Install safety net for DeepSeek Harness: pre-install snapshots, one-click/automatic rollback, guarded boot, and incident reports that auto-trigger agent analysis. 中文: DeepSeek Harness 插件安装安全网（安装前自动快照、一键/自动回退、守护启动、事故报告自动触发 Agent 分析）。

Real-time cost tracking and budget management for Claude Code. Zero setup. No Docker. No Grafana. Just install and go.

Hard gate for self-modification restarts: a green-build credential bound to the git HEAD, checked before any restart of the running instance

Real-time secret-leak guardrails for AI coding agents (Claude Code, Codex), Git hooks, and CI.

An AI coding agent guardrail — a CLI hook that blocks destructive git and filesystem commands and secret file access before they execute. Supports Amp Code, Antigravity CLI, Claude Code, Codex, Copilot CLI, Cursor, Gemini CLI, Hermes Agent, Kimi Code, OpenClaw, OpenCode, and Pi.

TDD enforcement and guardrails for Claude Code, Codex, and GitHub Copilot CLI.

Action guardrails for AI coding agents — native Claude Code enforcement, MCP integrations, and Git/CI checks.

Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.

Quality gate for AI/Codex-generated pull requests: blocks TODO leftovers, leaked secrets, sloppy commits and red CI before they reach main.

Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.

Vendor-neutral control-plane contract for coding agents: a normalized ToolCallEvent/Verdict schema with per-agent adapters (Claude Code, Codex, Amp, Gemini CLI) and a conformance suite.

自动隔离损坏插件，让 DSH 在坏插件面前照常启动：坏插件被禁用、其余插件正常装配，提供隔离管理与一键恢复 UI（deepseek-harness plugin that quarantines broken plugins so the service keeps booting, with status tools, a one-click restore panel and auto patch adaptation）

The adaptive AI harness for React Native — project-aware SDLC intelligence for any agent

Compatibility package for Correctover runtime security. The legacy standalone MCP server has been replaced by correctover-mcp-gateway; the runtime SDK is available as correctover.

Lightweight Agent Detection & Response (ADR) layer for AI agents — guards commands, files, and web requests. Part of Gen Agent Trust Hub.

DSH Web UI plugin: auto-sends 「继续」 to resume requests interrupted by non-human causes — error classification, adaptive backoff, pause, idempotency guard, loop guard, templated resume texts, stats, all configurable from the settings card

"ULTRASHIP" Claude Code plugin — 39 skills, 33 tools, 11 agents for ship-ready workflows: planning, review, pentesting, safety guardrails, canary monitoring, SEO/AI-readiness check, penetration testing, code review, competitive analysis, incident response. 1 dependency. 180 tests. MIT.

Claude Code usage governor: compact professional output, context slimming, tool-output filtering, telemetry, and drift guardrails.

DeepSec — AI Security Offense & Defense Platform. Shield audits AI-generated code for hallucinated packages, missing safeguards & AI pattern errors in real time. Spear automates authorized penetration testing with 40+ skill packs, from recon to PoC.

Control what your AI can see. LeanCTX (Lean Context) is the context intelligence layer for AI agents — one local Rust binary that decides what they read, remembers what they learn, guards what they touch, and proves what they save. 60–90% fewer tokens as the receipt. 76 MCP tools, 30+ agents, local-first.

The agentic harness for AI coding agents — work cycles, bounded RAG context, persistent memory, guardrails, and performance evals.

Deterministic, local-first memory and guardrails for AI coding agents with no LLM in the hot path.

Safety-first context & orchestration engine for AI coding agents. MCP server with mandatory research pipeline, knowledge graph, impact analysis, decision memory, and safety guard — works with any MCP client.

Enterprise AI Platform with guardrails, MCP registry, gateway & orchestrator