Skip to main content

taskai

A command-line task manager with AI features.

📖 Full documentation: https://taskai.readthedocs.io

pip install taskai-cli

Setup

task setup

Commands

task                              interactive mode
task help                         show every command
task examples                     worked command sequences for common workflows

task show all                     show everything
task show <id|name>               show a specific item

task create <name>                create a top-level item
task add <parent> <name>          add a child item
task update <id> --field value    update any field
task rename <id> <new name>       rename an item
task move <item> <new parent>     reparent an item
task complete <id>                mark complete (recursive)
task delete <id|name>             delete by id or name
task clear                        delete all completed items
task clear <parent>               delete completed under a parent

task comment <id> <text>          add a comment
task link <parent> <item>         soft-link an item under a second parent
task unlink <parent> <item>       remove a soft-link
task reorder <id1> before|after <id2>

task <field> <id> <value>         set one field: description, due, priority, status, color
                                  (leave the value off to clear it)
task pomo <on_mins> <off_mins>    pomodoro timer

task ai <prompt>                  natural language → commands
  --context <path[,path...]>      fold file contents into the prompt
  --reasoning <level>             model thinking effort: minimal|low|medium|high|disable|none
task ai headstart <id>            AI suggests next step, saved as comment

task browser                      launch the web UI (see below)

task config show                  list current config
task config set <key> <value>     set a config value
task config get <key>             get a config value
task config pop <key>             remove a config value

task repair                       repair the database
task nuke                         delete all data (asks to confirm)

Item fields

Pass any of these as --field value to create, add, or update:

Field Format Example
description string --description "needs review"
due MM-DD-YYYY --due 08-15-2026
priority integer --priority 2
status string --status "in progress"
completed bool --completed true
color CSS color --color "#ff8844"

Config

AI features need a model. task setup walks you through choosing a provider and model, then tells you which environment variable(s) to set:

$ task setup
Beginning setup
  1. openai
  2. anthropic
  3. gemini
  4. vertex_ai
  5. groq
  ...
  20. ollama

Select a provider (number or name): 3
  1. gemini-3.7-flash
  2. gemini-3.1-pro-preview
  3. gemini-3.6-flash
  4. gemini-3.5-flash-lite
  5. gemini-2.5-pro

Select a model for 'gemini' (number or name): 1
Storing: gemini/gemini-3.7-flash
Make sure these environment variables are set:
  GEMINI_API_KEY
Setup complete! Use 'task config set|get|list' to interact with your configuration options

Either prompt also accepts free-typed text, so you can pick a model newer than the built-in menu.

Or set it directly — a provider/model string, using litellm's naming:

task config set AI_MODEL <provider>/<model>   # e.g. gemini/gemini-3.7-flash

Web UI

task browser

Launches a local web server with a canvas view of your item tree:

  • pan / zoom the graph; completed items are tinted green, and soft-links (task link) show as dashed "shadow" copies under their host item
  • click a node to open an edit panel — each field writes back immediately, there's no save button
  • console at the bottom for typing raw task commands against the same data

Examples

task create "Launch website"

# add subtasks (by name or id)
task add "Launch website" "Write copy"
task add "Launch website" "Design mockups" --priority 1
task add "Launch website" "Set up hosting" --due 08-15-2026

# check your work
task show "Launch website"

# ask AI what to do first on a specific task
task ai headstart 3

# mark something done and clean up
task complete 2
task clear "Launch website"

Or drive it entirely from a prompt:

task ai "add a task called 'Reply to Alex' under Launch website, and mark the hosting task as done"

Run task examples for more worked sequences.

Metadata

Release files for taskai-cli 1.10.2

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

Source distribution (sdist)

Source distribution for taskai-cli 1.10.2
File Size Uploaded Provenance Actions
taskai_cli-1.10.2.tar.gz 122.5 kB With provenance Details for taskai_cli-1.10.2.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for taskai-cli 1.10.2
File Interpreter ABI Platform Actions
taskai_cli-1.10.2-py3-none-any.whl Python 3 none any Details for taskai_cli-1.10.2-py3-none-any.whl

Total release size: 188.1 kB

Release files / taskai_cli-1.10.2.tar.gz

Download URL taskai_cli-1.10.2.tar.gz
Size 122.5 kB
Tags Source
SHA-256 checksum
How to use checksums
56590f8da8873871c29339b061890ff54fcadeb9a8a82783b411ee19b8ce6696
BLAKE2b-256 checksum
How to use checksums
869b6a7621c7fc414e1a32df78af24893fde1612e01a48c6aa272c1f68bf5e93
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 26, 2026.

Transparency log

Release files / taskai_cli-1.10.2-py3-none-any.whl

Download URL taskai_cli-1.10.2-py3-none-any.whl
Size 65.6 kB
Tags Python 3
SHA-256 checksum
How to use checksums
3a4eb7c8041313752431a9e9b886e7aad36899b4a9874039fe5741a6e0f39620
BLAKE2b-256 checksum
How to use checksums
d805b6c2726b5fc6105141641f307e4a5d2678384d8b17dedbbc1bbef0ec5fc3
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 26, 2026.

Transparency log

Security for taskai-cli 1.10.2

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Full provenance

Both files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for taskai_cli-1.10.2.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 26, 2026.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

1.10.2 This release

2 release files Full provenance

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