RRiskAverseTechBenchmarks & research

toolgate (RiskAverseTech)

Open auto mode for AI agents — a calibrated tool-call firewall powered by TypeSafe Jev. Ships as a Claude Code hook

Explore repository

A measured tool-call firewall for AI agents: allow, ask or deny before the agent acts. Claude Code mod and hook, MCP proxy. Built on TypeSafe Jev, measured on real sessions with a blind second labeler.

How it uses Jev

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.

Getting started

Then quit and reopen Claude Code. That's it.

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.

Keep exploring

Similar to toolgate (RiskAverseTech)

Browse all
jev-harness project preview

jev-harness

Benchmarks & research
Decision harness for TypeSafe Jev — confidence gates, shadow mode, recipes, and evals. Claude CLI 48.9s → Jev 1.3s on the same row-filter job.
AMade byAntonioCoppe14
jev-firewall project preview

jev-firewall

Agent tooling
Real-time firewall for AI coding agents: a PreToolUse hook checks every Claude Code / Codex tool call with deterministic shell-aware rules, and unmatched actions go to Jev for a calibrated allow/ask/block that fails closed.
KMade byKoushik8901
toolgate project preview

toolgate

Demos & playgrounds
Agent tool/MCP call gate — allow / ask_human / deny via TypeSafe Jev
NMade byndolinschi2
rh-guard project preview

rh-guard

Benchmarks & research
Reward-hack radar for coding agents: structural denies + TypeSafe Jev System One sidecar for Claude Code & Cursor hooks
2Made by246013
jev-agent-authorization project preview

jev-agent-authorization

Benchmarks & research
Jev agent authorization for MCP tool calls: Kinde identity and permissions plus Jev's typed, calibrated decisions, checked server-side before every call runs
KMade bykinde-starter-kits5
jev-mcp (rashedInt32) project preview

jev-mcp (rashedInt32)

Agent tooling
MCP server exposing TypeSafe Jev as typed, calibrated judgment tools: classify, score, check, batched ask. Ships as a Claude Code plugin.
RMade byrashedInt327
pi-jev-auto-mode project preview

pi-jev-auto-mode

Agent tooling
Jev (TypeSafe System One) backed auto mode for the Pi coding agent: semantically auto-approves bash, write, and edit tool calls and fails closed when a decision cannot be made.
JMade byjomatsu23
eve project preview

eve

Integrations
Vercel's open agent framework, which ships Jev as the default evaluation model in its experimental evaluate path.
VMade byvercel5.3k
agent-fastpath project preview

agent-fastpath

Browser & computer use
Jev MCP server: a decision layer for coding agents, built on TypeSafe Jev (System One model). Ship gates, risk checks, file triage that keeps files out of context, and a safe headless browser, with calibrated confidence. For Claude Code, Codex, Cursor.
AMade byabhishekswe3