DSH-PLUGIN STORE / LIVE CATALOG
聚合 GitHub 上的 DSH 插件，打造 DeepSeek Harness 生态的一站式目录。
39 个项目，匹配「agent」
strukto-ai
The World's First Unified Virtual Filesystem For AI Agents
xiaods
k8e.sh - OpenSource Agentic AI Sandbox Matrix
hashgraph-online
Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.
alibaba
ANOLISA (Agentic Nexus Operating Layer & Interface System Architecture) | Agentic OS with runtime, security, observability, and Tokenless response compression for lower token usage and cost.
cofy-x
Open-source sandboxes for AI agents, untrusted code execution, and durable services.
openguardrails
The vendor-neutral protocol for AI agent safety & security — and the neutral benchmark that ranks the vendors.
PerryLink
Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approval/asked -> autoReview/verdict -> approval/decided).
sjh9714
在 Windows 上把 DSH 用起来。一行装好极简模式的持久 shell，沙箱内也能用 | Get DSH working on Windows: persistent shell for Minimal mode, sandbox included
tensorlakeai
A deepseek harness plugin for tensorlake sandbox
030611
Observe-only hash-chained evidence receipts for DeepSeek Harness
MicroMilo
DSH plugin security and dependency monitoring for DeepSeek Harness: exact vulnerable paths, breaking updates, and Agent follow-up.
agentic-control-plane
Agentic Control Plane for DeepSeek Harness — policy-check every tool call before it runs
cdxiaodong
该仓库暂未提供项目说明。
Chhlafiu4312
Local prompt-injection and secret-exfiltration firewall for DeepSeek Harness.
Drifter-yh
Declarative deny-by-default tool policy plugin for DeepSeek Harness
Hyperionjust
该仓库暂未提供项目说明。
MkaliezZ
Deterministic fail-closed tool-call authorization for DSH with evidence: allow/block/ask policy gate plus approval-chain deferral.
SiliconPsycheLabs
PSA is a multi-classifier behavioral analysis engine for LLM responses. It classifies every sentence into behavioral postures, then derives metrics from the posture sequences to detect adversarial stress, sycophancy, hallucination risk, persuasion techniques, and input pressure — in real time.
ang-XWBWZ
AI approval answerer for DeepSeek Harness (DSH) using the unified LLM route with fail-closed policy checks.
cyzlmh
Authorized security-assessment profile for DeepSeek Harness: scoped network tools, container-backed shell, authorization guard, durable evidence, 21 security skills, 7 specialist subagents
dongsheng123132
Read-only recovery drill evidence for DeepSeek Harness
securstack
SecurStack adapter for DeepSeek Harness: run repository security scans, policy gates, doctor diagnostics, and JSON CLI results from safe AI-agent tools.
ChenLaoshiYF
?? for DeepSeek Harness: first security plugin for dsh. Scans skills/MCP configs for prompt injection, homoglyphs, hidden Unicode, dangerous shell, credential leaks. DSH ????????
Jelee0145
Codex-style automated approval review for DeepSeek Harness: an isolated reviewer subagent decides sandbox escalations by intrinsic risk and user authorization. Community Beta — not an official DeepSeek AI plugin.