Agent SDK and Runtime
Public
promptfoo
Agent SDK project for checking tool calls, state, handoffs, traces, evaluation, and permission boundaries.
Agent SDKTool callsHandoffs
Category preview
Security Review & Permission Governance
Open-source AI capabilities for reviewing permissions, secrets, risk boundaries, and install-time safety.
Security Review & Permission Governance
Public
bandit
Bandit is a tool designed to find common security issues in Python code.
Security Review & Permission Governance
Public
pydantic-ai-backend
File Storage & Sandbox Backends for Pydantic AI: console tools for file operations, Docker-isolated sandboxes for safe execution, and permission system with presets for access control. Enables secure multi-user handling and testing in agents via in-memory, local, or containerized storage.
MCP Tool Integration
Public
Causal-Memory-Layer
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
MCPTool callingHost configuration
MCP Tool Integration
Public
ms-365-admin-mcp-server
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
MCPTool callingHost configuration
MCP Tool Integration
Public
decoy-scan
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
MCPTool callingHost configuration
Security Review & Permission Governance
Public
csec-node-agent
New Relic Security Agent for Node.js
MCP Tool Integration
Public
node804-mcp-toolkit
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
MCPTool callingHost configuration