Fabraix
AI-nativeOur agents hack your AI, before attackers do.
fabraix.com Source★ 14 DiscordSecurity & Privacy / Application & Cloud Security
- Monthly visits
- <5K
- Sep 2026
- Public revenue
- Undisclosed
- No public revenue evidence yet
- Entry price
- Usage-based
- No monthly subscription pricing
- Launched
- 9mo ago
- 2026-02-10 · Est.
Traffic
Marketing moves
Launches, search & content, referrals, promotions- this feels increasingly important with cyber guardrails on frontier models preventing this kind of work and potential bans on chinese open source models. 引用帖 @fabraixhq： Introducing Nyx, the world’s frontier hacker of AI agents. On AgentH
@gabrielste1n · 2026-07-20 · 3 likes · 0 reposts · 564 views
Launched on Show HN (13 pts · 4 comments)Launch
Open-source playground to red-team AI agents against public prompts
Aug 9 · 3mo agoLaunch page
At the time: 7.6K visits/moVisits: next 2 mo -65%2 concurrent movesLaunched on Show HN (4 pts)Launch
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…
Jul 13 · 4mo agoLaunch page
Launched on Product HuntLaunch
Earn $100K+ in weekly rewards for hacking AI agents.
Jul 13 · 4mo agoLaunch page
Launched on Show HN (20 pts · 8 comments)Launch
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…
Apr 19 · 7mo agoLaunch page
Third-party reviews & case dossiers
Acquisition breakdowns, engineer reviews & open-source metrics- Post excerpt:
- 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
- Post excerpt:
- 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
- Post excerpt:
- 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
- Post excerpt:
- 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
- Post excerpt:
- 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
Open Source & Self-Hosting
- GitHub Stars
- ★ 14
- Forks
- 1
- License
- See repository
- Primary language
- —
Traffic sources
Traffic breakdown
Channels
- Direct39%
- Organic Search32%
- Referrals11%
- Social6%
- Other12%
Countries
- United States91%
- Canada9%
Search
Domain authority —Domain registered 2025-04-13
| Keyword | Monthly volume |
|---|---|
| fabraix | 500 |
| fabrantic ai | 60 |
| ai ferracio | 0 |
Traffic data: Vaneform
Pricing
Trial: None · Enterprise custom tier · Observed 2026-11-03 · Pricing page
Pages & changes
Key pages
Weekly snapshots- Homefabraix.com/
- Pricingfabraix.com/pricing Snapshot 2026-11-03
- Featuresfabraix.com/security Snapshot 2026-11-03
Changes
No pricing, plan, or positioning changes detected since tracking started.
Questions & evidence
- How much does Fabraix cost?
- Researchers: $0; One-Off Scan: Unknown; Continuous: Unknown; Enterprise: Contact sales. Observed 2026-11-03. Check the source for current billing terms, usage limits and taxes.Source
- How much website traffic does Fabraix get?
- Vaneform estimates <5K website visits in 2026-09. Visits can include repeat visits; this estimate measures web traffic separately from paying customers or revenue.Source
- What is Fabraix and what platforms does it support?
- Fabraix is catalogued under Application & Cloud Security: Our agents hack your AI, before attackers do.. Supported platforms: Web.
- Is Fabraix open source?
- Fabraix has a public repository (https://github.com/fabraix/playground) with its source repository published, recording 14 GitHub stars.Source
Related products in this category
These products share a catalog category. Compare customer tasks, features and deployment requirements before treating them as alternatives.