Source: NVIDIA NeMo Guardrails documentation

NVIDIA's docs and README for the open-source NeMo Guardrails library: five rail types, config.yml and Colang, self-check rails, streaming and parallel options.

Contents
  • What: official library documentation and GitHub README (overview, “How it works”, guardrail catalog, configuration reference, Colang 1.0 input-rails tutorial)
  • Publisher: NVIDIA
  • Date: “latest” docs read 2026-11-14; latest released version 0.24.1 per the README (no release date given)
  • Original: NeMo Guardrails docs · configuration reference · input rails tutorial · GitHub

Summary

NeMo Guardrails is a Python library (and a Kubernetes microservice using the same config format) that sits between an application and its LLM and runs “rails” at five points of a request. Rails are configured in YAML (config.yml, prompts.yml) and Colang flows, plus Python custom actions. It ships self-check rails (the LLM judges its own input/output with a yes/no prompt) and integrations with dedicated safety models and third-party services.

Key claims

  • Five rail types, in request order: input (allow, alter or reject the user message), retrieval (filter or transform RAG chunks), dialog (Colang flows over canonical-form messages that pick the next step), execution (validate tool/action inputs and outputs), output (allow, edit or block the response).
  • The runtime is event-driven: a user message becomes an event; depending on config it may generate a canonical user intent, decide the next step, run an action, retrieve chunks, call the LLM and generate the bot message. Dialog prompt tasks are generate_user_intent, generate_next_steps, generate_bot_message.
  • Colang 1.0 and 2.0 are both supported; 1.0 is the default.
  • Config keys: models (types main, embeddings, jailbreak_detection are reserved; content_safety is a convention referenced as $model=content_safety), instructions, rails.input.flows, rails.output.flows, prompts, knowledge_base, tracing.
  • Self-check input: a separate LLM call with the self_check_input prompt; answer “Yes” blocks. In the tutorial’s explain() output a blocked request costs 1 LLM call, an allowed one 2 (check + general answer). Missing prompt raises an error at load; reasoning models need an explicit max_tokens (default fallback 1024).
  • Output-rail streaming (rails.output.streaming): enabled (default false), chunk_size 200 tokens, context_size 50 tokens carried between chunks, stream_first true (stream before the rails run on the chunk).
  • rails.input.parallel / rails.output.parallel (default false) run rails concurrently; rails.dialog.single_call.enabled merges intent and response into one LLM call, with fallback to multiple calls.
  • Catalog categories: content safety (e.g. Llama 3.1 NemoGuard 8B Content Safety, Llama Guard), jailbreak protection (heuristics, self-check, NemoGuard Jailbreak Detect NIM), topic control, PII (Presidio, GLiNER-PII and others), agentic security, tool-call rails, hallucination and fact-checking, LLM self-check, third-party APIs (ActiveFence, Cisco AI Defense, Guardrails AI, and more).
  • Server mode exposes an OpenAI-style /v1/chat/completions; LangChain and LangGraph integrations exist.

Feeds

Guardrail tooling

Suggest changes →