Open-source MCP gateway and control plane for teams to govern which tools agents can use, what they can do, and how it’s audited—across agentic IDEs like Cursor, or other agents and AI tools.
A TypeScript library providing a set of guards for LLM (Large Language Model) applications
Middleware for the Vercel AI SDK that adds safety, quality control, and cost management to your AI applications by intercepting prompts and responses.
Deterministic LLM testing for CI. Record→Replay + policy-as-code to block risky merges (PII, schema drift, regressions, budget creep).
AI-powered ethical decision-making using multi-agent tools
[PoC] Actions to protect repos from Supply Chain Attacks
The Modelmetry JS/TS SDK allows developers to easily integrate Modelmetry’s advanced guardrails and monitoring capabilities into their LLM-powered applications.
Validate, improve, and standardize AI prompt outputs.
The official Nodejs library for the OpenGuardrails API
Add a description, image, and links to the guardrails topic page so that developers can more easily learn about it.
To associate your repository with the guardrails topic, visit your repo's landing page and select "manage topics."