jev-agent-guardrail
Xano template for an agent tool-call guardrail in which Jev decides and Xano enforces.
This summary is based on how curated lists describe the project; its README was not available to review.
Overview
This is a Xano template, listed in wh000wh000/awesome-jev-live, that adds a guardrail in front of an AI agent's tool calls. The design summarised as Jev decides, Xano enforces means the proposed tool call is sent to Jev for a typed risk judgment and the Xano backend applies the outcome, allowing or blocking the call.
It is aimed at teams building agent backends on Xano's no-code or low-code platform who want a calibrated safety check without writing a custom service. No README was available, so the exact questions, thresholds and setup steps are not documented here.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Yes / no | Is this proposed tool call risky or disallowed?(inferred) | yes · no |
How it works
- Agent proposes a tool call
- Xano sends the call to Jev
- Jev returns a probability of risk
- Xano allows or blocks based on a threshold
Strengths
- Enforcement stays in the backend platform
- Calibrated check rather than an LLM review
Caveats
- No README; details unknown
- Tied to the Xano platform
At a glance
- Type
- Project
- Runtime
- Xano backend template
Use cases and integrations
How curated lists describe it
Xano template: Jev agent tool-call guardrail. Jev decides, Xano enforces.
wh000wh000/awesome-jev-live
Frequently asked questions
What does the template decide?
Whether an agent's tool call should be allowed, using a Jev judgment enforced by Xano.
Who is it for?
Teams building agent backends on Xano.
Is there documentation?
No README was available; check the repository and Xano template.
Related projects
Auditable Zig terminal agent pairing Codex for coding with Jev typed preflight and postflight checks under deterministic policy gates.
CLIproductionZigGateway that checks agent tool calls with policy plus Jev evidence, then binds approval to a single-use permit for that exact action.
MCP serverbetaTypeScriptMCP proxy and hooks that screen agent tool calls before they run and their results before the agent reads them, using Jev judgments.
MCP serverbetaTypeScriptXano backend template where Jev judges each agent tool call as safe, needs review or dangerous, and uncertain calls wait for a human.
ProjectbetaXanoScriptOpenAI-compatible endpoint that answers an agent's command-approval call with APPROVE, DENY or ESCALATE from a Jev Choice, failing closed.
ProxybetaPythonClaude Code plugin adding Jev judgments to Bash, Write and Edit calls and their outputs; a semantic guardrail, not a sandbox.
Pluginbeta