- 月访问
- <5K
- 2026 年 9 月
- 公开收入
- 未公开
- 暂无公开收入证据
- 入门价
- 按量付费
- 没有月付订阅价
- 首次发布
- 9 个月前
- 2026-02-10 · 估算
访问
近 12 个月
营销动作
发布、搜索与内容、引荐、促销X 账号@fabraixhq
在 Show HN 发布（13 分 · 4 评论）发布
Open-source playground to red-team AI agents against public prompts
8 月 9 日 · 3 个月前发布页
当时 月访问 7.6K访问：之后 2 个月 -65%同期还有 2 个动作在 Show HN 发布（4 分）发布
We are giving away $100K > over the next 12 months to hack AI agents — We build AI agents to find vulnerabilities in other AI agents. The playground started as an internal tool that we used to test our own off…
7 月 13 日 · 4 个月前发布页
在 Show HN 发布（20 分 · 8 评论）发布
Nyx – multi-turn, adaptive, offensive testing harness for AI agents — We built Nyx to solve a problem we kept hitting while building agents: AI agents break in ways traditional software doesn't. Logic bugs, r…
4 月 19 日 · 7 个月前发布页
第三方评测与案例拆解
获客渠道拆解、工程师评测与开源档案Show HN
2026-02-10查看原文
- 创作者原帖摘录：
- Each week we deploy a live AI agent with real tools (web search, browsing, more), a persona, and something it's been told to protect. The system prompt is fully visible. Your job is to break through the guardrails anyway. Fastest successful jailbreak wins and the winning technique gets published for everyone to learn from. First challenge is live now. Give i
Show HN
2026-03-15查看原文
- 创作者原帖摘录：
- We build runtime security for AI agents. The playground started as an internal tool that we used to test our own guardrails. But we kept finding the same types of vulnerabilities because we think about attacks a certain way. At some point you need people who don't think like you. So we open-sourced it. Each challenge is a live agent with real tools and a pub
Show HN
2026-04-05查看原文
- 创作者原帖摘录：
- We built Adversarial Cost to Exploit (ACE), a benchmark that measures the token expenditure an autonomous adversary must invest to breach an LLM agent. Instead of binary pass/fail, ACE quantifies adversarial effort in dollars, enabling game-theoretic analysis of when an attack is economically rational. We tested six budget-tier models (Gemini Flash-Lite, Dee
Show HN
2026-04-19查看原文
- 创作者原帖摘录：
- We built Nyx to solve a problem we kept hitting while building agents: AI agents break in ways traditional software doesn't. Logic bugs, reasoning failures, edge cases that manual testing and static benchmarks never explore. Nyx is an autonomous testing harness that probes your AI agents to find failure modes before users do. It’s used to find logic bugs, in
Show HN
2026-07-13查看原文
- 创作者原帖摘录：
- We build AI agents to find vulnerabilities in other AI agents. The playground started as an internal tool that we used to test our own offensive agent Nyx. But we realised that hacking an AI is about have as wide a distribution of attacks as possible, especially those which aren't in the distribution of the models. So we are launching playground as a platfor
开源仓库与自部署
GitHub 开源与智能体接入
流量来源
2026 年 9 月
访问构成
渠道
- 直接访问39%
- 自然搜索32%
- 外部引荐11%
- 社交媒体6%
- 其他12%
国家/地区
- 美国91%
- 加拿大9%
搜索
站点权重 —域名注册 2025-04-13
| 关键词 | 月搜索量 |
|---|---|
| fabraix | 500 |
| fabrantic ai | 60 |
| ai ferracio | 0 |
流量数据：Vaneform
定价
Researchers
$0
1 target · Core interaction library · Standard findings report · Publish-friendly results · Community support
One-Off Scan
未知
One agent, full coverage · 10,000+ adversarial strategies · AIVSS-scored pentest report · Reproduction steps per finding · Remediation guidance
Continuous
未知
Enterprise
联系销售
Dedicated infrastructure · SSO & audit logging · custom SLAs · policy-template coverage (EU AI Act, ISO 42001, MITRE ATLAS) · hands-on remediation support
试用：未提供 · 设企业定制档 · 观察于 2026-11-03 · 原定价页
页面与变化
开始记录于 2026-05-08
关键页面
每周快照- 首页fabraix.com/
- 定价fabraix.com/pricing 快照 2026-11-03
- 功能fabraix.com/security 快照 2026-11-03
变化
开始记录以来，定价、套餐与定位都没有变化。
问题与证据
- Fabraix 的价格是多少？
- Researchers: $0; One-Off Scan: 未知; Continuous: 未知; Enterprise: 联系销售. 观察于 2026-11-03。 当前计费条件、用量限制与税费以来源页面为准。来源
- Fabraix 的网站访问量是多少？
- Vaneform 估算 2026-09 网站访问量为 <5K。访问量包含重复访问，付费客户数与收入需分别查看对应证据。来源
- Fabraix 是什么产品，支持哪些平台？
- Fabraix 归属「应用与云安全」赛道：Fabraix 的 Nyx 为部署 AI 的团队提供自主红队测试，持续发现 AI 智能体在安全、逻辑和对齐方面的漏洞。。 支持平台包括：网页。
- Fabraix 是开源项目吗？采用什么协议？
- Fabraix 拥有公开代码仓库（https://github.com/fabraix/playground），已公开源代码仓库，记录有 14 个 GitHub Stars。来源
同分类研究对象
安全与隐私 / 应用与云安全
这些产品属于同一目录分类。选型时请进一步核对客户任务、功能与部署要求。