hermes-jev-approvals

PoC: TypeSafe Jev as the reviewer for Hermes Agent smart command approvals. 8.7x faster, 4.4x fewer prompts, measured on 153 real commands. Approvals only.

Explore repository

TypeSafe Jev as the reviewer for Hermes Agent smart command approvals. 8.7x faster, 4.4x fewer prompts, measured on 153 real commands. Approvals only.

How it uses Jev

Smart command approvals for Hermes Agent, served by TypeSafe's Jev decision model.

Highlights

APPROVE — execute without interrupting the user.
DENY — block the command.
ESCALATE — ask the user.

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

Language: Python 100%
License: MIT
Latest release: jev-approvals v0.3.0
Last activity: Sep 2026
Added: 2026-09-18
Stars at snapshot: 14
Status: Community listing

Is this your project?

Add the badge to your README to link back here.

[![Listed in Jev Library](https://jevlibrary.dev/api/badge/anpicasso-hermes-jev-approvals)](https://jevlibrary.dev/projects/anpicasso-hermes-jev-approvals)

Something wrong, or rather not be listed? Tell us.

Keep exploring

Similar to hermes-jev-approvals

Browse all

jev-decisions

Agent tooling

Safety checks for Hermes and other AI agents before they act, ask for approval, or verify a change.

BMade bybojansandhaus2

ask-jev-skill

Agent tooling

Skill for Hermes, and other agents, to ask typesafe's jev

SMade byshantanugoel39

hermes-jev-plugin

Agent tooling

TypeSafe Jev (System One) decision tools for Hermes Agent: jev_check / jev_route / jev_score / jev_evaluate

AMade byajensenwaud5

jevbench

Benchmarks & research

JevBench v1 - a benchmark for Jev-class typed decision models: smart, cheap, fast, reliable, open.

FMade byfstandhartinger114

hermes-jev-skills

Browser & computer use

Jev-powered model routing, memory, compaction, skill selection, computer and browser use for Hermes agents (also Claude Code and Codex)

KMade bykerpopule726

typesafe-ai-jev-example

Demos & playgrounds

Hands-on demos for TypeSafe's Jev (System One) model: six runnable examples and four field notes. Runs offline with no API key; samples/ holds real measured output from jev-1.13.0.

IMade byItBayMax2

jev-ra

Browser & computer use

Browser use for coding agents, 3-5x faster than browser-use. MCP server + CLI; TypeSafe Jev decides every step in ~300 ms.

BMade bybrnyxx4

jev-voice

Applications

Talk to your Mac. Local whisper.cpp + one Jev (TypeSafe) call per command + macOS automation.

KMade bykevinbadi86

jev-guardrails

Benchmarks & research

Comparing LLM-as-judge vs TypeSafe Jev for agent guardrails: same rules, same agent, measured on cost, latency, calibration and coverage.

DMade bydeepansh-saxena3