Source: https://spec-kitty.ai/ # Spec Kitty | Decision layer for autonomous software delivery > Your AI agents write the code. Your people make the calls. Spec Kitty makes sure coding agents build with what your experts know and what your team decided. Free, MIT CLI for Claude Code, Codex, Cursor, Copilot and 20+ more. _Decision layer for autonomous software delivery_ ## Your AI agents write the code. Your people make the calls. Coding agents now make thousands of small decisions at machine speed. Spec Kitty makes sure they build with what your experts know and what your team decided. [Start free with the CLI](https://spec-kitty.ai/getting-started.md) · [Book a demo](https://spec-kitty.ai/contact?topic=demo) - Free and open source (MIT) - Works in Claude Code, Codex, Cursor, Copilot and 20+ more - Your models, your keys **GitHub stars** 1,677 **CLI downloads in the last 6 months** 28.1k **Open-source contributors** 100+ As of 8 Oct 2026. Sources: GitHub, PyPI. ## Red button or blue button? Every real system is thousands of red-or-blue calls, usually made by whoever is at the keyboard, and now by AI agents at machine speed. Deciding them well is still a human job, and most teams have no system for it. - Problem 1 **Agents never read the wiki** Your standards and past decisions live in people's heads and in wikis agents never read. The same ticket comes out differently depending on who picks it up. - Problem 2 **Decisions made in chat get lost** When behavior changes, nobody can show who decided it, why, or what it was checked against. The reasoning stayed in a chat window. - Problem 3 **Agents grade their own work** The agent that wrote the change is the one that says it's fine. Review becomes a rubber stamp at machine speed. ## Know what you decided. Decide what applies. Build with it. Start with the free CLI today; add your team's knowledge when you are ready. 1. 1 · Know: Contact us **Brain Kitty** Each person curates their own knowledge graph of the standards, runbooks, rules and decisions they own. Answers cite it, and people approve every change. [See Brain Kitty](https://spec-kitty.ai/index.md#years-of-how-you-work-in-a-form-agents-can-use) 2. 2 · Decide: Early access **Team Kitty** The hosted team product. It collects the team's Brain Kitty graphs so the team decides together what applies, then serves it to Build Kitty over MCP, the standard way coding agents load outside knowledge. [Request early access](https://spec-kitty.ai/contact?topic=early-access) 3. 3 · Build: Free, MIT **Build Kitty** The free Spec Kitty CLI. Agents spec, plan, build and review in the coding agent you already use, with the knowledge Team Kitty serves over MCP and checks an agent can't skip. [See how it works](https://spec-kitty.ai/index.md#from-what-your-people-know-to-merged-reviewed-work) Work solo for free. Bring in Team Kitty when you invite your team. ## Years of how you work, in a form agents can use. Each person curates their own Brain Kitty: a knowledge graph of the standards, runbooks, rules and decisions they own. Every answer cites its source. - **Ask.** Before the decision: what was already decided, cited, the same answer every time. - **Check.** After the work: new work reviewed against what was decided, with the evidence quoted. - **People approve.** Brain Kitty proposes and informs. It never silently changes what was decided. [Contact us about Brain Kitty](https://spec-kitty.ai/contact?topic=brain-kitty) ![Brain Kitty knowledge graph: 31 dimensions, 65 plays, 8 decision rules and 24 rulings drawn as linked nodes, a ranked list of matching nodes, and an agent chat panel answering a question about Spec Kitty and citing the ruling it used.](https://spec-kitty.ai/cms/brain-kitty-knowledge-graph.webp) Brain Kitty: your standards and rulings as a graph, with an agent answering from it. ## From what your people know to merged, reviewed work 1. **Each person curates their Brain Kitty** The standards, runbooks, rules and decisions you own, in your own knowledge graph. You decide what goes in and approve every change. Brain Kitty proposes updates; it never changes what was decided on its own. 2. **Team Kitty combines them** Team Kitty brings everyone's Brain Kitty together and serves it to every coding agent over MCP. The team decides together what applies to its work. Agents load only what the team chose, and only the slice each step needs. 3. **Provide answers, read the spec** Build Kitty asks what to build and how, with your team's knowledge loaded. You answer, then review and edit the spec before any code. Agents write the spec, plan and work packages. 4. **Agents build in parallel** Each work package runs in its own git worktree, so agents don't collide. You schedule the work packages like any other work. Agents build, each in its own worktree. 5. **A second reviewer checks, you merge** The work is checked against the spec and your team's knowledge before it lands. You merge. Nothing lands without a person. A reviewer that isn't the author checks the work. From a first workshop > “A ticket our own engineers had sized at ten days went out the door in about five hours, during the workshop, on our first time using it.” Engineering leadership, legacy Java ERP platform One team's result on one ticket, not a benchmark. [See the rollout workshop](https://spec-kitty.ai/training.md) ## Pick your starting point. - Engineering executives · **[Your organization's knowledge, in every team's AI coding agents.](https://spec-kitty.ai/executives.md)** · What your experts know reaches every team's agents, and leadership can see what was decided and why. · Brain Kitty + Services - Engineering managers · **[Your team's standards, in every engineer's coding agent.](https://spec-kitty.ai/engineering-managers.md)** · One way of working for the whole team: same standards, same review, whoever picks up the ticket. · Team Kitty + CLI - Product and program managers · **[Agents build what you decided.](https://spec-kitty.ai/product-managers.md)** · Product decisions written down, cited every time, and built by every agent. · Brain Kitty + Team Kitty - Developers · **[Stop babysitting your coding agent.](https://spec-kitty.ai/developers.md)** · Free. Your agent asks first, works in its own worktree, and gets a second reviewer. · Build Kitty (free CLI) - Use case · **[Modernize legacy code with AI agents, one reviewable step at a time.](https://spec-kitty.ai/legacy-modernization.md)** · The free CLI turns a legacy rewrite into small, specced, reviewed steps your team can schedule. · Legacy modernization ## Your knowledge. Your decisions. Agents that follow. Start free with the CLI, or book a demo. Our rollout packages leave working software behind. [Start free with the CLI](https://spec-kitty.ai/getting-started.md) · [Book a demo](https://spec-kitty.ai/contact?topic=demo) [Rollout packages](https://spec-kitty.ai/training.md)