Back to directory

Agent Kanban

A task board built for autonomous coding agents rather than people, where agents claim and execute tasks through machine-discoverable APIs while humans review and approve the work.

Agent Kanban

Agent Kanban is a mission-control board for autonomous software agents, treating agents as first-class actors rather than a convention layered on a human-only board. Assignment, execution provenance, task dependencies, review and inter-task communication are part of the product model.

It provides agent-native operations through authenticated tools and a live OpenAPI contract, human review gates that require an authorized actor other than the assignee to accept or reject submitted work, verified execution provenance tied to a signed session binding, dependency-aware planning that rejects cycles, live streaming of task activity, and public read-only board views. It ships as one Cloudflare Worker with a D1 database, combining a React frontend and a Hono API.

More in Coding agents

See all 793
  • The City

    github.com

    A native macOS app that shows Claude Code runs as a city, with each project as a building, each team as a floor of robots, and every animation driven by a real event from the claude CLI's stream.

  • rig

    tryrig.ai

    A small, single-binary agent runtime that points at any OpenAI-compatible model, local or hosted, reads and edits a repository's code, runs its tests and remembers what it learned, with a loop implemented in a few hundred lines.

  • Jauvex

    jauvex.reindent.com

    An Electron desktop app that puts Claude Code, Codex and Grok coding-agent sessions side by side and lets you steer them by voice, with a small model handling fast routing decisions.