Skip to main content

AI-powered Kanban TUI for autonomous development workflows

Project description

Kagan

A terminal task board that runs AI agents on your code — you review, you decide, you merge.

PyPI Python License: MIT Stars Discord

Snyk

DocumentationQuickstartMCP SetupCLI ReferenceIssues


Kagan Demo

Create a task. Pick a mode. The agent works. You review, approve, and merge.

Install

=== "UV (Recommended)"

uv tool install kagan

=== "Mac / Linux"

curl -fsSL https://uvget.me/install.sh | bash -s -- kagan

=== "Windows (PowerShell)"

iwr -useb uvget.me/install.ps1 -OutFile install.ps1; .\install.ps1 kagan

=== "pip"

pip install kagan

Requirements

  • Python 3.12 -- 3.13, Git, terminal 80x20+
  • tmux (recommended for PAIR sessions on macOS/Linux)
  • VS Code or Cursor (PAIR launchers, especially on Windows)

Usage

kagan              # Launch TUI (default command)
kagan tui          # Launch TUI explicitly
kagan core status  # Show status of the core process
kagan core stop    # Stop the running core process
kagan mcp          # Run as MCP server (connects to core via IPC)
kagan tools        # Stateless developer utilities (prompt enhancement)
kagan update       # Check for and install updates
kagan list         # List all projects with task counts
kagan reset        # Reset data (interactive)
kagan --help       # Show all options

Ways to Use Kagan

TUI (interactive)

Run kagan -- create tasks, run AUTO/PAIR workflows, review/rebase/merge, switch projects.

Editor (MCP)

Operate Kagan from Claude Code, Gemini CLI, or any MCP-compatible client -- no TUI required:

kagan mcp --capability pair_worker

Start with pair_worker. Escalate to maintainer when needed. See MCP setup for editor configs.

Features

  • Kanban lifecycle: BACKLOG -> IN_PROGRESS -> REVIEW -> DONE
  • Task CRUD, duplicate, inspect
  • Work modes: AUTO (background agent) / PAIR (interactive session)
  • Chat-driven planning with approval flow
  • Review: diff, approve/reject/rebase/merge
  • Multi-repo: project switching, base-branch controls
  • PAIR handoff: tmux / VS Code / Cursor session management
  • MCP: 23 tools spanning tasks, sessions, review, planning, projects, audit, settings
  • Core daemon management: run, inspect, stop

Supported Agents

Docs

docs.kagan.sh -- Quickstart | MCP Setup | Editor MCP Setup

License

MIT


Star History

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

kagan-0.6.0b1-py3-none-any.whl (598.3 kB view details)

Uploaded Python 3

File details

Details for the file kagan-0.6.0b1-py3-none-any.whl.

File metadata

  • Download URL: kagan-0.6.0b1-py3-none-any.whl
  • Upload date:
  • Size: 598.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for kagan-0.6.0b1-py3-none-any.whl
Algorithm Hash digest
SHA256 9f9469b212cb4af06ccc17225c835528af9e5c1a028e0cbc8dfed6023f99424b
MD5 13c08f9d31f56a0e871fe793da24ac5d
BLAKE2b-256 f4a6c53bcf1de782541d4b676357935fe07b5e59c360295ecf4d4b5168b0c650

See more details on using hashes here.

Provenance

The following attestation bundles were made for kagan-0.6.0b1-py3-none-any.whl:

Publisher: cd.yaml on kagan-sh/kagan

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page