x.comtoolAmada Echeverría (@amadaecheverria) on X
jes is an open-source real-time guardrails project for AI agents, built by LangChain Ambassador Eden Marco, that inspects every step of an agent's trajectory — prompts, tool calls, tool results, skills, and responses. It runs on decision models like Jev from TypeSafeAI and ships with a LangChain middleware example for wiring the checks into an agent pipeline.
TL;DR Open-source agent guardrails tool (jes) that checks prompts, tool calls/results, skills and responses in real time using LangChain middleware.
Also seen from another angle🧠 AI →
Organisations named here
- Eden Marco
- TypeSafeAI
Technologies named here
- jes
- TypeSafeClassifier
- LangChain
- Jev
Related in AI Security
blog.talosintelligence.comtoolIntroducing CAIRN: Frontier tracking for AI-integrated malware (Cisco Talos)
github.comadvisoryFlowise MCP Security Bypass Enables RCE
github.comrepoYesWeHack Claude Kit
jfrog.comarticle