Skip to content

Add AgentShield — open-source AI agent firewall and audit log #14

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
brigen wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Add AgentShield — open-source AI agent firewall and audit log #14

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,7 @@ This list is organized by the **security lifecycle** of an autonomous agent, cov

- **[AgentGateway](https://github.com/agentgateway/agentgateway)** - A Linux Foundation project providing an AI-native proxy for secure connectivity (A2A & MCP protocols). It adds RBAC, observability, and policy enforcement to agent-tool interactions.
- **[Envoy AI Gateway](https://gateway.envoyproxy.io/)** - An Envoy-based gateway that manages request traffic to GenAI services, providing a control point for rate limiting and policy enforcement.
- **[AgentShield](https://github.com/brigen/agent-shield)** - An open-source firewall and audit log for AI agents. Sits between agents and their tools as a policy-enforcing proxy with three interception layers: MCP tool calls, CLI commands, and HTTP requests. Features a rules-based allow/deny/warn policy engine with rate limiting, structured JSON audit logging with automatic secret redaction, and a real-time web dashboard.

## ⚔️ Red Teaming & Vulnerability Scanners
*Offensive tools to test agents for security flaws, loop conditions, and unauthorized actions.*
Expand Down