🛡️ Open-source safety guardrail for AI agent tool calls. <2ms, zero dependencies.
-
Updated
Feb 15, 2026 - TypeScript
#
tool-validation
Here are 2 public repositories matching this topic...
Open-source security firewall for AI agents — validates tool calls, strips ghost arguments, enforces type safety, PII masking, RBAC, cost tracking & sandbox isolation. Works with LangChain, OpenAI Agents SDK, PydanticAI & CrewAI.
python sandbox firewall openai rbac ai-agents zero-trust ai-security langchain llm-safety crewai mcp-server pydantic-ai pii-masking tool-validation
-
Updated
Feb 6, 2026 - Python
Improve this page
Add a description, image, and links to the tool-validation topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the tool-validation topic, visit your repo's landing page and select "manage topics."