Security guardrails for AI agent harnesses that keeps regulated data local and scans every prompt and tool call before execution. Protects sensitive information in automated workflows.
ai-tc provides security guardrails designed for AI agent harnesses, ensuring that regulated and sensitive data remains on your local machine while monitoring all interactions. It implements a scanning mechanism that inspects every prompt input and tool call before execution, preventing unauthorized data exposure and malicious operations.
As an open-source project hosted on GitHub, installation involves cloning the repository and following the provided setup instructions. Integration typically works as a middleware layer between your Claude-based agent and external tools, requiring configuration of data sensitivity rules and scanning policies for your specific use case.
Thesis Structure Helper assists students and researchers in organizing their academic theses by providing…
by FormAI
Dependency Auditor helps developers audit project dependencies for security vulnerabilities, licensing is…
by EnergyAI
FAQ Generator Pro auto-generates FAQ pages from support tickets, documentation, and product information.…
by EmailForge