Security and governance layer for AI agent tool access
Project description
░█▀▀░█▀█░█▀▀░▀█▀░█▀█░█▀▄░█░░█░█
░█▀▀░█▀█░█░░░░█░░█░█░█▀▄░█░░░█░
░▀░░░▀░▀░▀▀▀░░▀░░▀▀▀░▀░▀░▀▀▀░▀░
Factorly
Stop giving your AI agents your API keys. One command. All your tools. Credentials stay out of your agent's hands.
Factorly is a local runtime for agent tool chains. It proxies agent tool calls, injects credentials from an encrypted vault, enforces governance rules, and logs everything.
REST APIs, CLI commands, and MCP servers run through one config, one audit log, one set of rules.
Your agent sees workflows, tool names, and data. Never secrets.
Install
pip install factorly
Quick Start
Then, define your tools, secure your credentials, and sync with your agent:
# 1. Configure your tools or install a template (36 services: GitHub, Slack, Stripe, Linear, Gmail, ...)
factorly init
# 2. Store your credentials in the encrypted vault
factorly vault set GITHUB_TOKEN ghp_xxxxxxxxxxxx
# 3. Connect to your agent (auto-detects Claude Code, Cursor, Codex)
factorly sync
The agent never sees your credentials. Factorly injected it, made the API call, logged it, and returned the data.
Already Using an MCP Server?
Wrap it with Factorly — no config file needed, no changes to the server:
factorly wrap -- npx @modelcontextprotocol/server-github
Same tools, same interface. Now every call is logged, output is compressed, loops are detected, and calls are rate-limited.
What You Get
- Encrypted vault — AES-256-GCM with per-entry encryption, secrets never leave your device
- Governance — deny destructive operations, require confirmation for writes, rate-limit calls, detect agent loops
- 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 wrapandfactorly execadd safety instantly - Output compression — compresses JSON, deduplicates logs, truncates to head + tail to save tokens
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
License
GPL-3.0
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file factorly-0.9.0.tar.gz.
File metadata
- Download URL: factorly-0.9.0.tar.gz
- Upload date:
- Size: 4.3 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.13
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
f2a4ac4ca2261a37ac66ffc709b940bcff80dcb61dda177d27ef21fcc2ad6c44
|
|
| MD5 |
4c93a09385496c9b8ecd7f916c3549fe
|
|
| BLAKE2b-256 |
178ce6c2a9a5a7bb3f59a0b88213e46e076e6a856ec8fbd60d68de807c4d0e5b
|
File details
Details for the file factorly-0.9.0-py3-none-any.whl.
File metadata
- Download URL: factorly-0.9.0-py3-none-any.whl
- Upload date:
- Size: 5.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.13
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
4086d19f5941537cfd752358ec5ed4b03f96301c9081bf1fb74c30132107d043
|
|
| MD5 |
a19c55726b3052233044bf6506fe0d3c
|
|
| BLAKE2b-256 |
ebea9f12510cfdb653e8fe926c0859a88dc591bf96f366d20320f6777dfb7c22
|