GgodspedeAgent tooling

construct-auto-classifier

Effect-based safety gate for AI coding agents' shell commands (OpenCode, Antigravity): fast structural rules, then TypeSafe's Jev or a chat model judges what a command does. Certified with Jev at zero dangerous commands allowed.

Explore repositoryVisit website

How it uses Jev

Universal, effect-based safety gate and command classifier for AI coding assistants, deciding with TypeSafe's Jev or any chat LLM. Supports Google Antigravity ( agy ) , OpenCode , and external agent harnesses.

Getting started

Prerequisites - Bun v1.2+ to build and test (the built plugin and CLI run on Node.js 18+ too) - A TypeSafe API key for Jev (the default), or an OpenAI-compatible LLM endpoint (DeepSeek, Ollama, vLLM, OpenRouter, Groq, OpenAI, or local gateway).

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

Keep exploring

Similar to construct-auto-classifier

Browse all
jev-code (FrancoisChastel) project preview

jev-code (FrancoisChastel)

Agent tooling
Jev, TypeSafe's System One classifier, as a tool inside Claude Code, Codex, Pi, and OpenCode: typed classify, check, score, rank, and ask, plus one-command setup.
FMade byFrancoisChastel15
jev-guard project preview

jev-guard

Agent tooling
Prompt-injection and dangerous-action guard for coding agents (Claude Code, Codex, pi, ACP), powered by Jev
LMade byleepokai32
slop-grader project preview

slop-grader

Agent tooling
Rule-based slop grader for text files powered by Jev: evaluates markdown against customizable rulesets, outputting violation flags and scores for an AI agent to auto-fix.
LMade bylukstei22
jevalyzer project preview

jevalyzer

Benchmarks & research
Grade the agent sessions already on your disk. Claude Code, Codex, opencode, Gemini CLI and Antigravity, scored with Jev for cents.
KMade bykillerz32
jgrep (kyu1204) project preview

jgrep (kyu1204)

Applications
grep for what code does, not what it's called. Semantic code search powered by TypeSafe Jev.
KMade bykyu120425
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-shell-history project preview

jev-shell-history

Integrations
Fish-style zsh history autosuggestions ranked by Jev (TypeSafe)
MMade bymrnugget108
zerosweep project preview

zerosweep

Benchmarks & research
Autonomous System-One Triage Engine & Benchmark powered by TypeSafe AI (Jev). 75ms inference, $0 output tokens, and RLCD epistemic safety gates.
SMade bysysadarsh2
typesafe-cli (y0usaf) project preview

typesafe-cli (y0usaf)

Applications
Ask Jev typed questions from the shell: noul, choice, and score answers as numbers, not prose
YMade byy0usaf4