Guardrails releases

Config change

v0.22.0 Breaking risk · 12d

Auth

Usage reporting, LangChain optional, IORails enhancements

Open

v0.21.0 Breaking risk · 2mo

Breaking changes

• Removed stream_usage from streaming metadata capture

Notable features

• IORails Input/Output rail engine with parallel execution
• check_async method for standalone rail validation
• OpenAI-compatible server with v1/models endpoint

View release on GitHub

v0.20.0 Breaking risk · 4mo

Breaking changes

• Removed streaming field from configuration

Notable features

• Nemotron reasoning-capable content safety models
• GLiNER for open-source PII detection
• Multilingual refusal messages in content safety rails

View release on GitHub

v0.19.0 Breaking risk · 6mo

Notable features

• LangChain 1.x compatibility
• Content blocks API support for reasoning traces and tool calls

View release on GitHub

v0.18.0 Breaking risk · 6mo

Breaking changes

• Reasoning traces extracted to separate field instead of prepended to message
• stream_async now raises error if output rail streaming disabled
• Replaced reasoning trace extraction with LangChain additional_kwargs

Notable features

• BotThinking events for processing reasoning traces
• Embedding providers: Azure OpenAI, Cohere, Google
• In-memory LFU caches for content-safety, topic-control, jailbreak models

View release on GitHub

v0.17.0 New feature · 7mo

Notable features

• LangGraph integration for multi-agent workflows
• Tool calling with passthrough and validation
• RunnableRails rewrite with full Runnable protocol support

View release on GitHub

v0.16.0 New feature · 9mo

Notable features

• OpenTelemetry semantic conventions for tracing
• GuardrailsAI and Pangea AI Guard integrations
• KV cache reuse for LLM-based NemoGuard models

View release on GitHub

v0.15.0 Breaking risk · 9mo

Breaking changes

• Tracing updated to use OpenTelemetry API

Notable features

• Parallel rails execution in Colang 1.0
• Parallel streaming output rails execution
• Fixed streaming word concatenation and token usage tracking

View release on GitHub

v0.14.1 Bug fix · 11mo

Notable features

• Direct API key configuration for jailbreak detection

View release on GitHub

v0.14.0 Breaking risk · 11mo

Breaking changes

• Reasoning trace preservation and handling restructured
• Deprecated return_context argument removed
• Renamed remove_thinking_traces to remove_reasoning_traces

Security fixes

• YARA-based code injection detection guardrail

Notable features

• Reasoning model support for Nemotron and DeepSeek-r1
• YARA-based code injection detection guardrail
• Clavata community integration for content moderation

View release on GitHub