Ross ROSS = Recommend OSS · open-source software intelligence for agents

Priivacy-ai/spec-kitty

Spec-Driven Development for serious software developers. Spec Coding with with Claude, Cursor, Gemini, Codex. Kanban dashboard, git worktrees, auto-merge and more. observed · 2026-08-28

github.com/Priivacy-ai/spec-kitty · homepage · Python · MIT (permissive) observed · 2026-08-28

Health v2 · maintenance only

77/100

  • Activity 99
  • Release rhythm 80
  • Longevity 23
How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: 0
  • age_days: 328
  • days_rel: 56
  • days_push: 7
  • n_releases_24m: 132

Full methodology

Adoption not part of the score

1573 stars · 156 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Spec Kitty is an open-source Python CLI that implements spec-driven development workflows for AI coding agents like Claude Code, Codex, Cursor, Gemini, and Copilot. It stores specs, plans, tasks, review state, and merge decisions natively in your Git repository, and gives agents isolated git worktrees so multiple agents can implement work packages in parallel with a kanban dashboard and review gates.

Use cases

  • run spec-driven development with AI coding agents
  • orchestrate multiple AI agents working in parallel on one repo
  • keep AI coding requirements and acceptance criteria in git
  • manage git worktrees for parallel agent implementation
  • track AI coding progress with a kanban dashboard
  • add review and merge gates to agentic coding workflows
  • move from vibe coding to structured spec workflows

When to choose

  • your team uses AI coding agents (Claude Code, Cursor, Codex, Gemini, Copilot, Windsurf) and loses track of requirements or decisions
  • you need multiple agents or developers working in parallel without branch chaos
  • you want specs, plans, tasks, and review state stored in Git rather than an external tracker
  • you want human review gates and an audit trail around autonomous agent coding

When to avoid

  • you only make one-off edits, small scripts, or quick prototypes
  • your team does not use Git
  • you want a fully autonomous lights-out coding pipeline with no human review
  • you need a hosted project tracker rather than a repo-native workflow

Facets

cli-tool · maturity active

cli workflow-automation agent-framework developer-tools version-control developer-tools version-control cli python cross-platform windows spec-driven-development ai-coding-agents git-worktrees kanban-dashboard multi-agent-orchestration claude-code cursor codex gemini-cli agentic-coding code-review-workflow command-line ai-agents automation macos linux

2 sources

Member repositories

RepositoryRoleHealth v2
Priivacy-ai/spec-kittymain77

For agents

markdown · JSON · MCP: product_card(name="Priivacy-ai/spec-kitty")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem