AgentInterdict

Your agent is one document away from a breach.

Open Source

Privacy

Artificial Intelligence

GitHub

Visit WebsiteSee on Product HuntGithub ⧉Cloudflare Pages ⧉

It started with an uncomfortable realization: I was giving my AI agents more memory, more tools, and more autonomy — while almost nobody was securing the boundary where context becomes action. I kept seeing the same gap in every agent framework. A single poisoned document, a single malicious email, a single compromised web page could plant an instruction my agent would obey without question. My API keys, my credentials, my agent's integrity — all one bad retrieval away from being compromised. The uncomfortable truth that pushed me over the edge: if you run an agent with memory and tools and no enforcement layer, you are one malicious document away from a breach. Not "maybe." One document. So I built the thing I couldn't find: a local, open-source runtime that interdicts unsafe action before it executes — binds authority to origin, blocks credential leakage, quarantines memory poisoning, and revalidates every action at action-time. And I made a deliberate choice about honesty. Most security tools claim 99.9% block rates. I ran 200 real injection attempts through mine and got 96.5% — and I published the 7 misses with their payloads, because a security tool that hides its misses isn't trustworthy. It's free for personal/research use. The core that keeps your agent safe shouldn't be a paywall. → [github.com/BryanFiFife/AgentInterdict] What attack vectors am I missing? I'd genuinely love the community's input.