Kanban CLI: A Local-First, Agent-First Task Manager for the Terminal

Kanban CLI is a local-first, agent-first terminal-based project management tool written in Rust. It brings structured agile workflows to the command line, with deep git integration designed to tame the randomness of AI coding agents.
Workflow: Skills, Isolation, Review
The tool defines a 4-step workflow for agent-driven development:
- The model reads a skill to contextualize requirements.
- It authenticates and receives a strict, schema-validated JSON payload outlining exact files, context, and acceptance criteria.
- Implementation runs inside an automatically isolated Git worktree and branch. The tool tracks progress (e.g., verifying all files edited) before submission.
- A human reviewer evaluates the submission and manually transitions the task to “Done,” triggering the final merge and cleanup.
Key Features
- Rust-based – compiled binary, no runtime dependency.
- Git integration – automatic branch/worktree isolation per task.
- JSON schema validation – enforces required fileds in agent output.
- Role Pool system – built-in roles with claim workflow.
- Sprint lifecycle – scope creep detection, velocity tracking.
- Statistics engine – tracked metrics with recalibration support.
- Local-first storage – JSON-backed, atomic writes, file locking.
Project Structure
The repository is organized with clear documentation:
README.md– acts as an index to all documentation files.Concept docs– tasks, sprints, roles, statistics.Architecture docs– layered design, data model, concurrency.Reference docs– CLI commands, JSON output format, role pool.Development docs– Rust conventions, coding style.
Getting Started
Install via Nix or Cargo (see documentation for details). Initialize a project, create a task, assign a role, claim, and complete. All operations are local-first — no server needed.
The tool targets developers who want to enforce rigorous guardrails on agent-driven development while keeping full control in the terminal.
📖 Read the full source: HN AI Agents
👀 See Also

Setting Up OpenClaw as an Always-On AI Assistant
OpenClaw, configured as an always-on AI assistant for a small dev team, is set up on a Railway server with Claude as the backend and integrates with Google Workspace, GitHub, and more.

Claude Code Plugin 'nice-figures' Creates Research-Blog Style Matplotlib Plots
nice-figures is a Claude Code plugin that generates matplotlib figures matching Anthropic's soft-pastel research blog style. Includes 16 chart recipes, zero extra dependencies, and automatic styling.

First-Tree: Open-Source Daemon That Uses Claude Code to Triage GitHub Notifications While You Sleep
An open-source menu bar daemon that uses Claude Code to autonomously triage GitHub notifications – it handled 98 out of 100 notifications in a recent scan, leaving only 2 for human review.

OpenClaw memory fix tool addresses performance degradation
A new slash command called /claw_memory_fix helps clean up OpenClaw memory files when the agent forgets credentials or permissions. The tool implements techniques from Alibaba, GitHub engineering, MemGPT, and January 2026 research on memory management.