Jev in production › Agent guardrails and approvals

toolgate

Jev scores risk of each agent tool call before execution; an independent reviewer's test flagged a folder deletion at 77% destructive risk for confirmation (author).

Open on GitHub ↗

77%measured, as published by the source
Use
Agent guardrails and approvals
Industry
Security
Form
Open-source tool
Stage
Beta
Listed
2026-10-11
Found via
github
Repository
RiskAverseTech/toolgate
Stars
24
Forks
1
Last push
2026-10-10
Language
TypeScript
License
MIT

The README opens with

Featured: AI LABS tested the Jev tools built since launch and kept eight; toolgate is first in This Just Fixed Your Claude Code Setup's Biggest Flaw (October 7, 2026). Their independent test caught a folder deletion at 77% destructive risk, which lands in the ask band, as designed: a delete the task did not call for gets one confirmation, not a block.

Open auto mode for AI agents. A calibrated tool-call firewall that runs as a Claude Code mod (or PreToolUse hook) or as an MCP proxy in front of any MCP server (Cursor, Claude Desktop, custom agents): before the agent runs a risky action, toolgate asks a decision model — TypeSafe's Jev, through its API directly, via OpenRouter's Decisions API, or via Vercel AI Gateway — seven questions and acts on...

Badge

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

Listed in Jev in production

Also used for agent guardrails and approvals