NEWOne Koodos, every computer — move work across your fleet without losing context.See what it can do →

The Personal AI Agent

Build securely with any model
on every machine

One agent runtime for your files, terminal, projects, and devices. Work locally or across your fleet—with you in control.

Install once, then open your assistant from any browser.

# Install Koodos for Windows

$irm https://api.kprcli.com/dl/install.ps1 | iex
Signs in through your browser. No key to paste.See Koodos work
AutomateUnderstandDelegate
One assistant across your devicesLocal-first computer accessAny model through one workflow

Works where your work already lives

Windows
macOS
Linux
Browser
Telegram

See Koodos at work

One assistant across your local app, terminal, and device fleet. Pick a task and watch it run.

Koodos · Freshivories
README.md
Koodos is a personal agent runtime.

request
  ├─ local app
  ├─ terminal
  └─ remote device

routing
  ├─ local Ollama
  ├─ OpenRouter
  └─ hosted gateway

fleet
  ├─ desktop   online
  ├─ laptop    online
  └─ server    paused

Understand any project

Open a folder and ask about its structure, dependencies, history, or current changes. Koodos reads the real workspace before answering.

Build and verify changes

Let the agent edit files, run the smallest relevant tests, inspect failures, and explain the result with a clear activity trail.

Operate your computers

See your fleet, route a task to the machine that has the files, and manage devices without moving your workflow.

Works with your model providers·Tool activity stays visible·Windows, macOS, Linux

What Koodos does

Everything a personal agent should do, on your computer and across your fleet.

Project-aware. Tool-using. Multi-model. Built around your machines.

Edits across your project

Reads and changes real files, follows repository instructions, shows what it used, and verifies work with relevant checks.

Runs terminal commands

Executes commands on the selected machine and handles builds, tests, diagnostics, and development servers.

Understands local context

Knows the active folder, project tree, Git state, documentation, and files that make the request meaningful.

Uses skills and playbooks

Loads task-specific instructions for repeatable workflows, from design implementation to device control.

Every model, your choice

Use OpenRouter, OpenAI-compatible services, hosted Koodos inference, or local Ollama models.

Extends with tools and plugins

Connect data sources, web search, Figma, browser workflows, and custom tools without rebuilding the agent.

Coordinates agent teams

Delegate bounded work to specialists, keep persistent workers available, and gather results in one conversation.

Connects every computer

Install it on a desktop, laptop, or server and route work to the device with the right environment.

Explore the Koodos workflow →

Any model, your infrastructure

Bring your own key, use your own endpoint, connect a local model, or route through Koodos while keeping the workflow exactly the same.

Supported providers

Anthropic
OpenAI
Google Gemini
AWS Bedrock
Microsoft Azure
Google Cloud Vertex AI
Ollama
DeepSeek
xAI
Mistral AI
Cerebras
OpenRouter

+ any OpenAI-compatible API

Ready to put an AI agent on every computer you own?

Get Started