Skip to main content
Documentation Status https://github.com/MacHu-GWU/shai_tix-project/actions/workflows/main.yml/badge.svg https://codecov.io/gh/MacHu-GWU/shai_tix-project/branch/main/graph/badge.svg https://img.shields.io/pypi/v/shai-tix.svg https://img.shields.io/pypi/l/shai-tix.svg https://img.shields.io/pypi/pyversions/shai-tix.svg https://img.shields.io/badge/✍️_Release_History!--None.svg?style=social&logo=github https://img.shields.io/badge/⭐_Star_me_on_GitHub!--None.svg?style=social&logo=github
https://img.shields.io/badge/Link-API-blue.svg https://img.shields.io/badge/Link-Install-blue.svg https://img.shields.io/badge/Link-GitHub-blue.svg https://img.shields.io/badge/Link-Submit_Issue-blue.svg https://img.shields.io/badge/Link-Request_Feature-blue.svg https://img.shields.io/badge/Link-Download-blue.svg

Welcome to shai_tix Documentation

https://shai-tix.readthedocs.io/en/latest/_static/shai_tix-logo.png

File-based task management for AI agents with human-editable markdown storage.

What is shai_tix?

shai_tix is a JIRA-like project management system designed for AI agents. Instead of clicking through web UIs, AI agents (like Claude Code) use simple CLI commands to manage your project. You just tell the AI what you want in natural language, and it handles creating stories, tracking tasks, and updating status.

Key Benefits:

  • Voice-Driven Project Management: Tell your AI agent “create a story for user authentication with three tasks”, and it’s done

  • 100% Git-Friendly: All data lives in markdown files - track changes, review history, merge conflicts like code

  • Zero Vendor Lock-in: Plain files mean easy migration - no database exports, no API migrations

  • Human-Editable: Browse and edit .tix/ directory directly when needed

Why Not Just Use JIRA/Trello/etc?

Traditional project management tools are designed for humans clicking through UIs. When AI agents need to manage tasks, they face:

  • Complex APIs with authentication and rate limits

  • Heavyweight dependencies and network latency

  • Data locked in proprietary formats

shai_tix solves this by storing everything as local files:

  • AI agents use fast CLI commands with instant response

  • Humans get readable markdown they can edit anywhere

  • Git provides version control, history, and collaboration for free

Design Philosophy

Dual Storage Architecture

  • Filesystem (Source of Truth): Human-readable directories and markdown files

  • SQLite Index (Cache): Fast queries without scanning directories

Simple Two-Level Hierarchy

Story (Feature or Epic)
└── Task (Atomic work unit)

No deep nesting. If a task needs subtasks, promote it to a story.

CLI Commands Overview

Story Management

  • create_story: Create a new story (epic/feature)

  • get_story: View story details including description and report

  • list_stories: List all stories, newest first

  • search_stories: Find stories by title, status, date, or ID range

  • update_story: Update story title, status, description, or report

  • delete_story: Delete a story and all its tasks

Task Management

  • create_task: Create a task under a story

  • get_task: View task details including description and report

  • list_tasks: List all tasks, newest first

  • list_tasks_by_story: List tasks under a specific story

  • search_tasks: Find tasks by title, status, date, or ID range

  • update_task: Update task title, status, description, or report

  • delete_task: Delete a task

Index Management

  • rebuild_index_db: Sync SQLite index with filesystem (call before batch queries)

Quick Start

For AI Agents (CLI):

# Create a story and tasks
shai-tix create_story "User Authentication" --description "Implement login/logout"
shai-tix create_task 1 "Create login form"
shai-tix create_task 1 "Add session management"

# Query and update
shai-tix list_stories
shai-tix search_tasks --status TODO
shai-tix update_task 2 --status IN_PROGRESS
shai-tix update_task 2 --status COMPLETED --report "Login form implemented with validation"

For Humans (File System):

.tix/
├── index.sqlite                    # Fast query index (auto-generated)
└── stories/
    └── story-2025-01-15-00001-user-authentication/
        ├── metadata.json           # {"status": "IN_PROGRESS"}
        ├── description.md          # Story description (editable)
        ├── report.md               # Completion report (optional)
        └── tasks/
            └── task-2025-01-15-00002-create-login-form/
                ├── metadata.json   # {"status": "COMPLETED"}
                ├── description.md  # Task description
                └── report.md       # Task completion report

Status Values

  • TODO: Not started

  • IN_PROGRESS: Currently being worked on

  • COMPLETED: Finished

  • BLOCKED: Blocked by external dependencies

  • CANCELED: Canceled

Install

shai_tix is released on PyPI, so all you need is to:

$ pip install shai-tix

To upgrade to latest version:

$ pip install --upgrade shai-tix

Metadata

Release files for shai-tix 0.1.3

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for shai-tix 0.1.3
File Size Uploaded
shai_tix-0.1.3.tar.gz 21.7 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for shai-tix 0.1.3
File Interpreter ABI Platform
shai_tix-0.1.3-py3-none-any.whl Python 3 none any Details

Total release size: 44.3 kB

Release files / shai_tix-0.1.3.tar.gz

Download URL shai_tix-0.1.3.tar.gz
Size 21.7 kB
Tags Source
SHA-256 checksum
How to use checksums
f28e38e302c484d37092900de2b4e623593436a08ba901d8c72041a808c40eec
BLAKE2b-256 checksum
How to use checksums
885bd3464c47ac02d756c74557f89837fadf8234677c75c21200bcbc93848de3
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.1.0 CPython/3.11.8

Release files / shai_tix-0.1.3-py3-none-any.whl

Download URL shai_tix-0.1.3-py3-none-any.whl
Size 22.6 kB
Tags Python 3
SHA-256 checksum
How to use checksums
073a99e48a148df484a74ea198832f14ea050f6f71d669421e4adcb691794a95
BLAKE2b-256 checksum
How to use checksums
aec53073c688dc4735cc018d335eb0ccfd56ca7fd5392520c9dd222557a1545e
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.1.0 CPython/3.11.8

Release history Release notifications | RSS feed

This release

0.1.3 This release

2 release files

0.1.2

2 release files

0.1.1

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page