Koreshield
Security and evidence for AI support agents
Koreshield launched on September 22, 2026 with 91 votes, #296 of 8,042 launches that month and more than 95% of that year's launches.
What it does
Inspect customer input, retrieved context, and proposed actions before they become trusted instructions inside an AI support workflow.
Stop untrusted customer content from becoming trusted instructions inside your AI workflow. Koreshield evaluates each boundary independently and records the reason for every decision. Inspect messages, attachments, and externally controlled text before model execution. Keep poisoned tickets, CRM notes, and RAG documents from inheriting system authority. Evaluate tool calls against trust, approval, and authorization limits before execution. Begin with live traffic in detect mode. Review expected behavior and false positives, then enable enforcement when the fallback path is ready. Koreshield should prove itself against your support workflow before any request is blocked. Run the FastAPI…from koreshield.ai
Does a similar job
all alternatives →
- AI
More ai this month
the category →
E-ink bird frame for Raspberry Pi - real-time bird detection by audio, fully local AI, rendered as real, hand-cut 1800s bird illustrations. - arnegiacomo/fugleramme
AI · 17d ago · github.com
PixVerse R2▲381A real-time world model you can explore and change
AI · 10d ago · world.pixverse.video
Source: Product Hunt launch ↗
Launched alongside, September 2026
the whole month →E-ink bird frame for Raspberry Pi - real-time bird detection by audio, fully local AI, rendered as real, hand-cut 1800s bird illustrations. - arnegiacomo/fugleramme
AI · 17d ago · github.com
- WI
Special relativity simulator in which light crawls along at a human speed, so Lorentz contraction, aberration and Doppler shift happen at walking pace.
Life & fun · 23d ago · rivendell.dmitrybrant.com
Start coding agents, control sessions, review PRs. Anywhere.
Dev tools · 22d ago · kilo.ai