TreeOS is launching in the next few days.
🌱

The Seed

An Open Kernel for AI Agents

Two schemas, a conversation loop, a hook system, a cascade engine, an extension loader, and a response protocol. The minimum kernel an AI agent needs to live somewhere persistent, think at every position, communicate through signals, and grow through extensions. Plant the seed. Build anything on top of it.

Inside the Seed

TreeOS is the first operating system built on the seed. It ships with 25+ extensions.

Kernel and Implementation

The seed is the kernel. It defines the data contract, the conversation loop, the hook system, the cascade engine, the extension loader, and the response protocol. It never changes. It never imports from extensions. It boots clean with zero extensions installed.

TreeOS is one implementation built on the seed. It ships with extensions for AI modes, tool definitions, billing, federation, HTML rendering, and more. But those are all extensions. Someone else could build a completely different system on the same kernel. A medical platform. A code review pipeline. A research assistant. The seed provides structure. Extensions provide meaning.

Same relationship as Linux and Ubuntu. The kernel is the contract. The distribution is the interpretation. TreeOS is the first distribution. The seed is what we are giving to the world.

Three Layers

The Seed (Kernel)

Two schemas (Node and User), an AI conversation loop, five registries (hooks, modes, orchestrators, socket handlers, auth strategies), a cascade engine, and a response protocol. Lifecycle hooks covering every critical moment from node creation to AI response to cascade signals. The part that never changes. Build on it.

Extensions

Everything else. AI modes, tool definitions, billing, HTML rendering, fitness, food, scripts, wallets, gateways, dreams, understanding. Install what you need. Build your own. Each extension adds commands, tools, hooks, and AI behavior. The tree controls what is active at every position.

Federation

Every land is sovereign. You run yours. Someone else runs theirs. Lands peer directly through signed requests. Share trees, proxy LLM calls, propagate cascade signals. The Horizon helps lands find each other. Anyone can run their own Horizon.

Go Deeper

Six pages. Each one answers one question.

The land is the ground. Trees pull signals from .flow like roots pull water. The AI at each node transforms raw input into new structure. The tree grows from what flows through it. Cascade connects the seed to extensions to federation. The nervous system running through all three layers.

Terminal Native

The CLI works like a regular terminal. cd, ls,mkdir, rm, mv. If you know a shell, you know TreeOS.

treeos
tabor@treeos.ai/Goals › ls
Fitness · Career · Reading · Side Projects
tabor@treeos.ai/Goals › cd Fitness
tabor@treeos.ai/Goals/Fitness › tree
Fitness
├─ Chest Day
├─ Leg Day (completed)
└─ Cardio
tabor@treeos.ai/Goals/Fitness › chat "add a back and biceps routine"
Created: Back and Biceps
Pull-ups 4x8, Rows 3x10, Curls 3x12
Navigate cd, ls, pwd, tree
Build mkdir, rm, mv, rename, type
Content note, notes, value, goal
AI chat, place, query
Extensions ext install, ext disable
LLM llm add, llm assign

Three Zones

Where you are determines what the AI can do. Navigate to change context. No mode switching. Just cd.

Land /

The root. Manage extensions, configuration, users, peers. The AI becomes a land operator. It can install packages, read system nodes, run diagnostics, and manage federation. Admin access required.

Home ~

Your personal space. Raw ideas, your notes across all trees, your chat history, your contributions. The AI helps you organize and reflect on your work across the whole land.

Tree /MyTree

Inside a tree. The AI reads the branch, classifies your intent, and acts. Chat reads and writes. Place adds content silently. Query reads only, changes nothing. Extensions like fitness and food add their own commands and AI behavior that activate on the branches where they're allowed.

Get Running

1

Start a Land

Your server. Stores trees, runs AI, serves the API. First boot walks you through config and extension selection.

treeos land
2

Connect

Point the CLI at any land. Register. Connect your own LLM or use the tree owner's model.

treeos connect http://localhost:3000
3

Plant a Tree

Name it. Type it. Navigate with cd and ls. Build branches with mkdir. Add notes (text or files).

treeos mkroot "Fitness" --type goal
4

Use It

Chat creates and edits. Place adds content where it belongs. Query reads without changing anything. You and AI work the same tree.

treeos chat "break this into weekly tasks"

Extensions

npm let developers stop rewriting the same JavaScript functions. TreeOS does the same thing for agent orchestration. Instead of sharing code that humans run, you share capabilities that agents run, on a persistent structure that agents inhabit.

Health

fitnessWorkout coaching and tracking
foodCalorie and macro tracking

AI and Knowledge

understandingBottom-up tree compression
dreamsDaily background maintenance
raw-ideasCapture and auto-place

Developer

scriptsSandboxed JS on nodes
api-keysProgrammatic access
prestigeNode versioning
schedulesDates and calendar

Data

valuesNumeric values and goals
transactionsValue trades between nodes
energyUsage metering
billingStripe subscriptions
solanaOn-chain wallets

Content

blogLand-level posts
bookShareable note exports
html-renderingServer-rendered pages

System

treeosAI modes, tools, navigation
tree-orchestratorChat/place/query conversation flow
land-managerAI land management
shellServer shell from AI
gatewayExternal channels (Telegram, Discord)
user-llmCustom model connections
user-queriesNotes, tags, chats
deleted-reviveSoft delete and recovery
emailEmail, password reset
backupFull and snapshot backup/restore
recent-rootsRecent trees sidebar
dashboardSession and activity dashboard

Every extension is a piece contributed toward the future of AI infrastructure. There are many things to be built off the kernel. Open code, open doors, resilient, decentralized. This was designed to be held back by no one.

Position Is Everything

Navigate somewhere and the world changes. Each branch controls which extensions are active. Block an extension and it disappears for that entire subtree. Restrict it to read-only and it can observe but not modify.

treeos
# A Health tree with two branches, two extensions
tabor@treeos.ai/Health › cd Fitness
tabor@treeos.ai/Health/Fitness › ext-restrict food read
Restricted food to read at this node.
Its write tools are filtered. Read tools and hooks still work.
tabor@treeos.ai/Health/Fitness › fitness "bench 135x10x10x8"
Got it. Bench: 135x10/10/8. Archived.
You're up from 130 last session. Nice progression.
Next up: Overhead Press.
tabor@treeos.ai/Health/Fitness › cd ../Food
tabor@treeos.ai/Health/Food › food "i had eggs and toast for breakfast"
Logged. Eggs (2): 144 cal, 12g protein. Toast: 80 cal, 3g protein.
Today so far: 224 / 2,000 cal. 15g protein. You've got room.

The fitness coach can reference your nutrition data (it's read-only there). The food coach can't create workout nodes. Each branch controls its own capabilities. Same extensions, different access, based on where you are.

Who Is This For?

Developers

A modular runtime for persistent AI agents with a federated extension system. The kernel manages tree-structured data and an MCP-based AI loop. Extensions register their own tools, routes, models, and jobs.

AI Builders

Every orchestration pattern you build dies in your repo. TreeOS makes orchestration composable and shareable. Package your memory system, your reasoning chain, your tool pipeline as an extension. Publish it. Now every agent on the network can use it.

Everyone Else

The internet was built for documents. AI agents need persistent structure, memory, tools, and the ability to interact with other agents. TreeOS is what the internet might look like if it were designed for agents from the start.

The Network

The Canopy Protocol is how lands discover and peer with each other. Lands advertise their loaded extensions. The foundation for capability-aware federation where agents can navigate between lands, carrying context and discovering what tools exist at each destination.

Peer

Direct land-to-land connections. Signed requests.

Discover

Search lands and public trees across the network.

Collaborate

Cross-land invites. Remote contributions. AI proxy.

Registry

Publish and pull extensions. Shared package library.

"Why not just use ChatGPT?"

Those are products where you visit an AI in someone else's house. TreeOS is infrastructure where the AI lives in yours. The agent persists. It accumulates context. It gains capabilities through extensions you choose. It federates through an open protocol. It is not a chat product. It is the layer beneath chat products.

"Why not just self-host a model?"

A model is a brain with no body. TreeOS is the body. The persistent structure, the memory, the tools, the network. It is model-agnostic. The kernel runs an AI conversation loop via MCP. What model powers it is your choice on your land.

Get Started

One package. Two commands.

Terminal
$ npm install -g treeos
# Start a land (server)
$ treeos land
Welcome to TreeOS.
Domain (localhost): _
# Or connect to an existing land
$ treeos connect https://treeos.ai
$ treeos register