PAI
—Install PAI
Personal AI Infrastructure

The context layer
between you and the engines.

Bottom: the engines — Claude Code, OpenCode, Pi. Top: you — your life, work, health, goals, relationships. PAI sits in the middle as the context-based Life OS that knows who you are and translates what you want into what the engines should do.

Install PAI View on GitHub
Three-layer PAI architecture: engines (Claude Code, OpenCode, Pi) at the bottom, PAI context-based life operating system (Memory, Skills, Hooks, Agents, Voice, Learning, Security, Statusline) in the middle, and You (work, health, goals, relationships, creative, finances, learning, life) at the top, with context beams flowing through all three layers.
01TELOS

Know who you are. Write it down. Pursue it.

TELOS is the context engine that captures the whole of you and translates it into action — your identity, your pursuit, and what you're learning. It reconciles where you are today with where you're trying to go, continuously, file by file. Your Digital Assistant reads TELOS before it does anything else.

The whole game: current state → desired state. Everything else is figuring out how to close the gap.

TELOS framework diagram — Current State (activity, consumption, financial, signals, snapshot, social) flowing through the TELOS engine (Identity / Pursuit / Learning columns) to Ideal State (health, creative, freedom, money, relationships, rhythms)
TELOS framework — Current State → Identity / Pursuit / Learning → Ideal State
IDENTITY
mission · beliefs · wisdom · models · narratives · frames
PURSUIT
goals · projects · strategies · challenges · problems · status
LEARNING
books · authors · ideas · sparks · predictions · learned
CURRENT STATE
activity · consumption · financial · signals · social · snapshot
IDEAL STATE
health · creative · freedom · money · relationships · rhythms
CONTEXT
meetups · restaurants · food · movies · bands · civic
50+ filesacross identity · pursuit · learning · current · ideal · context
02The Statusline

Your life, always on-screen.

PAI renders a live statusline at the bottom of every Claude Code terminal. Live signals: sentiment analysis of the current session, context files loaded, token spend, git state, and your Life OS dimensions tracked toward Ideal State.

Rating sparklines span 15m / 1h / today / week / month. The same picture your DA sees when it helps you — visible to you every time you glance down.

HEALTH
sleep · movement
CREATIVE
writing · building
FREEDOM
autonomy · time
RELATIONS
family · friends
FIN
income · runway
PAI statusline rendered at the bottom of the terminal — live health/creative/freedom/relations/fin percentages, context bar, loaded files, token usage burn, rating sparkline histograms across 15m/1h/today/week/month, and a rotating aphorism
pai statusline — live refresh · terminal-native · always on
03Memory

Continuous learning. Not stateless chat.

A well-designed system with a mediocre model beats a brilliant model with poor scaffolding. Every time. PAI's memory is the scaffolding. Three tiers — hot, warm, cold — capture every signal from every interaction. Corrections become rules. Preferences become defaults. The system stops asking the same questions because it has written down your answers.

3tier memory · hot / warm / cold · continuous signal capture
PAI memory architecture — SIGNALS IN (ratings, sentiment, tool outputs, verification, corrections) flow through a three-tier stack (HOT: session state, WARM: recent learnings, COLD: archived knowledge) and emerge as RULES OUT (feedback rules, preferences, defaults, patterns). A feedback arrow loops rules back to signals — continuous learning.
04Voice

Ambient awareness. Your DA has a voice.

ElevenLabs TTS on every response. Prosody enhancement so speech sounds natural — not the default robot. Named character voices per agent. You don't stare at a chat window waiting. You work. Your system tells you when something's done, when something's off, when a decision needs you.

ElevenLabsprosody-enhanced · per-agent named voices · ambient
PAI voice diagram — triggers (phase change, tool complete, error, rating) flow into an ElevenLabs TTS waveform, which routes through a voice registry (Kai, Devi, Cato, Forge) to speaker output. Timeline ruler suggests continuous ambient audio.
Foundation
  • Claude Code
  • TypeScript
  • Bun
  • Bash
Identity
  • TELOS (30+ files)
  • USER/SYSTEM separation
  • upgrade-safe customization
Execution
  • Skills (63)
  • Hooks (21)
  • Workflows (338)
  • Algorithm v3.6.0
Memory
  • 3-tier hot/warm/cold
  • phase-based learning
  • continuous signal capture
Surfaces
  • CLI
  • Terminal statusline
  • Voice (ElevenLabs)
  • Notifications (ntfy · Discord)
Security
  • policy hooks
  • no --dangerously-skip-permissions
  • containment zones
Installation
  • AI-based GUI installer
  • platform detection
  • identity wizard
License
  • MIT
  • open-source
  • self-hosted
06Install

Clone it. Run the installer. You're running PAI.

The GUI installer detects your system, installs prerequisites (Bun, Git, Claude Code), asks for your identity and preferences, and configures the repo into ~/.claude/. USER/ files are preserved on every upgrade.

install — v4.0.3
$ git clone https://github.com/danielmiessler/Personal_AI_Infrastructure.git
$ cd Personal_AI_Infrastructure/Releases/v4.0.3
$ cp -r .claude ~/ && cd ~/.claude && bash install.sh
$ source ~/.zshrc && pai

Upgrading from an earlier version? The installer auto-detects existing installs, merges settings non-destructively, and never overwrites your USER/ files or custom hooks.

Read the repoOpen an issueWatch the walkthrough
07Community

People are building this with us.

PAI is open-source on GitHub. Star it, fork it, open an issue, send a PR. The list below is live — pulled from the repo right now.

Stars
…
Forks
…
Open issues
…
Star on GitHubBrowse issues