Jev in production › Agent guardrails and approvals

jes

Open-source agent guardrails classify prompts, tool calls and responses using a decision model such as Jev instead of an LLM, to block prompt injection and data leaks (jes).

Open on GitHub ↗

The source publishes no measured number.
Use
Agent guardrails and approvals
Industry
Security
Form
Open-source tool
Stage
In production
Listed
2026-10-02
Found via
github
Repository
everafterlabs/jes
Stars
14
Forks
0
Last push
2026-10-06
Language
Python
License
Apache-2.0

The README opens with

Open-source guardrails for AI agents, powered by a decision model, not an LLM. Stop prompt injection, jailbreaks, data leaks and risky tool calls at every step of your agent.

- A decision model, not an LLM. Every judgment runs on a System One decision model like Jev or Laya. It classifies instead of generating, so injected text can't talk it out of its verdict. - Every step of the agent. Prompt, retrieved page, skill, subagent, tool call, tool result and response. - Secrets stay local. Secrets and PII are redacted in your process before any model sees the text. - Your thresholds. No magic defaults. Pin the model (jev-1.13.0) once you've tuned them.

Badge

For the project's own README, linking back here:

Listed in Jev in production

Also used for agent guardrails and approvals