Discover the toolingbehind modern intelligence
The operating system for AI infrastructure discovery. Search a live map of MCP servers, AI agents, LLM tools, automation systems, and developer infrastructure.
agent-architecture-benchmark
Empirical benchmark comparing agent architectures (single-agent, multi-agent, adaptive) on ProgramDev-v0 and CyberGym tasks. Key finding: adaptive architecture > single-agent > fixed-pipeline multi-agent.
1stars
0forks
Python
agent-frameworkfailure-modesllmmcpmulti-agentsafety
Quality signals
ActiveNo testsNo CIThin docsNo licenseNew
InstallSKILLInstall as a Claude Code skill
Universal installANY TOOL
$ npx skillcity@latest outlawresearchlabs/agent-architecture-benchmarkAuto-detects the skill or MCP server in this repo and installs it for Claude Code, Codex, Cursor, Cline, OpenCode, Gemini CLI, Anti-Gravity, OpenClaw and Hermes.
Requires Node.js 18+ (ships with npx).
Or install manually
# Install into ~/.claude/skills/ mkdir -p ~/.claude/skills/agent-architecture-benchmark curl -fsSL https://raw.githubusercontent.com/outlawresearchlabs/agent-architecture-benchmark/main/SKILL.md -o ~/.claude/skills/agent-architecture-benchmark/SKILL.md
Loading README…
Ask a simulated agent to run this skill. It loads the real SKILL.md and reasons over your task with NVIDIA.
agent-architecture-benchmark — sandboxAI sandbox
Pick a quick prompt below or type your own — watch the agent execute this skill step by step.
guest@skillcity:~$Try a prompt