Cairn implements state-space search via a minimal blackboard architecture with stateless OODA loop workers. It scored perfectly at the Tencent AI Penetration Testing Challenge.
red-run orchestrates Claude Code AI agent teams across the full pentest kill chain using persistent teammates and semantic routing. Explore its architecture, strengths, and quickstart.
OpenClaw Agents deploys paired AI agents using shell scripts for adversarial collaboration in OpenClaw gateway, supporting multi-channel or local workflows with safe config merges.
A deep dive into Claude Code’s 512K lines of TypeScript reveals a layered YOLO safety classifier, multi-agent IPC, and terminal UI rendering—key to Anthropic’s AI production system.
KohakuTerrarium offers a Python framework to build modular AI agents using a unique algebra for composing multi-agent pipelines, with session persistence and multi-runtime support.
A curated list catalogs 80+ AI coding agent orchestration tools, revealing a fragmented ecosystem around git worktree isolation, parallel execution, and multi-agent coordination.
Station is an open-source Go runtime that orchestrates multi-agent AI systems on self-hosted infrastructure using a Git-backed workflow and MCP stdio bridging. It supports 41 AI tools and multiple AI providers.
LobeHub offers a TypeScript-based AI agent platform with a unique MCP plugin system for integrating 10,000+ skills and collaborative multi-agent workflows. Explore its architecture and developer experience.
Agno provides a minimal, production-ready Python framework for scalable agentic software with per-user isolation and native tracing in ~20 lines of code.
