Silmaril
Silmaril is a YC Spring 2026 (P26) company. Based in San Francisco, CA, USA. Team of 2.
About Silmaril
Summary
Silmaril builds runtime security for AI agents, protecting agentic systems from prompt injection, data exfiltration, and instruction hijacking attacks that exploit public inputs, trusted context, and web content. It targets B2B teams deploying agents on frameworks such as LangGraph, replacing manual threat detection and static rule-based defenses with a self-improving layer that inspects tool calls and message payloads in real time.
Business model
Customers integrate via a few lines of code into their agentic framework.
Go-to-market
B2B engineering and security teams adopt Silmaril through a self-serve integration into existing agentic frameworks, with a sales-assisted path via a booking flow on the website.
From the Y Combinator listing
Runtime security for AI that self-improves
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.
Facts
- B2B / B2B
- San Francisco, CA, USA
- 2
- Active
- Early
Founders (2)
Score every batch against your own thesis
GPAgent's sourcing agent reads every company in a batch, scores each one against your fund's thesis in a private workspace, and lines up the founders worth meeting before Demo Day. You decide who to contact. Your scores, notes, and pipeline never appear on these pages.
How Accelerator intelligence works