guardrailsai.com
Guardrails AI provides tooling for validating and structuring LLM inputs and outputs using reusable validators and guard definitions. Its product includes a validator hub, a local/server runtime, and client libraries for embedding these checks into applications.
Guardrails AI exposes a Python-installed CLI plus self-hosted HTTP surfaces: a Guardrails Server REST API and an OpenAI-compatible endpoint, with Hub-issued API keys used by the CLI and documented as a client/server credential.
- Guardrails Server REST APIdiscovered
- Guardrails OpenAI-compatible endpointdiscovered
- Guardrails CLIdiscovered
Sign in at Guardrails Hub or Guardrails Hub on guardrailsai.com and generate a free API key. Then configure the CLI with guardrails configure or provide it directly with guardrails configure --token <your_token>. The docs also mention client-side use via the GUARDRAILS_API_KEY environment variable or an api_key argument when pointing a Guard client at a Guardrails server.
conventions · 0/7 published
- integrations.json——
- llms.txt✗
/llms.txt - API catalog✗
/.well-known/api-catalog - OpenAPI document✗
/api/schema/, /openapi.json, /swagger.json, /api/openapi.json, or /v1/openapi.json - MCP server card✗
/.well-known/mcp/server-card.json - OAuth protected resource✗
/.well-known/oauth-protected-resource - Agent card✗
/.well-known/agent-card.json - Agent skills✗
/.well-known/agent-skills/index.json
Publish these signals → /publishing