Awesome Ai Agents 2026
Section: AI Safety and Guardrails Β· Prompt injection detection.
Entry
Appears in 5 awesome lists
π’ β Archived prompt-injection detector (heuristics + LLM + vector DB + canary tokens). (Protect AI) β note: archived by the maintainer; retained as a historical prompt-injection defense reference. Β· updated 2024-01-25); Related: LLM Guard
Section: AI Safety and Guardrails Β· Prompt injection detection.
Section: Scanners, Evals & Guardrails Β· π’ β Archived prompt-injection detector (heuristics + LLM + vector DB + canary tokens). (Protect AI) β note: archived by the maintainer; retained as a historical prompt-injection defense reference. Β· updated 2024-01-25); Related: LLM Guard
Section: Tools Β· a self-hardening prompt injection detector
Section: LLM Security & AI Security Β· Prompt injection detector for LLM applications.
Section: AI & Machine Learning Security Β· Archived prompt-injection detector by Protect AI combining heuristics, LLM-based detection, vector similarity, and canary tokens, retained as a historical reference for multi-layer prompt injection defense.
π’ β LLM eval + red-teaming/pentesting CLI with 50+ attack plugins (MIT). Note: OpenAI announced an acquisition agreement in March 2026; remains MIT-licensed β track governance. Β· updated 2026-10-13); Related: Promptfoo CI Action (checkout evaluation, not base/head diff; defaults to latest,β¦
π’ β Python framework for adding input/output guards, validators, structured-output controls, and Guardrails Hub checks to LLM applications. (Guardrails AI) Β· updated 2026-08-26); Related: NeMo Guardrails Β· LLM Guard Β· Pydantic AI Shields integration (README recommends a successor)
NVIDIA's programmable guardrails toolkit: define input, dialog, retrieval, execution, and output rails that intercept the agent loop at five distinct layers using the Colang DSL. The execution rail layer specifically governs what tools the LLM can invoke and what their inputs/outputs may contain ββ¦
Open-source CLI security scanner for agentic workflows. Scans your workflowβs source code, detects vulnerabilities, and generates an interactive visualization along with a detailed security report. Supports LangGraph, CrewAI, n8n, OpenAI Agents, and more.
LLM monitoring toolkit from WhyLabs that extracts safety and security signals including jailbreak similarity, prompt-injection similarity, hallucination checks, PII patterns, toxicity, and refusal metrics for production observability.
Python framework for adversarial attacks, data augmentation, and model training in NLP. Augment datasets to increase model robustness and generate adversarial examples. MIT licensed.