Back to catalog

GITHUB TOPIC

guardrails

16projects include this topic

The "guardrails" topic on GitHub groups 16 open-source projects in the DeepSeek Harness (DSH) ecosystem, led by dsh-memory with 579 GitHub stars. dsh-memory — White-box AGI architecture exploration: metacognition (self-awareness loop), continual learning (knowledge flywheel), world model (condition space + semantic spatiotemporal graph), self-improvement (bootstrapping discipline), zero-LLM white-box pipeline and auditable trust guardrails. Every project here is indexed by DSH Universe with live GitHub data — stars, activity and install status — so you can compare and install directly.

{count} projects

Exact GitHub Topic match

Models & MCPPlugin

dsh-memory

FuRongJun-1999

White-box AGI architecture exploration: metacognition (self-awareness loop), continual learning (knowledge flywheel), world model (condition space + semantic spatiotemporal graph), self-improvement (bootstrapping discipline), zero-LLM white-box pipeline and auditable trust guardrails.

Structure check pending
agent-safetyagentic-aiagiai-agent-framework
DSH PluginsPlugin

⚡ Millisecond System-1 judgement for every tool call in DeepSeek Harness — Jev-powered risk classification & evidence-gated auto-approval. Fail-closed by construction. dsh 生态第一个 System-1 决策插件

Structure check pending
agent-harnessagentic-aiai-agentsai-safety
Development toolsPlugin

SpecWave

Cyning12

SpecWave — multi-host coding CLI + P0 gates/Harness (Cursor/Claude/DSH). Formerly SpecGate / dsh-coding-kit. npx spec-wave

Unrecognized
agents-mdai-codingclaude-codecli
Security & governancePlugin

Caushell

fatmo666

Compiler-style pre-execution safety analysis for Harness shell actions.

Structure check pending
ai-agentbashclaude-codeclaude-code-plugin
Security & governancePlugin

dsh-safety-net

Asuna486-desuwa

Self-protection guardrails for the DeepSeek Harness: protected-path interception, backup-before-destroy, CLI self-recovery commands, and strict sandbox defaulting

Structure check pending
deepseek-harnessdsh-pluginguardrailssafety
Security & governancePlugin

Commitment write-gate for AI coding agents: two-tier pre-execution policy (deterministic guard + LLM judge) with measured receipts. DeepSeek Harness plugin, engine-agnostic core.

Structure check pending
agent-safetyai-agentsdeepseek-harnessdsh-plugin
Models & MCPChannel integration

NoLeakMCP

ishamishra0408

A teammate posts one Slack message. Your AI assistant reads it, believes it, and hands over your keys through a link preview — nothing shows in the channel. Three plugins for the dsh agent harness stop the message before it leaves. Live demo you can run: real detectors, a real model as the victim.

Structure check pending
agent-securityai-securitydata-exfiltrationguardrails
Security & governancePlugin

faultseed

JW53222

Nine deterministic hooks that block a coding agent from weakening tests, swallowing errors, or stubbing type checks — each backed by a planted-failure test proving the guard can actually fire. Runs on Claude Code and DeepSeek Harness.

Structure check pending
agent-safetyagent-testingai-agentsclaude-code
InterfacePlugin

dsb

tianye1999

DSB (逗沙包): an open-source, trust-first Android AI agent. Delegate app chores on a background virtual display, with execution gates, a task ledger and audit logs. No root, no always-on PC. Built on DeepSeek Harness (DSH), DeepSeek by default. | 逗沙包:开源、可信优先的 Android 手机 AI 助手。后台虚拟屏代你操作 App,执行闸门、任务账本与审计日志;不用 root,不用电脑常连。基于 DSH,默认 DeepSeek。

Structure check pending
accessibility-serviceai-agentai-assistantandroid
DSH PluginsPlugin

dsh-policy

x7687315-gif

User-controlled policy and personalization runtime for DeepSeek Harness - enforce hard project constraints at the agent lifecycle boundary.

Structure check pending
agentai-agentsdeepseekdeepseek-harness
Development toolsPlugin

dsh-plugins

artemiroshnichenko

Production-ready plugins for DeepSeek Harness (DSH): remote SSH agent execution, integrated terminal & file tree, security guardrails, skills & MCP server console.

Structure check pending
ai-agentai-agentscordiscordis-plugin
DSH PluginsPlugin

dsh-guard

KouzakiUmi

DeepSeek Harness 安全插件集:文件审计与会话回滚、可配置审查模型的自动审批;两个 bundle 可独立安装,设置由宿主管理。

Structure check pending
agent-safetyai-agentapprovalaudit
Security & governancePlugin

DeepSeek Harness 插件:按 Agent preset 限制每个 Agent 可见的工具,保留全局 provider 挂载;基于 agent/created 与 ctx.tools.restrict()。

Structure check pending
agent-presetcordis-plugindsh-bundledsh-plugin
Development toolsPlugin

Phocinae command approval gate for AI harnesses (Claude Code / Cline / Codex / Crush / dsh hooks): fail-closed local decision guard

Structure check pending
agent-securitycommand-approvaldecision-makingfail-closed
Security & governancePlugin

Indirect prompt-injection guard for DeepSeek Harness: taints tool output by origin, gates privileged calls that follow untrusted content, and refuses credentials heading off the machine.

Structure check pending
agent-securityai-securitydeepseek-harnessdsh
DSH PluginsPlugin

DeepSeek Harness plugin: per-tool-call Auto-permission review powered by TypeSafe Jev, with account usage and API-key management inline on its settings page

Structure check pending
auto-reviewcode-reviewdeepseek-harnessdsh