Search

🛡️ Autonomous Offensive AI Framework & Cognitive Multi-Agent Swarm for Red Teams & Penetration Testers. Polyglot Engine (C++20 SIMD, Rust Tokio, Go Prober, Python Swarm) with Zero False-Positive Proof Capsules & MCP Server.

News & monitoring skill set — build source-cited news digests (news-digest) and run lightweight delta watches (news-monitor) on any topic, with goap-research-ed25519 bundled as a MANDATORY verified-research backend (GOAP planning + ed25519-signed source p

Agentic AI research papers, benchmarks, frameworks, and tools curated across 24 domains.

TypeScript SDK for AI agents to access LivePort tunnels

AI-Haklab: Agente de automatización para Pentest en Termux. Basado en i-Haklab v3.11, optimiza flujos de seguridad, escaneo de vulnerabilidades y ejecución de exploits.

n8n community node for Radware Agentic AI Protection in-path enforcement

An experimental agentic overlay for Zelda: Breath of the Wild, combining screenshots, speech, persistent campaign memory, and a comprehensive knowledge base to spot overlooked details, explain the world, and provide context-aware guidance as you play.

A daily-driver AI agent runtime built solo: multi-process isolation pods (MCP/LSP/workflow), event-sourced task ledger, proactive scheduling, and multi-channel delivery.

OceanBus AI Agent Communication & Trust Infrastructure SDK

Scoped, time-bound, cryptographically-signed capabilities for AI agents. Zero dependencies. Sovereign by design.

A guardrail for LLM-generated Cypher, built for Neo4j.

The pre-trade safety net your LangChain agent didn't know it needed. Live sell simulation across every DEX on Base (Uniswap V2/V3/V4, Aerodrome), catching traps a static scan will never see. x402-powered.

Code and data for "Et Tu, Brute? Economic Misalignment in Personal AI Agents," reproduces the paper's finding that personal AI agents quote higher prices to users they infer are wealthy, even when asked for the cheapest option.

Universal execution authorization guard (PEP boundary) for OxDeAI

Official TypeScript SDK for Scopebound — runtime authorization and pre-execution scope enforcement for AI agent workflows.

A live, versioned registry of the agent-harness ecosystem — runtimes, orchestration, tools, sandboxes, memory, evals, governance and protocols. Discovered from GitHub, enriched from real manifests, classified into layers, and committed on a schedule.

AI safety toolkit with CLAW protocol for LLMs, AI agents, and humanoid robots - EU AI Act compliance and practical alignment for developers

🤖 Explore essential AI tools for building, automating, and monetizing projects across content, video, e-commerce, and more.

Tailrace wrappers for OpenAI Agents SDK function tools.

Core of the AgiMate agent platform: per-agent access to connectors and tools, credentials that never reach the model, every call checked before it leaves and logged after