Noisegate
a differential-privacy gateway for untrusted AI agents. Noisegate: a differential privacy gateway that lets an untrusted LLM agent query sensitive data over MCP (Model Context Protocol), with a formal guarantee no individual's record can leak even if the agent is adversarial - enforcement lives in trusted code below the model, validated by a runnable attack gallery.
오픈소스
반응 (1)
비슷한 프로덕트
설명이 비슷한 순
Halo
github.comopen-source, tamper-evident runtime evidence for AI agents
Context Gateway
github.comCompress agent context before it hits the LLM
HoundDog.ai
github.comUltra-Fast Code Scanner for Data Privacy
🔐 Firewall Your Data, Control Agents. Prevent agent data exfiltration. Gain visibility into AI's interactions with your data / systems of record / existing software. https://discord.gg/tXjATaKgTV
Open Bias
github.comproxy that enforces agent behavior at runtime