Team1 Factory — AI skill for Claude Code
Open-source AI software factory: GitHub issues in, merged PRs out.
How to install Team1 Factory
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open Team1-dev/Team1-Factory and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Team1 Factory does
Open-source AI software factory: GitHub issues in, merged PRs out.
Alternatives in AI
- Multica — Make humans and AI agents work as one team — open-source and self-hostable 47.8k ★
- AIHawk — Open-source AI browser agent: describe any task in plain language and it autonomously browses, clicks, types a 30.3k ★
- Kilocode — GitHub Repo stars Open Source AI coding assistant for planning, building, and fixing code Open source AI assis 17k ★
README
Team1 Software Factory
**Turn GitHub issues into shipped software.**
Visit [tryteam1.com](https://tryteam1.com) for the latest updates.
Team1 is a local-first, agentic software factory for GitHub. Point it at your repositories and it runs:
**triage → plan → implement → test → review → pull request → merge**
Claude Code agents do the engineering work while Team1 manages branches, worktrees, gates, reviews, and pull requests. You can stay in the loop for decisions or enable auto-merge.
Team1 runs as a single process on infrastructure you control, using your Claude Code login and GitHub account.
See it work
[Team1-demo](https://github.com/Team1-dev/Team1-demo) is a demo app repository that Team1-Factory is building one issue at a time. Every [issue](https://github.com/Team1-dev/Team1-demo/issues?q=is%3Aissue) shows the stages as comments, from triage to merge with the total cost of each. Every [pull request](https://github.com/Team1-dev/Team1-demo/pulls?q=is%3Apr) was opened, reviewed and merged by Team1-Factory.
[!CAUTION]
⚠️ WARNING — run Team1 on an isolated machine
**Do not run Team1 on your personal computer.** Use a disposable VPS, VM, container, or other isolated environment.
Team1 runs Claude Code with permission checks disabled and executes commands from managed repositories. It also has access to GitHub and Claude Code credentials.
- Use a dedicated VPS, VM, or container.
- Use a dedicated GitHub account with access only to required repositories.
- Do not store personal credentials, SSH keys, cloud credentials, or other secrets on the host.
- Assume code in a managed repository can execute with Team1's permissions.
- Prefer testing with a private repository; public repositories are not tested.
Requirements
- A fresh Linux VPS. The steps below are for Ubuntu or Debian.
- Node.js 22.18+
git,jq,npmpnpmif required by a repository- Claude Code, installed and logged in
- Dedicated GitHub acc
Related Skills
AI Software Factory
Self-hosted, open-source AI Software Factory: a Governance Controller that orchestrates heterogeneous coding a
Agent Readiness
The open-source alternative to Factory.ai's Agent Readiness.
GitHub Demand Radar
AI Agent Skill to scan GitHub issues/PRs with JTBD + RICE scoring, find high-value market gaps, and generate f
Gh Issue ROI
Analyze repo issues without PRs, classify by difficulty + token/business impact. Args: owner/repo (e.g. rtk-ai
Paul Agent Bot
Self-hosted multi-channel AI coding agent powered by Claude Code. Handles GitHub issues, PRs, and Telegram — a
Agent Eval Harness
Live, open-source benchmark for comparing AI coding agents on real GitHub issues
Related Agents
Taskmaster
Maintain docs/todos.md as the canonical Gemma-Code progress tracker. Reads recent commits, open issues, merged
Opensource Contributor
Systematic open source contributor that analyzes projects, finds suitable issues, implements fixes, and create
Docs Reconciler
Drift detection agent for any software project. Use every 3–5 merged PRs, before a release, or when picking up