An AI-native operating system

Intelligence,
native.

Every program can already read files and open sockets. TharAI adds one more capability: intelligence. Write a prompt to a file, read back the answer. Any language, any framework, any machine — laptop to cloud.

tharai — bash
# Listen and transcribe — as simple as reading a file
$ cat /dev/ai/hear > transcript.txt
⠿ Listening... "Hello, welcome to the demo"
 
# Understand an image
$ cat photo.jpg > /dev/ai/see
{ "scene": "office", "objects": ["laptop", "coffee"] }
 
# Generate a response
$ echo "Summarize this doc" > /dev/ai/think
The document outlines a three-phase...
 
$

Every capability becomes a primitive.
AI hasn't — yet.

Every fundamental computing capability eventually graduates from application-level code to an OS primitive. AI is the last holdout.

Era Capability Before After
1970sFile StorageCustom disk drivers per app/dev/sda, POSIX file I/O
1980sNetworkingCustom protocol stacks/dev/eth0, BSD sockets
1990sGraphicsDirect hardware access/dev/gpu, framebuffer
2000sAudioPer-app sound drivers/dev/audio, ALSA
2020sIntelligenceCloud APIs, custom pipelines/dev/aiTharAI

/dev/ai
for everything.

Any language. Any framework. Any application. If your code can read and write files, it can use AI. No SDKs. No API keys. No vendor lock-in.

The same interface works whether the model runs locally on your laptop, on a cloud VM, or routes to Claude/GPT via your own API key. Zero code changes between environments.

Speech to text Bash
# Real-time transcription
$ cat /dev/ai/hear | grep "help"
→ Triggers on keyword detection
Vision pipeline Python
# Standard file I/O — no imports needed
with open('/dev/ai/see', 'w') as f:
    f.write(open('camera.jpg', 'rb').read())
    
result = open('/dev/ai/see').read()
# → {"objects": ["person", "desk"], ...}
Compose pipelines Bash
# Chain: hear → think → speak
$ cat /dev/ai/hear \
    | tharai pipe /dev/ai/think \
    | tharai pipe /dev/ai/speak
→ Voice assistant in 3 lines
Any language works C / Rust / Go / Node
// It's just a file descriptor
int fd = open("/dev/ai/think", O_RDWR);
write(fd, prompt, strlen(prompt));
read(fd, response, BUFSIZ);
// That's it. POSIX. Universal.

Five principles. No compromises.

TharAI is built on ideas that have proven themselves across fifty years of UNIX heritage.

/dev

POSIX-native

AI through standard file operations. Not proprietary SDKs, not REST APIs, not Python-only libraries. If your language can open a file, it can use AI.

Local-first

Runs on your hardware by default. Models execute locally — your data never leaves your machine unless you explicitly choose cloud augmentation.

Model-agnostic

Swap models like you swap drives. Whisper today, Deepgram tomorrow — same /dev/ai/hear interface. No code changes. Ever.

◎→◎

Pipeline composable

Chain capabilities with standard UNIX pipes: hear → think → speak. Build complex AI workflows from simple, testable primitives.

{ }

Open-core

Apache 2.0 core — inspect, modify, deploy freely. Commercial extensions for enterprise features, managed models, and support.

☁⟶◻

Cloud-augmented

Need GPT-4 class reasoning? Route /dev/ai/think to the cloud with a config change. Same interface. Local and cloud, unified.

If you can write to a file,
you can use AI.

🛠

Developers

Add AI to any system in two lines — no Python SDK, no dependency chain, no framework lock-in. Works with bash scripts, C programs, Go services, Rust binaries, or anything that can open a file.

  • Git hooks that review code before every commit
  • Log analysis pipelines that explain errors in English
  • Cron jobs that generate daily summaries with AI
  • APIs that validate responses using natural language
🏗

Infrastructure teams

Deploy AI as a system service, not an application dependency. Every server, every VM, every container gets /dev/ai — managed centrally, monitored like any other service.

  • Incident response: AI diagnoses alerts automatically
  • Terraform/Ansible validation before applying
  • Fleet-wide AI with consistent interface and audit logging
  • Cloud VMs, bare metal, or air-gapped — same /dev/ai

Not another framework.
The layer beneath them all.

TharAI isn't replacing your tools — it's giving them a universal foundation.

Approach
Limitation
TharAI
Cloud APIs
Internet required, vendor lock-in, data leaves machine
Local-first, cloud-optional, data stays
Model runners
No OS integration, no pipeline composition
POSIX-native, pipeable, composable
AI frameworks
Python-only, heavy dependencies
Any language — it's a file descriptor
Vendor OS AI
Closed, single-vendor, no dev API
Open-core, model-agnostic, dev-first
Ollama / LM Studio
Chat-only, no OS integration, no pipelines
OS-native, composable hear→think→speak

Try /dev/ai right now.

This terminal connects to a real TharAI instance running on a standard cloud VM. Type a command, click a button, or hold 🎤 to speak.

/dev/ai mounted · Claude Haiku · Voice ready
echo 'What is 2+2?' > /tmp/ai/think
cat /tmp/ai/think
cat /tmp/ai/status
haiku
help
tharai-demo · /dev/ai · live
$
Enter Execute ↑↓ History 🎤 Hold mic to speak
15 req/min

The POSIX of intelligence.

cat /dev/ai/hear > transcript.txt