Skip to content

Jev Kit — jonathanavis96

Claude Code kit that guards PreToolUse calls with a free pre-filter plus one Jev question for ambiguous cases, and adds sub-agent sizing, rechecks, search, daemon speedups, and monitoring.

Stars
63
Language
Python
License
MIT
Published by
Community
Author
jonathanavis96
Last verified
Oct 2026

jonathanavis96/jev-kit

User repository on GitHub

View on GitHub

Everything you need to run TypeSafe's Jev with Claude Code: a tool-call guard, tier guard, file search, browser agent, review, belay, compaction and installers.

Forks
7
Last pushed
Updated Oct 2026

Repo stats from the GitHub API, cached Oct 2026.

About this project

Everything you need to run TypeSafe's Jev with Claude Code: guard your agent's tool calls, right-size its sub-agents, and wire Jev into search, browsing, review and more. Quickstart · What is in the kit · Browser result · How it works · Measured results · Safety · FAQ.

Quoted from the project's README. Read the full README.

Highlights

  • Airlock judge with code pre-filter, single typed Jev question, redacted summaries, and fail-open errors.
  • Warm daemon, file search, monitoring, installer, doctor, rollback, and tuning loop with exercised status per component.
  • Browser, review, classifier, log triage, and shim as opt-in uses with explicit data-exposure notes.
  • Shadow-first workflow with mode file, kill switch, pipeable deny proof, and never-print key handling.

Watch out

Needs a TYPESAFE_API_KEY stored at the kit path, defaults to shadow log-only mode until you enforce, and any judging error lets the call through. Copy reviewed against the repository README on 2026-10-04, not from running it.

Questions about this entry

Short answers drawn from the linked project or page.

Other listings of this project

Forks and copies of this project in the directory. This entry is the canonical one.

0GitHub stars
Typed Jev client plus benchmark harness reached through Vercel AI Gateway for measuring accuracy and picking thresholds.
Jev Benchmarks & Evaluations#community#github

More Jev resources like this

macOS computer-use kit exposing an 18-tool stdio MCP server plus CLI that drives apps through the accessibility tree, posting input in the background without moving the user cursor.
Jev Demos & Experiments#community#awesomejev#catalog-import
2GitHub stars
A computer-use agent for the browser and for native macOS apps that puts a Jev guard in front of the driver: claimed completions are checked against observed state and the trajectory, irreversible actions pass a gate, and Jev can take the mechanical steps itself.
Jev Demos & Experiments#community#awesomejev#catalog-import
22GitHub stars
Terminal harness that checks ROS 2 robots with deterministic health tests, capability descriptions, SQLite history, and optional Jev evidence routing.
Jev Demos & Experiments#community#jevbest#catalog-import
19GitHub stars
MCP server where one browser_goal call hands a URL, a goal, and code-checked assertions to a server-side loop driven by a decision model over live page elements.
Jev Demos & Experiments#community#jevbest#catalog-import
16GitHub stars
Local Qwen3.5 decision models in 0.8B and 2B sizes with fitted temperatures, systemone-shaped server, playground, guard, MCP tools, and eval harness.
Jev Demos & Experiments#community#jevbest#catalog-import
8GitHub stars
Browser workflow that keeps one Aside REPL session open, compacts page observations into allowed candidates, and has Jev pick the next action with confidence checks.
Jev Demos & Experiments#community#awesomejev#catalog-import

From the Jev guides

Original write-ups on what this entry is for.

A game tick is a state plus a legal action list. How Clash Royale, Minecraft, and the earlier Mario, Pokémon, StarCraft, and drone loops ask Jev one step at a time.
Jev Demos & Experiments#gaming#agents#control
Read article
Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai