Jev in production › Agent guardrails and approvals

agent-reflex

A coding agent plugin uses Jev as a fast System One model to block dangerous shell commands and drive history compaction and thinking-effort selection for the agent.

Open on GitHub ↗

The source publishes no measured number.
Use
Agent guardrails and approvals
Industry
Developer tools
Form
Open-source tool
Stage
In production
Listed
2026-10-18
Found via
github
Repository
psygreg/agent-reflex
Stars
2
Forks
0
Last push
2026-10-24
Language
TypeScript
License
Apache-2.0

The README opens with

agent-reflex Plugin for coding agent workflow optimization and safeguarding using any system one decision model, from Jev to self-hosted LM Studio, Ollama or llama.cpp.

Goals - Safeguard against potentially dangerous shell commands - Improve token efficiency - Deliver more reliable solutions to tasks

Requirement The plugin needs a System One decision model as its classifier, served at /systemone — local llama.cpp (0.6 onwards), Ollama (0.35 onwards) or LM Studio (0.4.26 onwards), or TypeSafe Jev and other System One models through the TypeSafe API, OpenRouter, the Vercel AI Gateway or OpenCode Zen. Every feature below is driven by this classifier.

Badge

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

Listed in Jev in production

Also used for agent guardrails and approvals