Show HN: VS Code Agent Kanban: Task Management for the AI-Assisted Developer

“Context rot” with AI coding tools is definitely real. After a few sessions the agent forgets earlier decisions, and you end up repeating the same planning conversation again.

Storing the plan and discussion as Markdown in Git is an interesting approach. It basically treats the agent’s reasoning as part of the project history, not just the final code.

Curious if others here are doing something similar to keep context across sessions.

OpenKanban is pretty cool if you’re on the other end and want to use Terminal for both Coding and Task/Project management. It’s almost as good as a Terminal version of VibeKanban, but not so feature rich - https://github.com/TechDufus/openkanban

I am using another VSCode Kanban extension. Very similar workflow to this one. I am very happy with it, it solved many issues I am having with context.

https://github.com/LachyFS/kanban-markdown-vscode-extension

Lane position should be managed by putting files into different folders.

Name and dates can also be stored in the filename and file metadata.

Intro: https://www.appsoftware.com/blog/introducing-vs-code-agent-k...

Youtube (Quick demo): https://www.youtube.com/watch?v=Y4a3FnFftKw

GitHub: https://github.com/appsoftwareltd/vscode-agent-kanban

I can certainly see the appeal of distributing the context with vc. However, I have always imagined this to be integrated into an existing kanban workflow, similar to a Jira or gh issue board. Perhaps agent specific, perhaps not.

Furthermore, an existing kanban (ticket) workflow will expect you to refine the context into something more ... concentrated, or at least something that we are used to seeing as developers working with tickets, at least more so than the chat history that seem to be favored.

Have you put any thought into how this would integrate into such a process?

Excited to see many version of such tools to pop up, was also planning on building my own actually. Hope people can share the most competitive ones here in the comments.

The .md task format as persistent source of truth is the key insight. Context rot is a real problem mid-sprint when agents lose track of earlier decisions. Do you diff against previous state if the agent rewrites a task file mid-execution, or does the human review before committing?

For a long time I've been an agile fundamentalist. I welcome agent assisted coding because it reduces team size and increases autonomy, experimentation, and generally makes self organizing teams a more obvious choice.

Highly structured pseudo agile practices like scrum, never mind SAfE, make even less sense now than they did before. Flat collegial teams for the win.

There's also https://github.com/openai/symphony that's being developed following a similar Kanban pattern based agent manager (though yours is more sophisticated at the moment imo)

Interesting to see the Kanban workflow being adapted to managing agents, makes sense; each item having the same UX as a Github Issue.

Great to see more products in this space! Definitely going to try this out on desktop.

I’m doing a fair amount of work on mobile, and prompting remote agents. I would love someone to build an OSS cross-platform kanban. It’d probably be complex to add triggers of workflows both locally and remotely though.

Sorry for the slightly unrelated comment, but the amount of AI written slop comments here is so high. Was this caused by mentioning "AI" in the title?

This is interesting. We've seen markdown as the app. This is markdown as the database for your tasks.

I had claude build me something similar for my own autonomous agent system, because I was irritated at how much friction Jira has. I suspect a lot of people will do this.

As a project manager returning to coding after 20 years — this is directly relevant to my experience. AI can genuinely augment both productivity and creativity, but it needs strong process and constraints to do it well. What separates throwaway AI code from something maintainable is product vision and tooling that keeps the AI focused. This looks like a step in that direction.

Every time I see this phrase: "Why This Matters"

I wish I could unread it.

interesting feature!

[dead]

[flagged]

[dead]