Awesome Ai Agents 2026
Section: AI Safety and Guardrails · Prompt injection detection.
ActiveScore 74
Entry
Rebuff
Appears in 4 awesome lists
🟢 — Archived prompt-injection detector (heuristics + LLM + vector DB + canary tokens). (Protect AI) — note: archived by the maintainer; retained as a historical prompt-injection defense reference. · updated 2024-01-25); Related: LLM Guard
Open github.comprotectai/rebuff
Found in these lists
Awesome AI Security Tools
Section: Scanners, Evals & Guardrails · 🟢 — Archived prompt-injection detector (heuristics + LLM + vector DB + canary tokens). (Protect AI) — note: archived by the maintainer; retained as a historical prompt-injection defense reference. · updated 2024-01-25); Related: LLM Guard
FreshScore 85
Awesome LLM Security
Section: Tools · a self-hardening prompt injection detector
SlowScore 53
SOCIAL MEDIA
Section: LLM Security & AI Security · Prompt injection detector for LLM applications.
FreshScore 86
Often listed next to it
promptfoo
Test your prompts, models, RAGs. Evaluate and compare LLM outputs, catch regressions, and improve prompt quality. LLM evals for OpenAI/Azure GPT, Anthropic Claude, VertexAI Gemini, Ollama, Local & private models like Mistral/Mixtral/Llama with CI/CD
In 11 listsDetails
Agentic Radar
Open-source CLI security scanner for agentic workflows. Scans your workflow’s source code, detects vulnerabilities, and generates an interactive visualization along with a detailed security report. Supports LangGraph, CrewAI, n8n, OpenAI Agents, and more.
In 6 listsDetails
Guardrails AI
Input/output validation framework for building reliable AI applications. Detects and mitigates risks through composable validators for PII, toxicity, prompt injection, and structured output validation. Features Guardrails Hub with 50+ pre-built validators. Apache 2.0 licensed.
In 6 listsDetails
NeMo Guardrails
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 —…
In 6 listsDetails
TextAttack
Python framework for adversarial attacks, data augmentation, and model training in NLP. Augment datasets to increase model robustness and generate adversarial examples. MIT licensed.
In 6 listsDetails
garak
The LLM vulnerability scanner. Probes models for hallucinations, data leakage, prompt injection, misinformation, toxicity, and jailbreaks. Extensive plugin-based architecture with 100+ vulnerability probes. Apache 2.0 licensed.
In 4 listsDetails
LangKit
🟢 — LLM monitoring toolkit extracting safety/security signals such as jailbreak similarity, prompt-injection similarity, hallucination checks, PII patterns, toxicity, and refusal metrics. (WhyLabs) · updated 2024-11-22)
In 4 listsDetails
NeMo Guardrails
NeMo Guardrails is an open-source toolkit facilitating the integration of programmable guardrails, essential for steering and safeguarding AI agents' conversational outputs, into large language model-based applications github | research paper
In 4 listsDetails