DEDUPEDWhat do you want to do?
3 use cases
-
Check your AI agent program against 35 controls
Use the six outcomes and 35 controls to find gaps in how your company runs agents.
- REPO
agentbaseline/agentbaseline - Security and science
- Intermediate
View prompt
Using agentbaseline/agentbaseline whitepaper/controls.yaml, build a gap table for <organization> with each control id, title and status. Cite control ids exactly.
- REPO
-
Load the controls into your GRC tooling
Parse the YAML source of truth to import outcomes and controls into your own systems.
- REPO
agentbaseline/agentbaseline - Security and science
- Intermediate
View prompt
Parse whitepaper/controls.yaml from agentbaseline and output CSV rows of id, outcome, title, type and status. Confirm 35 controls were parsed.
- REPO
-
Regenerate the white paper figures from the YAML
Run the figure scripts so diagrams stay in sync with control changes.
View prompt
Run the agentbaseline figure scripts and confirm Figure 1 regenerates without errors.
Quick start with Agentbaseline
- Check you have what it needs: Python 3 to build the figures.
- Open agentbaseline/agentbaseline on GitHub and read the README and license.
- Read the six outcomes starting with Discover
- Open whitepaper/controls.yaml
- Mark each control as met, partial or missing
- Prioritize missing controls
These steps come from our top use case, Check your AI agent program against 35 controls, which also has a copy-paste agent prompt.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for agentbaseline/agentbaseline
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeAgentbaseline alternatives · Best AI repos for Security and science
About this repo
- Who it is forSecurity leaders and architects writing policy for enterprise AI agents.
- Why it is hot100 stars, launched 89 days ago
- LanguagePython
- Sourcegithub.com/agentbaseline/agentbaseline · Back to Hot repos
Requirements
- Python 3 to build the figures
Add this badge to your README
Maintain Agentbaseline? Show readers where to find these use cases. 
Markdown
[](https://dedupedai.com/use-cases/agentbaseline-agentbaseline/?utm_source=github&utm_medium=badge&utm_campaign=agentbaseline-agentbaseline)
HTML
<a href="https://dedupedai.com/use-cases/agentbaseline-agentbaseline/?utm_source=github&utm_medium=badge&utm_campaign=agentbaseline-agentbaseline"><img src="https://dedupedai.com/badge/agentbaseline/agentbaseline.svg" alt="Use cases on Deduped" height="20"></a>
A static image, no tracking script. About the badge
Questions about Agentbaseline
What is Agentbaseline?
Agent Baseline is a draft framework of six security outcomes and 35 controls an enterprise must evidence to run AI agents safely, kept as machine-readable YAML. It is an open-source project on GitHub: https://github.com/agentbaseline/agentbaseline.
Who is Agentbaseline for?
Security leaders and architects writing policy for enterprise AI agents.
What can I do with Agentbaseline?
3 use cases so far, for example: Check your AI agent program against 35 controls; Load the controls into your GRC tooling; Regenerate the white paper figures from the YAML. Each has steps and a copy-paste agent prompt.
What do I need to run Agentbaseline?
Python 3 to build the figures.
What are alternatives to Agentbaseline?
Other hot AI repos in Security and science: Security Audit Skill, RiftX, Hacker, Codex Privacy Hud, Robo TTT.
Is Agentbaseline safe to run?
Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.