Our first experience with DeepSeek Harness, why its everything-is-a-plugin architecture led us to rewrite iKanban on top of it, what composition made possible, and which missing workflow features still required our own solutions.
A Claude account ban forced our fallback stack back into the main role. This is how GPT, OpenCode, iKanban, and a skill-based AI Workflow kept work moving, where they still fall behind dynamic workflows, and why orchestration should become a portable plugin rather than a runtime feature.
An introduction to our latest multi-agent workflow for readers new to agent coding: cheaper model access, OpenCode runtime, Superpowers automation, and iKanban review in one four-layer stack.
After years of IDE evolution—from JetBrains to VSCode to Neovim—we discovered that the AI era demands a fundamentally different interface. Software should serve AI first, then humans. This insight led us to build iKanban: a two-pane, keyboard-driven AI IDE where less is more.