Verification & Guardrails

Plugin suite adding Jev judgments to DeepSeek Harness: tool pruning, dead-loop blocking, a safety guard and skill routing.

DeepSeek Harness plugin where Jev classifies risk, irreversibility, task fit and injection for every tool call before it runs.

DeepSeek Harness plugin where Jev prunes long tool output, screens fetched pages for injected instructions and gates completion claims.

Supervisor for unattended coding agents: one batched Jev Choice over the trajectory decides continue, pause or escalate.

Self-hosted software factory running coding agents in microVMs with verification gates; offers optional DSPy/Jev task intake advice.

Claude Code plugin with rules and checks that make agents prove their work; an optional Jev judge triages review findings.

Software-factory supervisor where Jev independently judges coding agents' completion, test sufficiency, progress and need for a human.

SRT subtitle translator that translates with any OpenRouter LLM and asks Jev a review Noul per line to flag defects before export.

Two stdlib-only Hermes Agent plugins: a Jev pre-tool gate with a jev_ask tool, and a skill router that names one skill per turn.

Semantic code search and plain-English review rules that send repository chunks to Jev and return scored source locations.

Local guard layer for coding agents that blocks dangerous tool calls by deterministic rules, with optional Jev judgments.

Invalidation layer for agent memory: each fact gets a lease and Jev yes/no votes decide whether new evidence ends it.

CLI that scans source, build and CI files with Jev for hidden, deceptive or data-stealing behavior before you run unfamiliar code.

Read-only Go CLI that checks files against your plain-language code rules with Jev, locally or in CI.

Open-source agent guardrails that use Jev or LAYA to check prompts, retrieved content, tool calls and outputs for injection and risk.

Evidence-first experiment-memory skill for coding agents, with an optional Jev audit layer that checks provenance and claim support.

Starter kit that gates every MCP tool call with Kinde identity checks plus Jev risk signals, then allows, holds for approval or stops it.

Portable skill pack giving agents a conservative Jev second opinion on intent, completion, routing and bounded browser navigation.

GitHub Action that asks Jev three yes/no questions about a pull request and approves it only when all clear a confidence threshold.

Agent-ergonomic Jev CLI and PreToolUse hook that scores shell commands for hazards and screens fetched text for injection.

Claude Code Stop hook that blocks an unverified done: one four-question Jev call only when files changed and no check passed.

Browser QA where Playwright drives and records while Jev judges assertions, matches controls to intent and picks goal-directed clicks.

jevctl: Node CLI for typed Jev judgments (verify claims, screen agent hijacks, classify) with exit codes for CI gating.

CLI and agent commands auditing a git diff against YAML standards packs, scoring each hunk with Jev so agents fix only flags.

Commit-msg hook where one Jev request checks the message against the staged diff and flags filler, contradictions and secrets.

Unix-style tools where Jev learns a repo's decision norms and judges each node of a code lead as a bug, lead or clean.

Hermes plugin that asks Jev to review risky plans, check claims against sources, and judge whether a task is really finished.

Gateway admission control that asks Jev what each incoming request is trying to do, filtering prompt injection and abuse.

Claude Code plugin that checks every reply and file edit against your CLAUDE.md rules with one Jev yes/no per rule.

Coding-agent tools on Jev with public benchmarks: a strict command gate, a code-review router Action, and use cases.