Silmaril

About

Silmaril is the first runtime security for AI that self-improves. It understands application context to block 2x as many threats as current SOTA defenses with 10x lower latency. Customers plug us into agentic frameworks like LangGraph with 5 lines of code. Silmaril has stopped $28M of damages for customers.

Founders

• 
  Aum Upadhyay· Founder

  Co-Founder & CEO at Silmaril. I built the security and privacy framework at AWS that prevented over $1.8B in damages. Now I bring that same defensive mindset to Silmaril, working with customers to ship prompt injection defense.

  LinkedIn ↗Twitter ↗
• 
  Eduardo Velasco· Founder

  Co-Founder & CTO at Silmaril, the world's first self-healing prompt injection defense. I prove the risks are real by finding exploits myself. I chained a prompt injection into root access inside ChatGPT. Ex-Amazon tech lead specializing in low latency ML models that generated $400M in annual revenue.

  LinkedIn ↗Twitter ↗

Product launches · 1 launch

• Silmaril: Self-healing Prompt Injection Defense ↗▲ 21Apr 13, 2026

  Block 2x more attacks with 10x lower latency.

Change history · 5 recorded

1. June 23, 2026
   • Pitch updated07:00 PM
   • Description rewritten07:00 PM
2. June 14, 2026
   • Pitch updated07:00 PM
   • Description rewritten07:00 PM
3. April 13, 2026
   • New launch posted: Silmaril: Self-healing Prompt Injection Defense06:16 PM