Enables agents and applications to detect, inspect, and neutralize prompt injection, jailbreak attempts, and hidden instruction escapes in untrusted text before it is passed into prompts.

Enables AI assistants to raise, submit, approve, amend, and cancel purchase orders and onboard suppliers in ERPNext or SAP S/4HANA while enforcing procurement controls such as duplicate detection, budget limits, split-purchase checks, price tolerances, and segregation of duties.

Enables clients to look up failure modes and corresponding procedures, search and retrieve entries, and build prompts or reviews through structured tools over stdio JSON-RPC.

Find and redact leaked secrets, wallet keys and PII before an AI agent sends text.

Check an email before your AI agent sends it: allow, review or block with reasons.

白箱AGI架构探索：元认知（自我认知循环）、持续学习（知识飞轮）、世界模型（条件空间+语义时空图）、自我改进（自举纪律）、零LLM白箱管线与可审计信任护栏。

Keeps coding agents on your design system: catches palette colors, native elements and APIs your system lacks, at every edit and pull request, with the fix. Set it up once in your design-system package; every app in your monorepo gets it.

Unofficial skill that teaches coding agents to build with TypeSafe AI's Jev: typed decisions, calibrated confidence, and prior art from 150+ community projects.

jevmem saves the decisions, rules and failed approaches from your Claude Code chats to JEVMEM.md in your repo, and brings the relevant ones back next session.

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.

Tu equipo de desarrolladores en un plugin. 10 agentes, 11 skills planas, 18 comandos /alfred-dev:*. Memoria persistente, quality gates con evidencia y MCP local.

Delivery quality gate for DeepSeek Harness: grill the requirements, test the implementation, prove the delivery, and gate the handoff with a deliverable/rework decision.

Access gate for AI coding harnesses (DSH plugin + Claude Code hook): per-directory deny/read/full, roster groups, audit log, model-facing tools with owner-approved widening.

Gives DeepSeek Harness three automatic Jev judgments — prune oversized tool output, screen fetched pages for injected instructions, suggest which skill to use — plus the jev_ask and jev_gate tools, a persistent judgment ledger, and a /jev-status diagnosis

When Claude says “tests pass”, makoto checks the record — every claim held against the agent's own logged deeds; fakes blocked, not warned. Each check ships at measured zero false positives. 誠

The deterministic agent-integrity gate. One ruleset, evaluated on the actual diff/commands as a verdict, enforced everywhere a change can be made.

An AI-enabled NAT Router/Firewall for the ESP32

🛡️ Security audit CLI for Model Context Protocol (MCP) servers — scan AI agent configs for tool poisoning, rug pulls, hardcoded secrets, command injection & supply-chain risks. Pure Python, SARIF + CI ready.

6,000+ Claude Code mods, with what each one can access before you install it. Context and usage meters, prompt cache warmers, status lines, guards and more, with install hints.

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」 after non-human interruptions, with error classification, adaptive backoff, pause, idempotency/loop guards, resume templates, and stats—all configurable in settings UI | DSH 前端 UI 插件：非人为中断后自动发送「继续」，支持错误分类、自适应退避、暂停、幂等/循环保护、续跑模板与统计，均可在设置界面配置

High-frequency in-browser behavior tree execution engine for autonomous AI agents — 60Hz tick loops, reactive triggers, telemetry recordings, and safety guardrails.

MCP server for Adobe Premiere Pro with 441 core AI video editing tools, a guarded After Effects MOGRT studio, and a capability-aware UXP bridge for supported Premiere workflows.

Claude Code mods: panes, bands, prompt guards, secret handling and memory tools