JJevHunt
LaunchesProjectsTasksCategoriesCollectionsGuidesFAQEvidenceUpdatesSubmit
JevHunt / Tasks / Guardrails & safety

Guardrails & safety — page 7

Permission checks, moderation and safety filters for agents. Jev answers an explicit policy question before the action runs.

147 active projects match this task, ordered by traction.

← Previous Page 7 of 7
K

KAsset-Trader-Core

gim47656-ship-it/KAsset-Trader-Core
★ 0

LLM agent trades KR/US stocks & crypto behind a deterministic safety layer — approval gates, idempotent orders, fill-evidence reconciliation. FastAPI · MCP · PostgreSQL

VerifiedJev applicationPythonupdated 2026-09-29
Details →GitHub ↗Documented ↗
O

omp-classifier

STRML/omp-classifier
★ 0

Model-judged permission gate for OMP: classifies bash commands and spawn-bearing eval payloads before they run, prompts on risk, fails closed

VerifiedResearchTypeScriptupdated 2026-09-28
Details →GitHub ↗Documented ↗
P

pikachu

tsnAnh/pikachu
★ 0

Curated Pi coding agent configuration with Jev compaction, LSP, subagents, plan mode, safety tools, and automatic updates.

VerifiedJev applicationTypeScriptupdated 2026-09-25
Details →GitHub ↗Documented ↗
← Previous Page 7 of 7

Related tasks

Browser automationDrive Chrome or Playwright with typed decisionsComputer & desktop useControl apps, screens and the mouseAgent routing & tool choicePick the next tool, model or branchClassification & labellingSort text, tickets and intentReranking & relevanceReorder search and retrieval resultsRAG & retrievalGround answers in your own data
Independent Jev ecosystem directoryPrivacyTermsSecurityEnglish简体中文繁體中文日本語한국어EspañolFrançaisDeutschPortuguêsРусскийहिन्दीBahasa IndonesiaTiếng ViệtTürkçeItaliano