Search

A security-first agent platform — Models Propose, Records Decide. 17 deterministic constraints gate every LLM proposal before it becomes state.

AEBA cybersecurity distribution -- Agent Event Behaviour Analytics for security teams running agent fleets. Anomaly detection + signed audit + L0-L4 trust.

OpenCode plugin for MegaRouter cloud agents — auto-discovers and registers specialist AI agents (code review, security audit, debugging, etc.) as native subagents

Agent orchestration & security template featuring MCP tool building, agent2agent workflows, mechanistic interpretability on sleeper agents, and agent integration via CLI wrappers

Memory-centric self-improving harness for AI agents. Six-phase cycle + Security by Absence. ADRs, JSON schemas, and a dependency-free Python reference.

Your AI Chief of Staff — Personal Assistant framework for Claude Code. Email, semantic memory, task management, content security. Works standalone or on AI Maestro.

Autonomous production readiness and audit system — 18 expert AI agents, 4-judge quality council, 100% file-line traceability for security, compliance, and release gates

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.

Agentic AI Security & Multi Agent Management: Agent Agnostic Platform. Offers Protection against Prompt Injection via Granular Action Scope & Cryptographically Protected Instruction Channel

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.

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.

⚡ Self-hosted AI agent framework — sandboxed plug-and-play WASM agents, a live code security radar (Threat Radar), Telegram-native bots & crypto/finance tooling. Single Go binary. Pair with Flowork Router for the full LLM gateway.

Autonomous self-learning agent plugin for Claude Code — 36 specialized subagents in a 4-tier architecture (analysis, planning, execution, validation), 27 skills, 41 slash commands across 10 categories. Pattern learning, real-time dashboard, full-stack validation, OWASP security. 100% local processing, privacy-first, cross-platform.

Agentic Kubernetes security scanner powered by an LLM

AgenticDome zero-trust security firewall plugin for OpenClaw

GPU-accelerated FHE security layer for any LLM agent — any NVIDIA GPU

Security layer for AI coding agents, command routing, scanner integration, and policy enforcement

Scan AI artifacts like agent skills and config files for security risks, privacy issues, and instruction-level attacks with a Python CLI tool.

Runtime security for AI agent sandboxes. Drop-in protection against prompt injection, secret exfiltration, and sandbox escape — works with [Vercel](https://vercel.com/sandbox), [E2B](https://e2b.dev/), [Daytona](https://www.daytona.io/), [Cloudflare Conta

LlamaIndex integration for the Chio protocol -- capability-scoped FunctionTool and QueryEngineTool with vector-collection scoping