{"id":93541,"title":"Superagent — the AI Firewall 🥷🔥","tagline":"Stops prompt injections, backdoors, and data leaks.","body":"Hi everyone, we’re Alan and Ismail, founders of **Superagent** (YC W24).\n\nWe built the world’s first **AI Firewall** — powered by a model that sits between you and your models, protecting every request and response in real time.\n\n---\n\n## The Problem\n\nAI is quickly becoming the foundation of how software is built and used. But every time you send a prompt or receive a response, you take a risk:\n\n* Models can be tricked with prompt injections or jailbreaks\n* Sensitive data like API keys and PII can leak out\n* Malicious code or backdoors can slip through responses\n\nIf you’re building with AI or adopting third-party AI tools, you’re exposed.\n\n---\n\n## Our Solution\n\nSuperagent introduces **NinjaLM** — a small language model fine-tuned for security and safety. It runs in runtime (tens of milliseconds) and reasons about every prompt and response before it reaches your system.\n\n✅ Stops prompt injections and jailbreaks\\\n✅ Prevents secret leaks (API keys, credentials, PII)\\\n✅ Blocks malicious code before it reaches your system\\\n✅ Full audit logs, traces, and observability for compliance\n\nFrom internal apps to tools like Claude Code or ChatGPT, Superagent protects your AI without slowing you down.\n\n## https://youtu.be/GBTAs9yZiPM\n\n## Backstory\n\nBefore Superagent, we built plenty of AI apps ourselves. Each time, we ran into the same problem: adding even the most basic kind of protection was incredibly hard.\n\nTraditional firewalls are built for static rules — not reasoning. But AI isn’t static. It thinks, it adapts, and that creates a completely new class of security challenges.\n\nWe realized the only way forward was to fight fire with fire: build a model that could reason about other models, catching attacks, leaks, and malicious behavior in real time. That’s how the AI Firewall was born.\n\n---\n\n## Try It\n\nWe just launched our hosted service, and the open-source repo is live. Engineers can get started in minutes, and executives get the auditability and compliance they need.\n\n👉 [superagent.sh](http://www.superagent.sh)\\\n👉 [github.com/superagent-ai/superagent](https://github.com/superagent-ai/superagent)\n\n---\n\n## Call to Action\n\nIf you’re building or adopting AI:\n\n* Engineers — run your apps through Superagent today\n* Security teams — add prevention and compliance controls\n* Partners — we’re exploring integrations and distribution\n\nWe’d love your feedback. Links in comments.\n\n![uploaded image](/media/?type=post\u0026id=93541\u0026key=user_uploads/1367556/b76c2ef1-9036-484d-9564-73cecff2c9ff)\n\n---","slug":"OKj-superagent-the-ai-firewall","created_at":"2025-09-03T14:51:00.274Z","updated_at":"2026-05-25T01:22:22.502Z","total_vote_count":10,"url":"https://www.ycombinator.com/launches/OKj-superagent-the-ai-firewall","share_image_url":"https://www.ycombinator.com/media/?type=post\u0026id=93541\u0026key=user_uploads/1367556/b76c2ef1-9036-484d-9564-73cecff2c9ff","company":{"id":29374,"name":"Superagent","slug":"superagent","url":"https://superagent.sh/","logo":"https://bookface-images.s3.amazonaws.com/small_logos/a5fb7dd012389ddf81869040550578bb786988ed.png","batch":"Winter 2024","industry":"B2B","tags":["Artificial Intelligence","Security","Open Source","AI"],"search_path":"https://bookface.ycombinator.com/company/29374"}}