Search
snowhypers
Open-source AI agent CLI with native MCP support, Human-in-the-Loop approval, 5-layer security guardrails, and optional Docker sandboxing.
...more23blocks-OS
Your AI Chief of Staff — Personal Assistant framework for Claude Code. Email, semantic memory, task management, content security. Works standalone or on AI Maestro.
...moreMuhammadNoman2
Secure AI agent platform: FastAPI + LangGraph with authenticated, tenant-isolated, policy-governed tool use, human approvals and a tamper-evident audit log.
...moreproofxhq
AEBA cybersecurity distribution -- Agent Event Behaviour Analytics for security teams running agent fleets. Anomaly detection + signed audit + L0-L4 trust.
...moreAndrewAltimit
Agent orchestration & security template featuring MCP tool building, agent2agent workflows, mechanistic interpretability on sleeper agents, and agent integration via CLI wrappers
...moreprinceixr
AgentGuard is the open-source security layer for Google ADK agents, blocking risky MCP actions, routing sensitive calls for approval, and delivering enterprise auditability.
...moreshimo4228
Memory-centric self-improving harness for AI agents. Six-phase cycle + Security by Absence. ADRs, JSON schemas, and a dependency-free Python reference.
...morekiyoaki
OpenCode plugin for MegaRouter cloud agents — auto-discovers and registers specialist AI agents (code review, security audit, debugging, etc.) as native subagents
...moreziyulisiyuan
CSPRNG-backed random tools for DSH (DeepSeek Harness) agents: range-bound numbers, custom-alphabet strings, secure bytes, UUID v4, unbiased shuffle.
...morehidemi-k
Autonomous network security and operations framework — eBPF/XDP enforcement, NETCONF×RAG config management, and multi-layer fault diagnosis, all orchestrated by Microsoft Agent Framework rc5.
...moreTikyParkinson
Security & governance guardrails for MCP agents in Java — audit trail, agent-to-tool authorization, prompt-injection detection and rate limiting as a zero-config Spring Boot starter.
...morecmtopbas
Agentic AI Security & Multi Agent Management: Agent Agnostic Platform. Offers Protection against Prompt Injection via Granular Action Scope & Cryptographically Protected Instruction Channel
...morecyber-albsecop
A curated directory of open-source AI repositories for agents, LLM apps, coding assistants, MCP servers, RAG, generative AI, automation, developer tools, research, and AI security.
...morealok-vibe-code
A practical 12-week Agentic AI learning roadmap covering LLM foundations, tool calling, RAG, memory, MCP, multi-agent systems, evaluation, security, and production deployment.
...more352moose
A self-organizing AI workspace, model agnostic, all in plain markdown. Turn-based and semi-autonomous — quality output over loops or sandboxes. Security-first build practices by a house coding agent pair.
...moreArchieIndian
44 plug-and-play skills for OpenClaw — self-modifying AI agent with cron scheduling, security guardrails, persistent memory, knowledge graphs, and MCP health monitoring. Your agent teaches itself new behaviors during conversation.
...moreYouranalyst-coder
AI-powered security scanner & auto-fixer built on GitAgent SDK. Multi-agent pipeline (Scanner -> Fixer) with custom tools, hooks, skills, and live SSE streaming. Built for the Lzyr Builder Challenge.
...moreThink-Define-Create
Crash-safe AI agents in Swift: an event-sourced durable execution kernel for iPhone, Mac and Linux. Typed side effects, approvals that survive restarts, Secure Enclave encryption, Apple Foundation Models and MCP.
...more13717930620-alt
HyperAgent (v5.2.0): Open-source AI agent framework skeleton. Built by a Chinese lawyer who cannot code. Seeking genius ideas on Fully Intrinsic AI, Auto-Evolution, Anti-Hallucination, and Security. GPL v3.
...moreagenticstore
AgenticStore: The secure toolkit for AI agents. Instantly equip Claude Desktop, Cursor, and Windsurf with 75+ MCP tools, persistent memory, and SearXNG search, all protected by a built-in PII prompt firewall to protect your data from being exposed to AI agents.
...more