TSK-1 (Taskade System Kernel)

TSK-1 is the Taskade System Kernel, the intelligence layer that coordinates models, memory, agents, and workflows into one running workspace. Every app you build with Taskade Genesis now runs on TSK-1. It is not another AI model. It is the kernel above the models: it routes each task across 15+ frontier models automatically, holds your context in connected projects, runs multi-agent reasoning, and keeps workflows executing after the chat ends.

TL;DR: TSK-1 stands for Taskade System Kernel. A kernel is the innermost core of a computer, the part that coordinates everything else. TSK-1 plays that role for your workspace, connecting frontier models, memory, agents, and automations so a single prompt becomes an app that remembers, reasons, and runs. Build one free →

What Is TSK-1?

TSK-1 is the coordination layer at the center of Taskade. When you describe an app in plain language, TSK-1 is what turns that description into a system that keeps working: it decides which model handles the task, reads your Workspace DNA, hands work to the right agent, and fires the automation that keeps things moving. You never see it. You feel it, because it is what makes everything else run together.

What Does "TSK-1" Stand For?

TSK-1 stands for Taskade System Kernel, version one.

A computer's core is called a kernel because it is the fundamental, innermost part of the system. Like the kernel of a nut or a seed, it sits hidden at the center, controlling every major function and talking directly to the machine underneath. Taskade has three layers that map onto how a computer is actually built:

You talk to the shell, Taskade EVE. The kernel, TSK-1, does the coordinating. Your Workspace DNA is where the work actually lives and runs.

You  ─▶  Prompt  ─▶  Taskade EVE  (shell)
                          │
                          ▼
                       TSK-1        (kernel)
             ┌────────────┼────────────┐
             ▼            ▼            ▼
         Projects      Agents      Workflows
         (memory)  (intelligence) (execution)
             └────────────┼────────────┘
                          ▼
             A living app that runs itself

Why a Kernel, Not a Model

This is the part people get backwards. TSK-1 is not a model. It is the kernel that runs the models.

Ask a chatbot a question and a single model answers. TSK-1 sits above the models and coordinates them: it routes each task to a sensible default across 15+ frontier models from OpenAI, Anthropic, Google, and open-weight providers, holds your memory, hands work to the right AI agent, and runs the automation. The model writes a sentence. The kernel runs a system. It is the difference between an autonomous agent that acts once and a workspace that keeps working.

Naming the kernel matters because agents are arriving faster than they hold together. A pile of models and agents is not a system until something coordinates them. That coordinator is TSK-1. It is not a developer framework you wire up and it is not a single system prompt. It is the intelligence already running inside your workspace, reachable by the rest of your tools through the Model Context Protocol.

One Model, on Autopilot

You never pick a model. TSK-1 runs on Auto and adapts on its own. Fast edits get an instant response. A hard question gets deeper reasoning. A long build gets the most capable path. The kernel reads the task and chooses the depth, so the setting disappears and you stay on the outcome. Power users can still pin a specific model, but most people never open the menu.

Your Workspace, Alive

Most AI tools stop the moment the app is generated. Taskade keeps going, because TSK-1 wires your workspace into a loop that does not stop when the chat does. This is living software, the Genesis loop made real:

• Projects remember. Your data and context stay connected. See memory graph.
• Agents reason. Multi-agent teams understand your goals and take action.
• Workflows run. Automations keep moving after the chat ends.
• Apps launch. One prompt, one live app.

The loop, stated plainly: memory feeds intelligence, intelligence triggers execution, execution updates memory. TSK-1 is the kernel that makes the loop turn.

Learn More

• Multi-Model AI Access, the frontier models TSK-1 coordinates
• Workspace DNA, memory, intelligence, and execution
• Taskade EVE, the shell you talk to
• Living Software, apps that keep running
• The Genesis Loop, how one prompt becomes a running system

Ready to build on the kernel? Start with a prompt or clone a live app.