Fabraix
Find vulnerabilities in your AI systems before users do.
San Francisco, United States · Founded 2026 · $500K raised
- Headquarters
- San Francisco, California
- Employees
- 1–10
- Founded
- 2026
- Business Model
- B2B
- Website
- fabraix.com
- Total Funding
- $500K
- Last Round
- $500K Pre-SeedJun 2026
- Rounds
- 1
About
Fabraix is a Y Combinator-backed (S26) AI security research lab that builds autonomous red-teaming agents to continuously find vulnerabilities in customer-facing AI systems. Its flagship product, Nyx, probes AI agents in pure blackbox mode — no source code access required — using a library of over 10,000 adaptive attack strategies that dynamically adjust based on the target agent's defenses, covering security, logic, and alignment failures across chat, voice, browser, and coding agents. Fabraix has achieved a 78% attack success rate on the AgentHarm benchmark (vs. 67% for GPT-5.6 Sol) and has already surfaced exploitable vulnerabilities in AI agents at dozens of Fortune 500 companies.
Summary
Fabraix is an Artificial Intelligence company based in San Francisco, United States, founded in 2026. It has raised $500K in total across 1 round, most recently a $500K Pre-Seed round in Jun 2026. Investors include Y Combinator Continuity Fund and Byld Ventures.
Funding History
Jun 2026
Investors
Similar Companies
Palantir Technologies builds data integration and analytics platforms (Gotham and Foundry) for go...

Cyera transforms the way organizations secure data in the cloud with Data Reality.
Real-time AI platform that detects early signs of high-impact events and emerging risks from publ...

OpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artifi...
Anthropic is an AI research company that builds reliable, interpretable, and steerable AI systems.
xAI is an AI platform for accelerating human scientific discovery.
