Adrian vs Guardrails
Runtime security for AI agents: watches actions AND reasoning traces to catch prompt injection, tool poisoning and out-of-remit behavior — blocking before the action lands. SDKs + Claude Code plugin. — versus — NVIDIA's programmable guardrails for LLM apps: input, output, dialog and retrieval rails defined in Colang, wrapping any model or LangChain runnable.
Both police live LLM behavior, opposite philosophies: NeMo Guardrails executes rails you wrote in Colang — you enumerate the policy; Adrian infers the agent's remit and flags deviations, reasoning traces included.
| Adrian | Guardrails | |
|---|---|---|
| Stars | 460 | 6.8k |
| Forks | 85 | 792 |
| Language | Python | Python |
| License | Apache-2.0 | NOASSERTION |
| Last activity | 4 days ago | yesterday |
| Topics | security, agents | security |
| Curated connections | 2 | 5 |
Adrian — the curator's take
The interesting bet is judging reasoning traces, not just tool calls, against a working model of the agent's remit — the OpenAI/DeepMind-cited combo that catches what injection-trained classifiers miss. Know the deployment shape: the quickstart routes your agent's actions AND thoughts through their managed dashboard; self-hosting exists but is the longer path. Young (★460) and a startup's wedge product — run audit mode first and measure false positives on your own traffic before trusting block mode in production.
Guardrails — the curator's take
For when policy needs to be programmable, not a blocklist: topic bans, jailbreak checks, tool-use constraints and dialog flows written in Colang, enforced as input/output/dialog/retrieval rails around any LLM — RunnableRails drops it straight into a LangChain pipeline. NOT free at runtime: every rail is extra LLM calls and latency, Colang is its own language to learn, and rails mitigate rather than guarantee — you still red-team the result (that's garak's job).