asaotomo/DeepSentry
DeepSentry(深哨) 一款 AI 驱动的新一代安全运维代理。支持本地/SSH 混合执行、动态风控与自动化审计报告生成。(集成 DeepSeek/OpenAI/Ollam/LM Stuido)
# DeepSentry Technical Summary Implements a multi-modal execution engine with automatic OS detection and cross-platform command translation, enabling the LLM to switch between local shell, SSH remote execution, and hybrid workflows (upload/download) within a single task. Built in Go with pluggable LLM backends (DeepSeek/OpenAI/Ollama), it includes a risk-scoring engine that auto-executes low-risk operations (`ls`, `ps`) while gating destructive commands (`rm`, `kill`) with user confirmation, plus automatic Markdown audit report generation with execution traces and timestamps.
Stars
8
Forks
4
Language
Go
License
—
Category
Last pushed
Jan 31, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/asaotomo/DeepSentry"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
TouHouQing/DataSentry
🛡️An AI-powered data governance agent platform. Supports Real-time Interception & Database Batch...
azdhril/Sentinel
🛡️ Zero-trust governance for AI agents. Intercept, approve, and audit LLM actions with one...
Raunplaymore/sentinel
Sentinel watches what your AI agents actually do — file access, network calls, risky commands —...
vectimus/sentinel
Automated threat intelligence pipeline for agentic AI security. Three AI agents discover...
josephawana/Kali-Safety-EDR
🛡️ Kali-Safety-EDR: A lightweight, Python-based Endpoint Detection and Response (EDR) tool...