~/orlix/docs/index.md
01 Overview
Orlix is not an AI assistant. It is the control layer that sits above any assistant — observing your context, enforcing your policies, executing tasks, verifying outcomes, and updating its own behavior from results.
The key distinction: assistants generate text. Orlix governs outcomes. You configure what matters, what is permitted, and how autonomous the system should be. Orlix operates within those bounds continuously.
architecture overview
┌─────────────────────────────────────────┐
│ your goals · policies · memory │
│ ↓ orlix ↓ │
│ observe → decide → act → verify → learn│
│ ↓ │
│ claude / gpt / gemini / any model │
└─────────────────────────────────────────┘
02 Installation
Orlix is distributed as a single binary for macOS, Linux, and Windows. Early access builds are provided to members of the access program.
macOS / Linux
shell
curl -fsSL https://get.orlix.dev | sh
✓ orlix v0.5.0-beta installed at /usr/local/bin/orlix
Windows
powershell
iwr https://get.orlix.dev/win | iex
Verify installation
shell
orlix --version
orlix v0.5.0-beta · personal AI operating system
03 Quick start
Initialize a new instance
shell
orlix init
[ok] world model initialized
[ok] default policies loaded (v1)
[ok] authority tier: supervised (default)
[ok] audit log: ~/.orlix/receipts/
Set your first goal
shell
orlix goal add --name "Ship MVP" --deadline 2026-07-15
✓ goal 'Ship MVP' added · id: g-0001
Check status
shell
orlix status
[ok] world model ........... online
[ok] policy engine ......... 14 active rules
[ok] memory ................ persistent · local-first
[ok] audit log ............. recording
04 Governance loop
Orlix runs a five-phase loop continuously. Each phase is configurable — you can set the authority tier per phase, per domain, or globally.
01 observe
Watches your calendar, goals, inbox signals, and external sources. Feeds the world model in real time. Never stores raw message content — only extracted, policy-compliant facts.
02 decide
Weighs observed signals against your goals and policies. Determines what — if anything — should happen next. Checks authority tier before proposing any action.
03 act
Executes the decided action — or requests approval if the authority tier requires it. Every action is written to the receipt log before execution, not after.
04 verify
Checks whether the action achieved its stated goal. Not just "was it sent" but "did it work." Discrepancies are flagged and held for review.
05 learn
Updates policy from real outcomes. Every policy change is versioned and requires explicit confirmation unless you've pre-authorized the update class. building
05 Authority tiers
The authority tier controls how much autonomy Orlix has. Set it globally or per domain (e.g. email, calendar, files).
observe
Log activity only. Orlix watches and records — nothing else. Zero risk of unintended action.
suggest
Recommendations only. Orlix surfaces suggestions; every decision is yours.
confirm
Orlix asks before acting on anything, no exceptions.
supervised ← default
Orlix acts, notifies you immediately, and can roll back within 30 days. Recommended starting point.
autonomous
Orlix acts independently within policy bounds. Receipts are logged but no approval required. Use only after establishing trust through supervised operation.
Set the tier
shell
orlix policy --set-tier supervised # global
orlix policy --set-tier confirm --domain email # domain override
06 Memory system
Orlix maintains a living world model — a structured graph of facts, goals, preferences, and relationships. Everything is stored locally, versioned, and exportable.
Memory types
facts
Discrete beliefs about the world. Each fact carries a source, confidence score, and timestamp. Example: "Alex owns the design review · source: email · 2026-06-02 · confidence: 0.95"
goals
Objectives you care about, with optional deadlines and progress tracking. Goals drive the observe and decide phases.
policies
Rules that govern Orlix behavior. Versioned — every change is tracked. Roll back to any previous version with orlix policy --rollback v12.
preferences
Soft preferences that bias decisions without hard-blocking them. Example: "prefer async communication over meetings."
Export and import
shell
orlix memory --export --out orlix-backup.json
✓ exported 1,204 facts · 7 goals · 14 policies
orlix memory --import orlix-backup.json
✓ world model restored · 1,204 facts · 7 goals
07 Action receipts
Every action Orlix takes or proposes generates a receipt — a structured record linking the action to the intent, policy, and verification result.
$ cat ~/.orlix/receipts/2026-06-13-0847.json
{
"intent": "Notify user of goal drift",
"context": "Goal 'Ship MVP' · 3 blockers · last touched 17d ago",
"policy": "Alert if goal drift > 3 days · v14",
"action": "Priority alert sent",
"approval": "User confirmed re-prioritization",
"verified": true,
"rollback": "available · expires 2026-07-13"
}
Viewing receipts
shell
orlix receipts --list # list recent receipts
orlix receipts --show 2026-06-13-0847 # view one receipt
orlix receipts --rollback 2026-06-13-0847# undo this action
08 Policies
Policies are the rules Orlix follows. They are versioned, auditable, and can be evolved manually or (in v0.5) automatically from outcomes.
shell
orlix policy --list # show all active policies
orlix policy --add "notify_if_blocker_gt_48h"
orlix policy --disable p-0003 # disable by id
orlix policy --rollback v12 # restore previous version
09 CLI reference
orlix init
Initialize a new Orlix instance in the current environment.
orlix status
Show the current state of the world model, policies, and audit log.
orlix goal
add, list, update, remove — manage your goal registry.
orlix memory
--export, --import, --search, --forget — manage the world model.
orlix policy
--list, --add, --disable, --rollback, --set-tier
orlix receipts
--list, --show, --rollback — view and manage action audit log.
orlix run
Execute a single governed task. Orlix will observe, decide, act, and verify — logging a receipt.
orlix --version
Print version string and exit.
orlix --help
Print help for any subcommand.
10 Configuration
Orlix reads ~/.orlix/config.toml on startup. The most important settings:
~/.orlix/config.toml
# authority tier: observe | suggest | confirm | supervised | autonomous
tier = "supervised"
# default AI model for decision and act phases
model = "claude-opus-4-8"
# local data directory
data_dir = "~/.orlix"
# opt-in telemetry (default: false)
telemetry = false
11 Integrations
Orlix connects to external services through policy-controlled adapters. Each adapter has its own authority tier setting.
AI models
Anthropic Claude, OpenAI GPT, Google Gemini, and any OpenAI-compatible endpoint. Swap models without losing your memory or policies.
Calendar
Google Calendar, Apple Calendar, Outlook. Orlix reads events to update goals and context. v0.1
Email
IMAP/SMTP compatible. Orlix extracts facts from messages you authorize — never stores raw email content. v0.1
Tasks
Linear, Notion, GitHub Issues. Bidirectional sync with your goal registry. v0.3
Files
Local filesystem access within configured paths. Read and write under supervised or confirm tier. v0.3
// all adapter credentials are stored encrypted in ~/.orlix/credentials — never transmitted to Orlix servers.