Preview. These maps are our reading of public sources and haven't been checked with the projects' maintainers yet.
Taskmaster AI
PRD-to-task-graph manager (CLI + MCP) that parses a requirements doc into dependent tasks for Cursor, Claude Code and others; now documented under Hamster, the authors' hosted planning product.
tryhamster.com/docs/taskmasterMaintenance
Last release task-master-ai 0.43.1 on 2026-03-31; last commit 2026-04-23 only re-pointed retired task-master.dev links to tryhamster.com; nothing since (2026-10-25) (checked 2026-10-25)
In Spec-driven development
Where it stands apart
- Is it actively maintained? maintenance or slowing (11% of 19 others)
- How is the main thing licensed? copyleft or source-available with restrictions (5% of 19 others)
- Do you need an account to use it? optional account (5% of 19 others)
- Which shared standard or format does it mainly build on? Model Context Protocol (MCP) (5% of 19 others)
- After implementation, what built-in step keeps specs and code aligned? (if several, the first that applies) nothing built in (22% of 18 others)
- What format are specs written in? a structured schema or dedicated spec language (6% of 18 others)
- What form does it mainly ship in? a CLI or MCP server that itself reads and writes the spec or task files (16% of 19 others)
- Does a human approve the spec or plan before code is written? no approval step (6% of 18 others)
What it shares with most of the community
- How is it mainly sustained? company with a paid product, tier, or ads (50% of 18 others)
- Can it run entirely on your own device or infrastructure, without the maker's servers? yes (79% of 19 others)
- Who is it for? developers (100% of 19 others)
- Once code exists, what is the spec? a planning scaffold: code becomes the truth after implementation (53% of 19 others)
- Where do specs live? plain files in the project repository (89% of 19 others)
- Which coding agents does it work with? many agents (five or more) (78% of 18 others)
- By default, once a plan is approved, how is implementation run? the human drives it, phase by phase or task by task (50% of 18 others)
Nearest neighbors
- Spec Workflow MCP 65% of 17 shared answers match
- Spec Kitty 53% of 17 shared answers match
- Agent OS 47% of 17 shared answers match
Every answer
| Question | Answer | Source |
|---|---|---|
| Is it actively maintained? | stands apart maintenance or slowing | source 2026-10-25 |
| How is the main thing licensed? | stands apart copyleft or source-available with restrictions MIT with Commons Clause: cannot sell Taskmaster itself as a service. | source 2026-10-25 |
| How is it mainly sustained? | company with a paid product, tier, or ads Team use goes through Hamster (cloud storage, sync); © Wheel Go Fast, Inc. | source 2026-10-25 |
| Can it run entirely on your own device or infrastructure, without the maker's servers? | yes Runs locally with your own API keys; Hamster cloud optional. | source 2026-10-25 |
| Do you need an account to use it? | stands apart optional account Solo mode is local; team mode needs a Hamster login. Model keys are from providers, not the maker. | source 2026-10-26 |
| Who is it for? | developers | source 2026-10-25 |
| Which shared standard or format does it mainly build on? | stands apart Model Context Protocol (MCP) Delivered to agents as an MCP server (plus CLI); tasks.json is its own. | source 2026-10-26 |
| Once code exists, what is the spec? | a planning scaffold: code becomes the truth after implementation PRD is parsed once into tasks; tasks, not the PRD, drive work. | source 2026-10-25 |
| After implementation, what built-in step keeps specs and code aligned? (if several, the first that applies) | stands apart nothing built in | source 2026-10-25 |
| What format are specs written in? | stands apart a structured schema or dedicated spec language Tasks in a JSON schema (tasks.json) with dependencies; PRD is free text. | source 2026-10-25 |
| Where do specs live? | plain files in the project repository Local .taskmaster folder; Hamster adds cloud sync for teams. | source 2026-10-25 |
| Which coding agents does it work with? | many agents (five or more) Cursor, Windsurf, VS Code, Claude Code, Q CLI, Codex, etc. | source 2026-10-25 |
| What form does it mainly ship in? | stands apart a CLI or MCP server that itself reads and writes the spec or task files CLI and MCP server that parse a PRD into tasks and store them in local tasks files. | source 2026-10-26 |
| How is the path from idea to code structured? | no fixed phases PRD -> parse -> expand -> next task; no gated phases. | source 2026-10-25 |
| Does a human approve the spec or plan before code is written? | stands apart no approval step Users can review generated tasks, but no approval step is built in. | source 2026-10-25 |
| By default, once a plan is approved, how is implementation run? | the human drives it, phase by phase or task by task 'next task' loop; a loop command can automate. | source 2026-10-25 |
| What does it offer teams beyond sharing files in git? (if both, pick the paid product) | team features in a paid hosted product Team collaboration via Hamster. | source 2026-10-25 |
Sources
This page was derived from:
- GitHub · github.com/eyaltoledano/claude-task-master · read 2026-10-25
- GitHub · github.com/eyaltoledano/claude-task-master/releases · read 2026-10-25
- Web page · registry.npmjs.org/task-master-ai · read 2026-10-25
- Web page · tryhamster.com/docs/taskmaster · read 2026-10-25
- Web page · tryhamster.com/docs/taskmaster/capabilities/task-structure · read 2026-10-25
- Web page · tryhamster.com/docs/taskmaster/ide-setup/supported-editors · read 2026-10-25
- Web page · tryhamster.com/docs/taskmaster/team/overview · read 2026-10-25
Are you a maintainer? Claiming and correcting projects is coming soon.