x.comthreadAmada Echeverría (@amadaecheverria) on X
Jes is an open-source real-time guardrails library for AI agents built by LangChain Ambassador Eden Marco, designed to check every step of an agent's trajectory: prompts, tool calls, tool results, skills, and final responses. It runs as LangChain middleware and uses decision models like Jev from TypeSafe AI via a TypeSafeClassifier to make pass or fail calls at each checkpoint, with docs showing a concrete middleware integration example.
TL;DR Jes is an open-source LangChain middleware adding real-time guardrails over prompts, tool calls, tool results, and responses in agent pipelines.
Also seen from another angle🛡️ Security →
Organisations named here
- LangChain
- TypeSafe AI
- Eden Marco
- Jev
Technologies named here
- jes
- Jev
- TypeSafeClassifier
- LangChain middleware
- LangChain
Techniques named here
- Agent trajectory guardrails
Related in agents
