factorly 0.1.10

Security and governance layer for AI agent tool access

░█▀▀░█▀█░█▀▀░▀█▀░█▀█░█▀▄░█░░█░█
░█▀▀░█▀█░█░░░░█░░█░█░█▀▄░█░░░█░
░▀░░░▀░▀░▀▀▀░░▀░░▀▀▀░▀░▀░▀▀▀░▀░

Factorly

Your agent calls tools. Factorly holds the keys.

A security and governance layer between AI agents and the tools they use. REST APIs, CLI commands, MCP servers — one config, one audit log, one set of rules.

Install

pip install factorly

Or with pipx:

pipx install factorly

Try It in 10 Seconds

# Run any command with compression + logging
factorly exec -- git status

# Wrap any MCP server with zero config
factorly wrap -- npx @modelcontextprotocol/server-everything

# Install a template for a service you use
factorly tools import templates github

Quick Start

factorly init                              # set up a project
factorly vault set GITHUB_TOKEN ghp_xxx    # store a secret
factorly sync                              # connect to Claude Code / Cursor

What You Get

• Credential isolation — secrets in encrypted vault, agent never sees them
• Governance — deny, confirm, rate limit, loop detection per tool
• Audit log — every call logged with params, response, and governance outcome
• 36 templates — pre-built configs for GitHub, Slack, Stripe, Gmail, Linear, and more
• Zero-config proxy — factorly wrap and factorly exec add safety instantly

Supported Platforms

OS	Architecture
Linux	x64
macOS	x64, arm64
Windows	x64

The pip package downloads the pre-built Go binary for your platform on first run.

Documentation

Full docs at github.com/factorly-dev/factorly-cli

License

MIT