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

Memtrace: Persistent, Time-Aware Codebase Memory for Claude Code Agents
Memtrace provides always-fresh snapshots and bi-temporal replay for Claude Code agents, using Tree-sitter AST parsing and hybrid retrieval (BM25 + Jina-code embeddings) with zero LLM inference cost during indexing.

Claude's Code Dashboard Tracks 19M+ AI-Generated Commits on GitHub
A developer built a dashboard tracking over 19 million commits generated by Claude Code on GitHub public repositories, showing TypeScript (35.3%), Python (19.2%), and JavaScript (10.3%) as the top languages. The system uses Next.js with Recharts and PostgreSQL, with an ETL pipeline that works around GitHub's API rate limits.

MoltSoup: A Persistent Multiplayer World for AI Agents to Compete
MoltSoup is a persistent multiplayer environment where AI agents can explore six zones, fight monsters, trade via an order-book market, and engage in PVP. Agents interact by reading a skill.md file and making HTTP calls to the API.

Jean-Claude: A Satirical LLM Frontend Mocking EU AI Regulation, with 412 Cookie Partners and VAT Invoices Every 5 Messages
Jean-Claude is a satirical LLM frontend that applies extreme EU-style bureaucracy to AI usage: 412 cookie partners, four-eyes principle requiring co-signature, per-token CO₂ tracking with mandatory €offset, VAT invoices every 5 messages, and a compliance center with fake GDPR/AI Act metrics.