# Guard0

> Accountability for AI Agents. Guard0 discovers every agent, maps what each can reach, proves what they did, and shows who is answerable, built on the AI Asset Graph and the Accountability Score (Known, Scoped, Tested, Controlled).

Guard0 is the accountability layer for AI agents. It answers the questions security teams and boards cannot answer today: what agents do we have, what can they access, and are they doing what we think? Discovery spans code, cloud, agent platforms (LangChain, CrewAI, Agentforce, Copilot Studio, Bedrock, and more), developer endpoints, and MCP servers. The open-source CLI, g0, lets anyone scan their own environment for free.

## Core pages
- [Product](https://guard0.ai/product): The AI agent accountability platform: Discover, Map, Prove, and stay accountable, built on the AI Asset Graph.
- [g0 (open-source CLI)](https://guard0.ai/g0): Background check for AI agents. Scan any repository for agent risks for free: npx @guard0/g0 scan
- [Sign up](https://guard0.ai/signup): Start your agent inventory: discover and map every agent and get your Accountability Score.
- [The Invisible Workforce](https://guard0.ai/solutions/the-invisible-workforce): Discover every AI agent across your org, including the shadow agents nobody approved.
- [The Blast Radius](https://guard0.ai/solutions/the-blast-radius): Map what every agent can read, write, and reach, and what happens when one fails.
- [Humans in the Lead](https://guard0.ai/solutions/humans-in-lead): Keep humans in control of autonomous agents with policy enforcement and a kill switch.
- [Research](https://guard0.ai/research): Guard0 security research on AI agents, MCP, and the agentic attack surface.
- [The Three Questions Framework](https://guard0.ai/research/three-questions-framework): A framework for reasoning about AI agent accountability.
- [Labs](https://guard0.ai/labs): Open-source tools from Guard0: TrustVector, AIHEM, and g0.
- [Events](https://guard0.ai/events): Workshops, webinars, and training on AI agent security.
- [About](https://guard0.ai/about): Why Guard0 exists: accountability for AI agents.
- [Security](https://guard0.ai/security): Guard0 security posture and practices.

## Blog
- [Announcing Guard0: Accountability for AI Agents](https://guard0.ai/blog/guard0-early-access): A year ago, most agents advised. Now they act, and the systems built for people cannot tell you what they did or who answers for them. Guard0 closes that gap. Today, we are opening it in early access.

## Open source
- [g0](https://github.com/guard0-ai/g0): Open-source AI agent security scanner (`npx @guard0/g0 scan`).
- [TrustVector](https://github.com/guard0-ai/TrustVector): Trust evaluations for AI tools and agents.
- [AIHEM](https://github.com/guard0-ai/AIHEM): An intentionally vulnerable AI agent environment for training and red teaming.

## Contact
- Website: https://guard0.ai
- Sign up: https://guard0.ai/signup