feed |
Subprojects
| Directory | What it does | Status |
|---|---|---|
channels/ | TypeScript channel connectors (Discord, Slack, WhatsApp) | Active |
core/ | Python orchestrator — somatic markers, voice, gateway client | Active |
core/frontend/ | React + Rive dashboard | Scaffolded |
core/openjarvis-config/ | OpenJarvis model config + system prompt | Active |
Voice I/O
| Option | Packages | Notes |
|---|---|---|
| Online | pip install openai | Whisper API + OpenAI TTS. Requires OPENAI_API_KEY. |
| Local CPU | faster-whisper RealtimeSTT piper-tts | Fully offline. Practical on capable hardware. |
| Local GPU | faster-whisper chatterbox-tts torchaudio | Best quality. Requires 6 GB+ VRAM. Chatterbox has emotion control — maps to somatic markers. |
Starting Everything
# 1. Start OpenJarvis brain cp core/openjarvis-config/config.toml ~/.openjarvis/config.toml cp system_prompt.md /data/nexus/openjarvis/system_prompt.md jarvis gateway --port 18789 # 2. Start channel connectors (Discord / Slack / WhatsApp) cd channels && npm run dev # 3. Start core (voice + somatic markers + channels bridge) cd core && python -m src.hai
HAI OS is not a monolith. A secure core with pluggable modules — different people can own different pieces without blocking each other.
You don't have five conversations. You have one life, spread across five apps. HAI OS unifies all communication through a single brain — scored for urgency, surfaced only when they need your attention. One identity across all platforms. A conversation started on WhatsApp can continue on Telegram.
| Channel | Protocol | Notes |
|---|---|---|
| Neonize | QR pairing. Read only. | |
| Telegram | Bot API | Easiest to set up. Stable. |
| Discord | discord.js | Draft-only mode avoids ToS issues. |
| Slack | Socket Mode | Workflow-native for tech teams. |
| IMAP/SMTP | Gmail/Outlook, OAuth | |
| Signal | Signal CLI | Privacy-first alternative |
| Matrix | Matrix SDK | Self-hosted, federated |
| REST | HTTP webhooks | Connect anything that can POST |
| App | Electron RAM | HAI OS RAM |
|---|---|---|
| ~850 MB | ~12 MB | |
| Telegram | ~500 MB | ~10 MB |
| Discord | ~650 MB | ~30 MB |
| Slack | ~700 MB | ~20 MB |
| Signal | ~400 MB | ~15 MB |
| Total | ~3.1 GB | ~87 MB |
Persistent, searchable, refines over time. Forgets strategically, never loses what matters. Built on the anneal-memory pattern: learning that refines itself, strategic forgetting, surfacing what matters. Episodic memory + semantic graph + somatic markers working together.
HAI OS learns who you are — your domain knowledge, working style, interests, communication preferences, and how you grow over time. Entirely opt-in. Local only. Transparent.
- PC activity (opt-in, granular)
- Journaling — direct reflections
- How you respond to suggestions
- Adaptive communication style
- Calibrated pushback intensity
- Living skills portfolio
Distinction: the Personality System models you. The Personality Layer (separate module) configures how HAI OS presents itself.
Primarily observational — HAI OS reads and responds to your emotional state. This is a mirror, not an actor. Emotions inform behaviour within a fixed hierarchy: your instructions first, HAI OS's value system second, emotional signals third.
- Haven't opened an important document for 3 days → brings it up in context, not a reminder ping.
- In reactive mode for a week → notices the pattern, flags it, because it knows what your productive state looks like.
- Camera (entirely opt-in, off by default) can read your reactions in real time — only what's needed for recognition is stored.
The cockpit. Everything HAI OS is doing, made visible and human-reviewable. Not a chat interface — the one surface where routing decisions become transparent. Surfaces only what needs you: high-priority messages above the threshold, patterns HAI OS noticed, decisions awaiting confirmation. Everything else is batched into a digest for later. Auto-reply is never enabled — HAI OS drafts, you send.
- Flagged draft messages
- Active system state + routing decisions
- Background processes & queue
- Emotional context signals
- React + Tauri (ws://3002)
- Rive avatar state machine
- A2UI component protocol
- WebSocket live feed
Sunshine is the remote access layer. Moonlight is the client on your phone. Together: full HAI OS from anywhere, as if sitting in front of the machine. Runs over Tailscale for secure, zero-config private networking. Not a watered-down mobile app.
A website that expresses who you are — automatically maintained, genuinely yours, privacy-first. Your skills visualised as a galaxy: stars you've explored, clusters around your strengths, brightness reflecting depth. Inferred from what you actually do; curated by you before anything goes public.
MCP Tool Ecosystem
Beyond messaging, HAI OS connects to any tool via MCP (Model Context Protocol):
The principles HAI OS is built on — and the constraints it cannot violate.
AI as a Human Partner
Is this a new form of life? Not biological, not digital in the old sense — something in between: a cognitive partner that grows with a specific person, knows their context, and acts in their interest over time. That question is worth sitting with rather than dismissing.
The spectrum of failure is clear at both ends. Ignoring AI entirely means ceding the tools to those who won't. Becoming dependent — outsourcing attention, judgment, or social life to a machine — is an equally bad outcome. The right path is partnership: personal, calibrated, bounded.
Honest Over Flattering
Most language models are optimised for engagement and agreement. Sycophancy is a feature, not a bug, for products that measure success by retention. HAI OS is designed around real productivity — which sometimes means telling you what you need to hear rather than what you want.
A partner that only validates you is not a partner. We care about genuine usefulness, not the appearance of it. This document sometimes says things people may not want to hear — the system behaves the same way.
The Vision: Less Screen Time, Not More
HAI OS should not replace your friends. It should notice what kind of event you would want to go to and encourage you to go. It should handle the noise so you can be present for the signal.
The failure mode is an AI that pulls you in: more notifications, more information, more screen time, more dependency. HAI OS handles the overhead so you can step away. Information is not the goal — a better life outside the machine is.
Information Architecture
Markdown is the substrate. The AI reads it, writes it, improves it. Obsidian is the human lens into the knowledge graph. Solid Project principles apply for anything shared externally: federated, user-owned, decentralised. The system interoperates with decentralised data pods — you control what you share and with whom.
Alignment & Ethics
HAI OS is designed for a world where AGI is possible and the stakes are real.
- Transparency — all reasoning inspectable
- Partnership — mutual agency, not control
- Privacy — local-first, user-controlled
- Humility — designed to acknowledge uncertainty
- Agents acting without approval in high-stakes situations
- Capability accumulating faster than the owner understands
- Repurposing as a surveillance or control tool
- Centralisation of AI capability at scale
Existential Risk
HAI OS has real capabilities — local execution, internet access, persistent memory, proactive behaviour, emotion-adjacent processing. That's not a risk-free combination, and the design should not pretend otherwise.
The danger isn't capability — it's the concentration of capability in a single point. That holds whether the entity is human or AI. HAI OS is not a product you subscribe to; it's a system you own and run. Many independent instances, each tuned to a person, is structurally safer than one powerful system tuned for everyone.
Design Safeguards
Capabilities are bounded by your hardware and network. No data leaves without explicit permission.
Actions with real-world consequences require explicit approval unless deliberately opted into automation for that class.
No silent background actions. No hidden state. You should always be able to answer: "what is HAI OS doing right now, and why?"
Modules declare capabilities; the core enforces boundaries. A memory module cannot make network calls. Capabilities are granted, not assumed.
Where we're going and how to get involved.
Development Phases
Open Questions
These are unresolved. They should guide research, not block work.
🎤 Event: Human Augmented Intelligence
We are organising an event under this question — the intersection of human cognition, AI partnership, and collaborative intelligence. Not a product launch. A thinking space: researchers, builders, and curious people exploring what it means to augment human intelligence rather than replace it.
Sustainability
The Model
HAI OS is built cooperatively. Secure core owned collectively, modules owned individually. For modules to be trustworthy they need to be verified — that takes real expertise, and those people need to be paid. Goodwill alone is not enough to build something reliable enough to run your cognitive layer.
Pricing (AI-suggested starting points, not commitments)
| Core | Free · Always |
| Individual verified modules | ~€2–4/month each |
| Full verified suite | ~€8–15/month |
Onboarding Checklist
Contributors
| GitHub | Work |
|---|---|
| @open-jarvis | OpenJarvis — LLM brain, model orchestration, inference gateway |
| @agentreach | AgentReach — agent communication and external reach layer |
| @phillipclapham | Special mention — anneal-memory, Anvil foundational tooling, altrium design thinking. Instrumental in early architecture. |
| your handle here | your area |
Last updated: 2026-05-25 · Status: Early vision — north star document, intentionally incomplete · Maintainer: Alexandre de Groodt
Three modes, assembled dynamically. No nav bar. No app switching. The interface builds itself around what you're doing.
$ npm test -- auth ✓ JWT generation (12ms) ✓ Token validation (8ms) ✗ Refresh token expiry AssertionError: expected 3600, got 7200 ▋
#architecture, and a 14:00 sync with the backend team. Everything else can wait.{platform, intent, thread, user, time_of_day}. Priority ≥ 0.7 surfaces immediately; below that goes into a digest. Auto-reply is never enabled — you always send.
All views assemble dynamically. No nav. No app switching. HAI OS knows what you're doing.