{"name":"Spec Kitty: Spec-Driven Development for AI Coding Agents and Software Factories","description":"Spec Kitty is an open-source CLI that enables spec-driven development for AI coding agents and multi-agent workflows. It transforms product intent into a structured, repo-native AI coding workflow, providing isolated git worktrees and a clear lifecycle for development tasks. This tool helps teams build governed software factories, ensuring visibility and traceability in AI-assisted software development.","github":"https://github.com/spec-kitty/spec-kitty","url":"https://osrepos.com/repo/spec-kitty-spec-kitty","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/spec-kitty-spec-kitty","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/spec-kitty-spec-kitty.md","json":"https://osrepos.com/repo/spec-kitty-spec-kitty.json","topics":["agentic-coding","ai-agents","ai-coding-workflow","spec-driven-development","kanban-workflow","multi-agent-support","python","software-development"],"keywords":["agentic-coding","ai-agents","ai-coding-workflow","spec-driven-development","kanban-workflow","multi-agent-support","python","software-development"],"stars":null,"summary":"Spec Kitty is an open-source CLI that enables spec-driven development for AI coding agents and multi-agent workflows. It transforms product intent into a structured, repo-native AI coding workflow, providing isolated git worktrees and a clear lifecycle for development tasks. This tool helps teams build governed software factories, ensuring visibility and traceability in AI-assisted software development.","content":"## Introduction\nSpec Kitty is an open-source command-line interface (CLI) designed to bring structure and governance to AI-assisted software development. It facilitates spec-driven development, transforming product intent into a repeatable, repo-native AI coding workflow. By integrating with various AI coding agents like Claude Code, Cursor, Gemini, and GitHub Copilot, Spec Kitty helps teams build robust software factories with clear processes.\n\n## Why Use It and Key Features\nSpec Kitty addresses common challenges in AI coding sessions, such as losing requirements, decisions, or acceptance criteria. It's ideal for teams moving from ad hoc \"vibe coding\" to a more structured, repeatable development workflow.\n\nKey features include:\n*   **Structured Workflow**: Guides users through `spec -> plan -> tasks -> next -> review -> accept -> merge` lifecycle.\n*   **Repository-Native Artifacts**: Stores specs, plans, work packages, and review states directly in your Git repository under `kitty-specs/`.\n*   **Parallel Development**: Utilizes isolated Git worktrees under `.worktrees/` to allow multiple agents or developers to work in parallel without branch chaos.\n*   **Visible Progress**: Offers a local Kanban dashboard (`spec-kitty dashboard`) for tracking mission progress.\n*   **Governance and Audit Trail**: Provides review, accept, and merge gates, ensuring human oversight and creating an audit trail.\n*   **Multi-Agent Support**: Integrates with a wide range of AI coding agents, including Claude Code, Codex, Cursor, Gemini, GitHub Copilot, and more.\n*   **Retrospective Learning**: Generates retrospectives for completed missions to foster continuous improvement.\n\n## Installation\nSpec Kitty is recommended to be installed using `pipx` to ensure it runs in its own virtual environment, avoiding potential dependency conflicts.\n\nTo install the CLI:\nbash\npipx install spec-kitty-cli\n\n\nAlternatively, you can use `uv` or `pip` within an activated virtual environment:\nbash\nuv tool install spec-kitty-cli\n# or, inside an activated virtual environment\npython -m pip install spec-kitty-cli\n\n\nAfter installation, initialize a new project:\nbash\nspec-kitty init my-project --ai claude\ncd my-project\nspec-kitty verify-setup\n\nReplace `claude` with your preferred agent key, such as `codex`, `cursor`, `gemini`, or `copilot`.\n\n## Examples\nHere's a quick example of the core workflow using Spec Kitty:\n\n1.  **Charter and Specify**: Define the mission and its requirements.\n    text\n    /spec-kitty.charter\n    /spec-kitty.specify Build a small task list app.\n    \n2.  **Plan and Tasks**: Create a plan and break it down into tasks.\n    text\n    /spec-kitty.plan\n    /spec-kitty.tasks\n    \n3.  **Execute Next Action**: Let Spec Kitty determine the next step for the agent.\n    bash\nspec-kitty next --agent claude --mission <mission-slug>\n    \n4.  **Review and Merge**: Review the agent's work, accept it, and merge.\n    text\n    /spec-kitty.review\n    /spec-kitty.accept\n    /spec-kitty.merge --push\n    \n\nFor a full walkthrough, refer to the official documentation.\n\n## Links\n*   **GitHub Repository**: [https://github.com/spec-kitty/spec-kitty](https://github.com/spec-kitty/spec-kitty){:target=\"_blank\"}\n*   **PyPI**: [https://pypi.org/project/spec-kitty-cli/](https://pypi.org/project/spec-kitty-cli/){:target=\"_blank\"}\n*   **Documentation**: [https://github.com/spec-kitty/spec-kitty/blob/main/docs/guides/tutorials/getting-started.md](https://github.com/spec-kitty/spec-kitty/blob/main/docs/guides/tutorials/getting-started.md){:target=\"_blank\"}","metrics":{"detailViews":1,"githubClicks":0},"dates":{"published":null,"modified":"2026-09-27T15:23:04.000Z"}}