- Published on
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.
Ai-coding
All Posts
- workflow (13)
- linux (12)
- ai (11)
- opencode (10)
- tools (10)
- arch-linux (9)
- productivity (9)
- ai-coding (9)
- multi-agent (9)
- claude-code (8)
- ide (7)
- ai-agent (7)
- neovim (6)
- wayland (5)
- window-manager (4)
- tiling (4)
- sway (4)
- coding (4)
- plugins (4)
- subagents (4)
- ikanban (4)
- vibe-coding (3)
- mcp (3)
- cli (3)
- journey (3)
- vim (3)
- dotfiles (3)
- reflection (3)
- configuration (3)
- development (3)
- surfingkeys (3)
- codex (3)
- dynamic-workflows (3)
- rust (3)
- i3 (2)
- river (2)
- skills (2)
- vscode (2)
- editor (2)
- setup (2)
- guide (2)
- introduction (2)
- chat (2)
- automation (2)
- misc (2)
- hyprland (2)
- browser (2)
- blog (2)
- verification (2)
- budget (2)
- video-generation (2)
- superpowers (2)
- ai-workflow (2)
- development-tools (2)
- deepseek (2)
- deepseek-harness (2)
- vibe-kanban (2)
- parallel-workflow (2)
- task-scheduling (2)
- qwen (2)
- 2025 (1)
- niri (1)
- scrollable-tiling (1)
- screen-sharing (1)
- webrtc (1)
- desktop-environment (1)
- x11 (1)
- keyboard-first (1)
- jetbrains (1)
- copilot (1)
- autohotkey (1)
- windows (1)
- docker-compose (1)
- experience (1)
- daily-use (1)
- agent (1)
- security (1)
- openness (1)
- life (1)
- summary (1)
- philosophy (1)
- claude (1)
- specialized-agents (1)
- development-workflow (1)
- github (1)
- godot (1)
- game (1)
- dev (1)
- laptop (1)
- i3wm (1)
- nvidia (1)
- wlroots (1)
- nixos (1)
- declarative (1)
- reproducible (1)
- deploy (1)
- oss (1)
- bot (1)
- js (1)
- typst (1)
- typesetting (1)
- document (1)
- template (1)
- academic (1)
- keymaps (1)
- chrome-devtools-mcp (1)
- token (1)
- pricing (1)
- openrouter (1)
- tts (1)
- python (1)
- manim (1)
- cache-hit (1)
- tmux (1)
- academic-research (1)
- cordis (1)
- multi-session (1)
- agent-runtime (1)
- ultracode (1)
- orchestrator (1)
- fzf (1)
- fuzzy-finding (1)
- research (1)
- human-ability (1)
- danmu (1)
- streaming (1)
- real-time (1)
- bilibili (1)
- md2video (1)
- agent-first (1)
- markdown (1)
- cui (1)
- harness (1)
- tool-use (1)
- gesture-recognition (1)
- magic-mouse (1)
- multi-touch (1)
- multi-provider (1)
- kimi (1)
- glm (1)
- keyboard-navigation (1)
- gui (1)
- evdev (1)
- Published on
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.- Published on
We used to split tasks by hand and launch agents one by one. Claude Code dynamic workflows (ultracode mode) now write their own orchestration script and run a fleet of subagents, shown through three real workflows that built our iread RSS reader, leaving asynchronous agent-to-agent communication as the next open problem.- Published on
After months of building tools and workflows on top of OpenCode, we are moving the daily driver back to Claude Code. The reasons are concrete: model quality after the GPT account-security change, ban risk when routing Claude through OpenCode, prefix-cache misses that burn the weekly quota, and a browser-wrapper experiment that did not return enough value to justify its complexity.- Published on
In the agent coding era, the key OS question is no longer desktop polish for humans, but safe and scriptable execution for agents. For serious AI coding workflows, Linux stands out through its permission model, CLI-first ecosystem, and open customization.