为什么之前 Superpowers 很火，最近 Grill with Docs ？因为他们是 Agent 发展不同时期的最佳实践
Superpowers 的流程会输出详细执行计划，这意味着他假设：
1. Agent 无法执行长程任务，所以需要 Plan 的 TODO 作为 Compact 后的执行锚点
2. Agent
promptfoo/promptfoo: Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line and CI/CD integration. Used by OpenAI and Anthropic.
Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command li...
Building Effective AI Agents \ Anthropic
Discover how Anthropic approaches the development of reliable AI agents. Learn about our research on agent capabilities, safety considerations, and technical framework for building trustworthy AI.
palmier-io/palmier-pro: macOS video editor built for AI
macOS video editor built for AI. Contribute to palmier-io/palmier-pro development by creating an account on GitHub.
Hi, folks | Airing
Airing's Homepage - Software Engineer @ Singapore
datawhalechina/Agent-Learning-Hub: AI Agent 学习路线与资料库收集
AI Agent 学习路线与资料库收集. Contribute to datawhalechina/Agent-Learning-Hub development by creating an account on GitHub.
WenyuChiou/awesome-agentic-ai-zh: A trilingual (繁中 / English / 简中) learning roadmap for agentic AI: from LLM basics to multi-agent systems, with 240+ curated resources and hands-on examples. 中文 AI agent 學習地圖。
A trilingual (繁中 / English / 简中) learning roadmap for agentic AI: from LLM basics to multi-agent systems, with 240+ curated resources and hands-on examples. 中文 AI agent 學習地圖。 - WenyuChiou/awesome-a...
chaofa用代码打点酱油
做了一个播客叫做逃逸速度，平常写 Python，对 NLP，计算广告，大模型感兴趣，尝试做一些有意义的事情