factory — security grade SAFE, quality 67/100

Security audit verdict: SAFE · quality 67/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by owainlewis · Codex Skill · ★ 205

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is factory safe to install? View the security audit →

About factory

Factory Factory is infrastructure for running coding agents across Git repositories. Its Go control plane stores work, shows the worker fleet, and delegates tasks. Each Go worker owns one agent runtime, currently Codex or Claude Code. The browser UI provides: an overview of execution throughput, reliability, cycle time, queue depth, and worker health; a work queue and task details; registered worker and repository status; task delegation using a title, prompt, repository, and worker. Factory is local-first today. The server only accepts loopback connections and does not include user authentication. Quick start Requirements: Go 1.25 or newer Git Codex CLI or Claude Code CLI, authenticated on the worker host Node.js is only needed when changing the UI. Normal builds use the committed, embedded UI assets. GitHub Automations and on-demand worker checkout depend on the GitHub CLI, . Factory does not include a separate GitHub API client. Install and authenticate on the control-plane host and each eligible worker host before enabling a GitHub Automation: Edit to select or . Workers need no repository list.

claude-codecodexgolangsoftware-factorytypescript

Quick Facts

Stars205
Forks40
LanguageGo
CategoryCodex Skill
LicenseMIT
Quality Score66.5915931508437/100
Open Issues60
Last Updated2026-08-24
Created2026-07-16
Platformsclaude-code, codex, go
Est. Tokens~16k

factory alternative? Top 6 similar tools

Looking for a factory alternative? If you're comparing factory with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • SWE-AF by Agent-Field · ⭐ 993

    Autonomous software engineering fleet of AI agents for production-grade PRs on AgentField: plan, code, test, a

  • agent-deck by asheshgoplani · ⭐ 925

    Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more.

  • memorix by AVIDS2 · ⭐ 784

    Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Wi

  • Overture by SixHq · ⭐ 630

    Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server

  • catnip by wandb · ⭐ 490

    Like catnip, a highly addictive agentic coding tool

  • Ivy-Tendril by Ivy-Interactive · ⭐ 193

    AI agents can now write 99% of the code. This changes what it means to be a developer. Our role shifts to know

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Go Agent Tools

Frequently Asked Questions

What is factory?

factory is Build your own software factory with AI agents. It is categorized as a Codex Skill with 205 GitHub stars.

What programming language is factory written in?

factory is primarily written in Go. It covers topics such as claude-code, codex, golang.

How do I install or use factory?

You can find installation instructions and usage details in the factory GitHub repository at github.com/owainlewis/factory. The project has 205 stars and 40 forks, indicating an active community.

What license does factory use?

factory is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to factory?

The top alternatives to factory on Agent Skills Hub include SWE-AF, agent-deck, memorix. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Codex Skill tools