OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Coding Agents

Spec Kitty

Spec Kitty is a Python command-line tool for organizing software development around repository-stored specifications, plans, tasks, acceptance criteria and review decisions. It coordinates AI coding agents through workflow stages and isolated Git worktrees, with human review and merge gates.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Spec Kitty — OpenViST project profile in Coding Agents.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Spec Kitty when agent-assisted development needs durable requirements, defined task boundaries, progress tracking and human review before changes are accepted or merged.

Who it is for

  • Software teams using AI coding agents that need requirements and acceptance criteria to persist across sessions.
  • Teams dividing implementation into reviewable work packages for multiple agents or developers.
  • Engineering groups seeking a repository-based workflow with explicit review and merge decisions.

Documented uses

  • Turn product intent, requirements, issues or bug reports into specifications, plans and executable work packages.
  • Keep project constraints and acceptance criteria available to coding agents in the repository.
  • Separate parallel agent tasks into isolated Git worktrees.
  • Track task status through planning, implementation, review, approval and completion.
Before you choose

Requirements & limits

The documented installation options are pipx, uv, or pip within an activated virtual environment. The README specifies Python 3.11 or later and identifies the project as MIT-licensed.

  • The README lists Claude Code, Codex, Cursor, Gemini, GitHub Copilot, Windsurf and OpenCode among supported agent environments.
  • Specifications, plans, work packages, acceptance criteria and review state are stored in the repository.
  • The workflow retains human control of intent, acceptance, review and merge decisions rather than defaulting to a lights-out process.
  • The project describes its approach as local and repository-first, with hosted tracker and sync integrations mentioned as optional.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up Spec Kitty in a project

Install the CLI, initialize a repository for a selected coding agent, and verify the project setup.

Before you start

  • Python 3.11 or later.
  • A project repository.
  • An agent key, such as claude, codex, cursor, gemini, copilot, opencode, or windsurf.

Steps

  1. Install the CLI with pipx install spec-kitty-cli, the command below, or the command below inside an activated virtual environment.

    Documented command
    uv tool install spec-kitty-cli
    Documented command
    python -m pip install spec-kitty-cli

  2. Run spec-kitty init my-project --ai claude to create a project, or use spec-kitty init . --ai in the current repository.

  3. Enter the project directory if you created one, then run spec-kitty verify-setup.

Expected outcome

The project is initialized for the selected agent and the CLI's setup check has been run.

Guide limitations

  • This guide covers setup only; it does not verify a complete coding mission or successful agent execution.
  • The README names agent keys but does not detail setup requirements for each agent environment.
Documentation 1 ↗
Source-based practical guide

Create and review a specification-driven mission

Use the documented agent workflow to define a project, create its plan and tasks, and move work through review and acceptance.

Before you start

  • Spec Kitty installed and initialized in a project.
  • An AI coding agent open in the project.

Steps

  1. Run /spec-kitty.charter to define the project charter.

  2. Run /spec-kitty.specify with a concrete product request, then run /spec-kitty.plan and /spec-kitty.tasks.

  3. Use spec-kitty next --agent --mission to ask for the next action.

  4. Run /spec-kitty.review, /spec-kitty.accept, and /spec-kitty.merge --push as the work proceeds through review, acceptance and merge.

Expected outcome

A mission follows the documented specification, planning, task, review, acceptance and merge stages.

Guide limitations

  • The README does not guarantee successful implementation or merge; review and acceptance are explicit stages.
  • The mission slug and selected agent must correspond to the project and work being handled.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for AI coding assistance

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
Spec KittyTurn product intent, requirements, issues or bug reports into specifications, plans and executable work packages.CLI, ServerThe documented installation options are pipx, uv, or pip within an activated virtual environment. The README specifies Python 3.11 or later and identifies the project as MIT-licensed.
SpectraClarify requirements and compare approaches before proposing a change.CLI, DesktopThe README lists a macOS and Windows desktop app, and a Homebrew installation for macOS. The CLI is published through npm and requires Node.js 22.14 or newer.
Skills — michaelshimelesInstall reusable task-specific skills into a coding-agent setup.CLIThe repository README provides an npx installation command for most coding agents and describes automatic or explicit skill invocation in Claude Code.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
13 October 2026
Original website title
spec-kitty/spec-kitty · Official homepage title · retained in its source language
How we review sourcesSuggest a correction