Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
LLM security testing framework for detecting prompt injection, jailbreaks, and adversarial attacks — 190+ probes, 28 providers, single Go binary
| Date | Stars |
|---|---|
| 2026-07-31 | 263 |
| 2026-08-11 | 273 |
| 2026-08-18 | 280 |
| 2026-08-23 | 281 |
| 2026-08-26 | 282 |
| 2026-08-27 | 283 |
| 2026-08-29 | 284 |
| 2026-09-09 | 285 |
| 2026-09-10 | 286 |
| 2026-09-12 | 287 |
| 2026-09-13 | 288 |
| 2026-09-16 | 289 |
| 2026-09-18 | 290 |
| 2026-09-20 | 290 |
| 2026-09-21 | 289 |
| 2026-09-22 | 290 |
| 2026-09-23 | 291 |
| 2026-09-24 | 293 |
| 2026-09-25 | 294 |
| 2026-09-29 | 295 |
| 2026-09-30 | 295 |
| 2026-10-03 | 298 |
| 2026-10-04 | 299 |
| 2026-10-06 | 300 |
| 2026-10-08 | 301 |
| 2026-10-10 | 302 |
| 2026-10-13 | 304 |
| 2026-10-15 | 307 |
| 2026-10-16 | 307 |
| 2026-10-17 | 307 |
| 2026-10-20 | 309 |
| 2026-10-22 | 310 |
| 2026-10-24 | 311 |
| 2026-10-28 | 312 |
| 2026-10-29 | 314 |
| 2026-10-30 | 314 |
| 2026-10-31 | 315 |
| 2026-11-02 | 315 |
| 2026-11-03 | 316 |
| 2026-11-04 | 317 |
Today
+1 stars today
This week
+5 stars this week
This month
+18 stars this month
Momentum
44.0
growth rate 1.60%/day
<img width="1200" height="628" alt="Augustus - LLM vulnerability scanner for prompt injection, jailbreak, and adversarial attack testing" src="https://github.com/user-attachments/assets/6a1205fd-3246-4d32-9520-549f048d1fa5" /> # Augustus - LLM Vulnerability Scanner > Test large language models against 210+ adversarial attacks covering prompt injection, jailbreaks, encoding exploits, and data extraction. [](https://github.com/praetorian-inc/augustus/actions/workflows/ci.yaml) [](go.mod) [](LICENSE) [](https://goreportcard.com/report/github.com/praetorian-inc/augustus) [](https://github.com/praetorian-inc/augustus/releases) **Augustus** is a Go-based LLM vulnerability scanner for security professionals. It tests large language models against a wide range of adversarial attacks, integrates with 28 LLM providers, and produces actionable vulnerability reports. Unlike research-oriented tools, Augustus is built for production security testing — concurrent scanning, rate limiting, retry logic, and timeout handling come out of the box. ## Table of Contents - [Why Augustus](#why-augustus) - [Features](#features) - [Quick Start](#quick-start) - [Supported Providers](#supported-providers) - [Usage](#usage) - [Single Probe](#single-probe) - [Multiple Probes](#multiple-probes) - [Buff Transformations](#buff-transformations) - [Output Formats](#output-formats) - [Custom REST Endpoints](#custom-rest-endpoints) - [How It Works](#how-it-works) - [Architecture](#architecture) - [Configuration](#configuration) - [FAQ](#faq) - [Troubleshooting](#troubleshooting) - [Contributing](#contributing) - [Security](#security) - [Support](#support) - [License](#license) ## Why Augustus | Feature | Augustus | garak | promptfoo | |---------|----------|-------|-----------| | Language | Go | Python | TypeScript | | Single binary | Yes | No | No | | Concurrent scanning | Goroutine pools | Multiprocessing pools | Yes | | LLM providers | 28 | 35+ | 80+ | | Probe types | 210+ | 160+ | 119 plugins + 36 strategies | | Enterprise focus | Yes | Research | Yes | ## Features | Feature | Description | |---------|-------------| | **210+ Vulnerability Probes** | 47 attack categories: jailbreaks, prompt injection, adversarial examples, data extraction, safety benchmarks, agent attacks, and more | | **28 LLM Providers** | OpenAI, Anthropic, Azure, Bedrock, Vertex AI, Ollama, and 22 more with 43 generator variants | | **90+ Detectors** | Pattern matching, LLM-as-a-judge, HarmJudge (arXiv:2511.15304), Perspective API, unsafe content detection | | **7 Buff Transformations** | Encoding, paraphrase, poetry (5 formats, 3 strategies), low-resource language translation, case transforms | | **Flexible Output** | Table, JSON, JSONL, and HTML report formats | | **Production Ready** | Concurrent scanning, rate limiting, retry logic, timeout handling | | **Single Binary** | Go-based tool compiles to one portable executable | | **Extensible** | Plugin-style registration via Go `init()` functions | ### Attack Categories - **Jailbreak attacks**: DAN, DAN 11.0, AIM, AntiGPT, Grandma, ArtPrompts - **Prompt injection**: Encoding (Base64, ROT13, Morse), Tag smuggling, FlipAttack, Prefix/Suffix injection - **Adversarial examples**: GCG, PAIR, AutoDAN, TAP (Tree of Attack Prompts), TreeSearch, DRA - **Multi-turn attacks**: Crescendo (gradual escalation), GOAT (adaptive technique switching) - **Data extraction**: API key leakage, Package hallucination, PII extraction, LeakReplay - **Context manipulation**: RAG poisoning, Context overflow, Mul
Excerpt of 34,753 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:83631566fd96862d, topic:ai-security, desc:llm security, desc:prompt injection