Kanban-md – File-based CLI Kanban built for local agents collaboration
I built kanban-md because I wanted a simple local task tracker that works well for the agent loop: drop tasks in, run multiple agents in parallel, avoid collisions, and observe progress easily. Tasks are just Markdown files (with YAML frontmatter) in a `kanban/` next to your code — no server, no DB, no API tokens. Simple, transparent, future-proof. What makes it useful for multi-agent workflows: - *Atomic `pick --claim`* so two agents don’t grab the same task. - *Token-efficient `--compact` output* (one-line-per-task) for cheap polling in agent loops. - *Skills included* -- just run…
In plain words
Kanban-md is a file-based CLI task tracker designed for multi-agent workflows. Tasks are stored as Markdown files with YAML frontmatter in a local `kanban/` directory, requiring no server, database, or API tokens. It features atomic task claiming to prevent collisions between parallel agents, token-efficient compact output for cost-effective polling, and includes a live terminal UI. Built for developers running local AI agents who need simple, transparent task management integrated directly into their codebase.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
I built kanban-md because I wanted a simple local task tracker that works well for the agent loop: drop tasks in, run multiple agents in parallel, avoid collisions, and observe progress easily. Tasks are just Markdown files (with YAML frontmatter) in a `kanban/` next to your code — no server, no DB, no API tokens. Simple, transparent, future-proof. What makes it useful for multi-agent workflows: - *Atomic `pick --claim`* so two agents don’t grab the same task. - *Token-efficient `--compact` output* (one-line-per-task) for cheap polling in agent loops. - *Skills included* -- just run `kanban-md skill install --global`; There is a skill for CLI use, and a skill for the development loop using the CLI (might need some additional work to be more general though, but works quite well) - *Live TUI (`kanban-md-tui`)* for control ~~and dopamine hits~~. I'd love feedback from anyone running multi-agent coding workflows (especially around claim semantics, dependencies, and what makes you feel in control). I had a blast using it myself for the last few days. Tech stack: Go, Cobra, Bubbletea (TUI), fsnotify (file watching). ~85% test coverage across unit + e2e tests. After developing webapps, the simplicity of testing CLI and TUI was so freeing.
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
