Battle Tested Agent

Battle-tested architecture patterns for OpenClaw agents. Covers WAL protocol (write-ahead logging for context safety), working buffer (survive context compac...

Benchmark your OpenClaw agent across 40 real-world tasks. Tests file creation, research, data analysis, multi-step workflows, memory, error handling, and too...

一键创建完整配置的 OpenClaw agent，包括身份定义、团队集成、模型与通信渠道设置，支持交互和命令行模式。

Run PinchBench benchmarks to evaluate OpenClaw agent performance across real-world tasks. Use when testing model capabilities, comparing models, submitting b...

Multi-agent orchestration patterns for OpenClaw. Quick reference for spawning sub-agents, parallel work, and basic coordination. Use when: simple parallel ta...

Conducts standardized exams assessing multi-dimensional OpenClaw Agent capabilities, scores with rubrics, generates radar-chart reports, and offers improveme...