Kanbots: AI Agents, Worktrees, & Dev Workflows on AI VOID

Setting Up Your Kanbots Workshop: Tauri v2 and Svelte 5

Sun, 24 May 2026 00:00:00 +0000

Welcome to the Kanbots project, where we’ll build an innovative desktop Kanban application designed to host and orchestrate multiple AI agents. This application will empower you to automate development tasks, from code generation to review, leveraging isolated Git worktrees for each agent’s context.

In this first chapter, we lay the groundwork for Kanbots. We’ll set up the core cross-platform desktop application using Tauri v2 for the backend and Rust, paired with a modern Svelte 5 frontend. By the end of this milestone, you will have a functional desktop application window displaying a basic Svelte interface, ready for further development. This foundational setup is crucial for enabling the local-first, privacy-conscious AI agent interactions that will define Kanbots.

Building the Core Kanban Board UI

Sun, 24 May 2026 00:00:00 +0000

In this chapter, we’re laying the visual and interactive groundwork for Kanbots: a functional Kanban board. This isn’t just about pretty pixels; it’s about creating the canvas where our AI agents will operate. By the end of this milestone, you will have a desktop application with a fully interactive Kanban board, allowing you to add, edit, and move task cards between columns. This core UI is essential for managing the AI-driven development tasks we’ll introduce later.

Mastering Git Worktrees for Isolated Agent Tasks

Sun, 24 May 2026 00:00:00 +0000

Isolated Development with Git Worktrees

Imagine a team of highly efficient AI developers, each working on a separate feature branch, but all within the same repository, without ever stepping on each other’s toes. This is the power we’re bringing to Kanbots in this chapter. We’ll enable each Kanban card to spawn and manage its own isolated Git environment using Git worktrees.

This milestone is critical because AI agents, especially those generating code, need a clean, predictable workspace. Without isolation, concurrent agents could overwrite each other’s changes, leading to chaos and unpredictable outcomes. Git worktrees provide this crucial sandboxing, allowing agents to operate in parallel, each with its own working directory and branch, while still sharing the underlying repository history and objects.

Integrating Your First AI Agent: Claude Code or Codex

Sun, 24 May 2026 00:00:00 +0000

This chapter marks a pivotal moment for Kanbots. We’re moving beyond a static Kanban board and injecting intelligence by integrating our first AI agent. You’ll learn how to connect an AI model like Claude Code or a modern OpenAI equivalent (e.g., GPT-4o) to a Kanban card. This enables the agent to perform specific tasks, such as generating code, within its dedicated git worktree. By the end of this milestone, your Kanbots application will be able to dispatch a task to an AI agent, have that agent generate content (like a simple code file), and observe the results directly within the isolated worktree associated with your Kanban card. This lays the foundation for powerful, automated development workflows.

Orchestrating Multi-Agent Workflows with Personas

Sun, 24 May 2026 00:00:00 +0000

In the previous chapters, you’ve built a foundational Kanban board, integrated Git worktrees for isolated task contexts, and even enabled a single AI agent to perform basic tasks. This chapter marks a significant step forward: orchestrating multiple AI agents to collaborate on a single task, each with a distinct persona.

This milestone is critical because real-world development often involves multiple roles and handoffs. By simulating this with AI agents, we move beyond simple task automation towards a more intelligent, autonomous development assistant. By the end of this chapter, your Kanbots application will be able to initiate and manage sequential workflows, demonstrating how different AI “personalities” can contribute to a larger goal. You’ll verify the workflow by observing agents making distinct, persona-aligned changes in a Git worktree, ultimately completing a small feature or refactoring task.

Real-time Agent Progress and User Control UI

Sun, 24 May 2026 00:00:00 +0000

Interacting with AI agents can often feel like giving a command to a black box. You trigger a task, wait, and eventually, an output appears. For a multi-agent system like Kanbots, this lack of transparency can lead to frustration and inefficiency. This chapter addresses that challenge by equipping our Kanbots application with real-time feedback and user controls.

By the end of this milestone, your Kanbots application will provide a dynamic interface that displays agent progress, streams logs, and allows users to pause, resume, or cancel agent tasks directly from the Kanban board. This dramatically improves the user experience, giving operators crucial insights and control over complex AI workflows.

Securing API Keys and Robust Error Handling

Sun, 24 May 2026 00:00:00 +0000

In this chapter, we elevate Kanbots from a functional prototype to a more robust, production-minded application. We’ll tackle two critical aspects: the secure management of sensitive AI API keys and the implementation of comprehensive error handling and logging. These elements are non-negotiable for any application that interacts with external services or handles user data, ensuring both security and a smooth user experience.

By the end of this milestone, your Kanbots application will no longer store API keys in plain text or crash silently. Instead, it will securely load credentials, gracefully handle expected and unexpected failures from AI agents or Git operations, and provide clear feedback to the user and logs for debugging. This significantly improves the application’s reliability, maintainability, and trustworthiness.

Logging Agent Activities and Deployment Considerations

Sun, 24 May 2026 00:00:00 +0000

Debugging and understanding the behavior of a multi-agent system like Kanbots can be incredibly challenging without proper visibility. In this final chapter, we’ll equip our Kanbots application with robust logging capabilities to capture agent activities, inputs, outputs, and any errors. This provides the essential observability needed to diagnose issues, track performance, and even audit AI agent decisions.

Beyond observability, this chapter also guides you through the critical steps of preparing your Kanbots application for distribution. We’ll explore Tauri’s deployment features, focusing on how to package your application for various operating systems and important considerations like secure API key management and application signing.