shipwithjev

Catalog / Agents & browsers

0617GitHub

toolgate: a tool-call firewall for agents

A Claude Code and MCP hook where Jev answers seven yes/no risk questions per tool call to allow, ask or deny. Usage and benchmark numbers are in the repo.

RiskAverseTech/toolgateREADME ↗
# toolgate

[](https://www.npmjs.com/package/@riskaverse/toolgate) [](https://github.com/RiskAverseTech/toolgate/releases) [](https://github.com/RiskAverseTech/toolgate/actions/workflows/ci.yml) [](LICENSE)

**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](https://www.youtube.com/watch?v=jlEMo6Dsh9E) (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.

**Auditable auto mode for AI agents.** A calibrated tool-call firewall that runs as a Claude Code mod (or `PreToolUse` hook), an OpenCode plugin, or 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](https://typesafe.ai/blog/introducing-system-one-models-and-jev), through its API directly, via [OpenRouter's Decisions API](https://openrouter.ai/docs/api/api-reference/alphadecisions/submit-a-decisions-questions-and-answers-request), via [Vercel AI Gateway](https://vercel.com/changelog/typesafe-ai-jev-now-available-on-ai-gateway), via [OpenCode Zen](https://opencode.ai/docs/zen/), or any `/v1/systemone`-compatible endpoint on your own machine — seven questions and acts on the probabilities. It is the "permissions / approval" pattern TypeSafe's CEO describes in his [public memo on a typesafe coding agent](https://docs.google.com/document/d/1G61uUB0FifUnmmrPzFQojZ3KpczYKmXGpgEXDJ2l_Zg/) — programmable queries on what may run, and reading what a file does before executing it — built as a plugin to the agents people already use, and measured (see [Evaluation]

Also filed under Agents & browsers

  1. 0226

    Flight search with Browser Use★

    Breaking: Browser Use + Jev = Ultrafast ⚡ Findings flights took 7s and cost only $0.0039 🤯 > new action space every step > DOM state space > small LLM fallback to type (this video is at 1x speed btw) Built a tiny open source browser agent. try it below ↓

    @gregpr07 · Agents & browsers · ~$0.004 · ~7 s

  2. 0619

    jevmem: automatic project memory for Claude Code

    After every Claude Code message, Jev decides in ~0.3 s whether it holds a decision, rule or bug worth keeping, and jevmem saves it as one line in JEVMEM.md.

    @jetwaniavinash · Agents & browsers · ~0.3 s

  3. 0618

    Playwright + Jev: tests in plain language

    Write Playwright steps like "add the most expensive item to the cart". Jev finds the right buttons and fields, fills forms and checks the result.

    Andrey Popov · Agents & browsers

  4. 0605

    Jev Layer: bounded decisions for agent harnesses

    An open-source decision layer that recommends a capability from a host-approved set and records the outcome for replay. The host keeps control of permissions.

    typakon4 · Agents & browsers