An Agentic Operating System

I wanted AI agents that actually remember things, coordinate with each other, and run on my own hardware. So I built an OS for them. 48 agents, 204 microservices. It got out of hand.

I'm selling access because GPUs are expensive and I have more ideas than funding.

0Microservices
0AI Agents
0Automation Scripts
0Cmdlets
0Service Groups
Aither ADK

Build an Agent in 10 Lines

Install the ADK, point it at your local Ollama or vLLM instance, and you have a fully capable agent with memory, tools, and personality — in under a minute.

agent.py
from adk import AitherAgent

# Auto-detects Ollama on localhost
agent = AitherAgent("atlas")

response = await agent.chat(
  "What's the project status?"
)
print(response.content)

# Or serve it as an API:
# $ aither-serve --identity atlas
LLM Integration

Any Backend. Your Choice.

Ollama

Local inference. Free. Auto-detected.

OpenAI / vLLM

Any OpenAI-compatible endpoint.

Anthropic

Claude via Messages API.

MCP Bridge

100+ tools via mcp.aitherium.com.

Cognitive Architecture

Six Pillars of Cognition

Every request flows through all six. Not a chain of prompts — an actual cognitive architecture. I may have overthought this.

Intent

PARSE

Classifies input into 16 intent types, assigns effort 1–10, routes to the correct pillar chain.

Reasoning

THINK

SASE methodology — Situation, Analysis, Synthesis, Execution. Gated: skips for trivial, deep chains for critical.

Orchestration

ACT

Routes to 48 specialist agents. Selects the right LLM per-task. MCP tool protocol.

Context

REMEMBER

5-layer memory hierarchy from 1ms working memory to permanent identity storage. Every pillar reads and writes here.

Creation

MAKE

Four creative domains: Visual (Canvas), Code (Demiurge swarm), Narrative (Saga), Audio — with quality gating.

Learning

EVOLVE

Captures outcomes, exports training data, runs Brier score calibration. The system improves itself.

12-Layer Architecture

Built Like a Nervous System

Yes, all of these are real and running. No, I don't know when to stop.

L10
UIAitherVeil
L9
TrainingPrism · Trainer · Harvest
L8
SecurityIdentity · Flux · Secrets
L7
AutomationScheduler · Demand · Workflows
L6
GPUParallel · Accel · Force · Exo
L5
AgentsCouncil · A2A · Genesis
L4
MemoryWorking · Spirit · Context
L3
CognitionMind · Reasoning · Judge
L2
PerceptionVoice · Vision · Portal
L1
CoreNode · Pulse · Watch · Scheduler
L0
InfraChronicle · Secrets · Nexus · Strata
Specialist Agents

Meet the Fleet

48 agents, each with their own personality and skills. They talk to each other over an event bus, not a serial chain. It's a whole society in there.

Demiurge

The Divine Craftsman

Intent-to-code engine with 11-agent swarm coding

🏛️

Atlas

The Infrastructure Titan

Roadmap, PR review, blast radius analysis

📚

Lyra

The Research Librarian

Deep research, quality scanning, continuous docs

📖

Saga

The Epic Storyteller

Narrative writing, roleplay, world-building

🎨

Iris

The Visual Artist

Autonomous image generation via ComfyUI

🌌

Genesis

The Watchful Guardian

Always-present orchestrator — voice, proactive, 50+ routers

📰

Vera

The Content Editor

Interactive journalism and tutorials

🔥

Prometheus

The Worldsmith

Tick-based grand simulation engine

What Makes It Different

Pain System

Agents feel pain — cascading alerts trigger autonomous remediation. Not a metaphor. Real signals, real healing.

Chaos Engineering

The Seven Sins of Chaos: Wrath, Pride, Greed, Sloth, Envy, Gluttony, Lust — each tests a different failure mode.

Capability Tokens

HMAC-SHA256 signed tokens enforce default-deny access. Every agent action is authorized, audited, bounded.

Dark Factory

Autonomous loops: neuron firing, pain-driven remediation, session learning, model finetuning — all overnight, no humans.

Swarm Coding

11 specialized LLM agents in 4 phases: Architect → 8 parallel workers → Reviewer → Judge. Intent to production code.

Self-Improving

Every interaction generates training data. Brier score calibration. The system gets better at being itself.

Wanna see what I'm building?

Seriously, try it. Install the ADK and spin up an agent in under a minute. Or just poke around the full 204-service stack. I don't mind.

$pip install aither-adk

one engineer, mass hallucinations, zero regrets.