Cat Factory

A visual board, task management, and LLM coding agents in one place. Turn tasks into reviewed pull requests you can watch run end to end. Run it on your own machine, on the coding subscriptions you already pay for.

Get Started →Core Concepts

100% free and open source

MIT licensed, no paid tier, no open-core holdback, nothing behind a license key. You run the whole platform on your own infrastructure, so your code, data, and model credentials never leave it.

The board is the plan

Lay out services, modules, and tasks on a pannable, zoomable canvas. Every block is both your plan and a unit of work, so there's no separate backlog to keep in sync.

Agents do real work

Coding agents clone your repository, implement the task, and open a pull request. A block is "done" only when its PR is merged with passing CI.

Multi-stage pipelines

Compose ordered agent chains (Architect → Coder → Reviewer → Tester → Acceptance) with default models per agent kind and human decision points along the way.

Human in the loop

A reviewer agent flags open questions and risky assumptions before code is written. You answer the questions, approve the plan, and review every PR before merge.

Run it your way

Heavy cloud workloads on Cloudflare Workers or self-hosted Node.js, or the whole platform on one machine in local mode. Run agents on coding subscriptions you already pay for instead of metered API spend.

What it does

You lay out work on a visual board. LLM agents pick up each block, implement it against a real repository checkout, and open pull requests for your team to review and merge. The same board is where you watch every run as it happens and step in when an agent needs you. It is self-hosted and MIT licensed, so the whole platform is yours to run.

Where to next?

Each card matches a section of the docs sidebar, so the path you pick here is the same one you will follow in the navigation.

Start — new here?

Read the Introduction and Core Concepts, then take the first-task tutorial end to end.

Guides — using it day to day?

Design your board, run a pipeline, or change a flow you already run with a short recipe from the Cookbook.

Deploy — want it running?

Pick a runtime — local, Cloudflare, or Node.js — and sign people in through your directory with enterprise SSO.

Operate — running it in production?

Set up observability, keep Troubleshooting within reach, and walk the hardening checklist.

Extend — building on it?

Write an integration manifest, build against the SDKs, or package a reusable operation for your organization.

Reference — looking something up?

The architecture, environment variables, and the glossary.

Integrations

Cat Factory connects to the tools you already use. Everything below ships in every deployment.

Category	Connects to
Repositories & pull requests	GitHub (via GitHub App) GitLab (all runtimes)
Issue trackers	Jira GitHub Issues Linear Seed tasks from issues and write progress back.
Document & context sources	Confluence Notion GitHub repo docs Figma & Zeplin (design context) Linear Docs
Model providers	Coding subscriptions: Claude, GLM, ChatGPT/Codex Direct API keys: Anthropic, OpenAI, Qwen, DeepSeek, Moonshot Aggregators: OpenRouter, LiteLLM Local runners: Ollama, LM Studio
Sign-in	Enterprise SSO (any OpenID Connect provider) GitHub Google Email and password
Notifications	In-app inbox Slack (optional) Email invitations

See Connect Issue & Document Sources and Connect a Model Provider for setup.

Advanced capabilities

Build & review

Multi-stage agent pipelines — ordered chains with per-agent models and human decision gates.
Requirements & spec — a reviewer agent flags gaps and risks per task; the Spec Writer keeps a unified, in-repo spec with Gherkin acceptance scenarios.
Visual confirmation (experimental) — a UI Tester screenshots each screen, then a gate parks for you to compare them against reference designs.
Custom agents & gates — extend the pipeline through a manifest model and the published @cat-factory/* packages.

Test & iterate

Sandbox — test prompts and models side by side against graded fixtures, scored by a judge, before you commit to a preset.
Ephemeral environments — spin up a live preview per run for integration and end-to-end tests, then tear it down automatically.
Recurring pipelines — schedule dependency bumps and tech-debt passes to ship as reviewed PRs on a cadence, with no one kicking them off.

Operate

Durable runs — every run is checkpointed, survives interruptions, and resumes where it left off.
Live observability — watch each step, decision, failure, and spend update stream over WebSockets.
Budgets & metering — an org-wide monthly LLM cap with per-run metering, prompt caching, auto-pause, and rollover resumption.
Runner pools — provision agent containers across your own runners.

Collaborate

Shared services — one account-owned service mounts onto many teams' boards as a single synced copy.
Members, roles & invitations — invite teammates into a shared organization with role-based access.
Localized, mobile-friendly UI — English, Spanish, French, Polish, and Ukrainian, with a responsive board shell (touch pan, pinch zoom, phone minimap).

Deploy anywhere

Runtime	Best for
Local mode	One machine, no cloud account: fastest way to try it end to end. Agents clone, commit, and push to real repos; CI gates on real GitHub Actions.
Cloudflare	Heavy production workloads on Workers (D1, Durable Objects, Workflows).
Node.js	Self-hosted production on Node with PostgreSQL and pg-boss.

Run agents on a coding subscription you already hold (Claude Pro/Max, GLM Coding Plan, or ChatGPT/Codex) instead of metered API spend. These plans are kept per-user, so each vendor's individual-use terms stay respected, and they unlock subscription-only models with no API-key equivalent. For shared, org-wide access, set a direct provider key, an aggregator like OpenRouter or LiteLLM, or run a local model with no key and no spend.

A note on scope

This site documents how to deploy and use Cat Factory. For source code, issues, and contribution guidelines, head to the kibertoad/cat-factory repository.