Computer Use 主流方案与工具调研
🖥️ Computer Use 主流方案与工具调研（2026-11） [!summary] 一句话结论 Computer Use 已经分成四层：模型层（Claude / GPT / Gemini / UI-TARS / Fara / Qwen-CUA）、Agent Harness 层（Cowork / Agent TARS / Agent S / Browser Use）、环境层（E2B / O…
Topic
#Agent
13 篇笔记
A harness for every task: dynamic workflows in Claude Code
Last week, we released dynamic workflows in Claude Code. Claude can now write its own harness on the fly, custom-built for the task at hand....
容器沙盒方案深度对比
容器沙盒方案深度对比 定位概览：以下 7 个项目都围绕"为 AI Agent / 不可信代码提供安全隔离的执行环境"这一核心需求，但技术路线、成熟度、适用场景差异极大。 ---|--------|------|---------|---------|----------| | #OpenSandbox | 阿里巴巴 | Python / Go / 多语言 SDK | 10.4k | Apache…
罗福莉访谈里那几句关于 memory 的话，被几乎所有人忽略了
张小珺前几天发了一期跟罗福莉的长访谈，三个半小时。小宇宙，YouTube，B 站都有，外面已经有很多解读。大家讨论得最多的是 OpenClaw 怎么改变了她的世界观，1T 是不是入场券，组织平权怎么搞，3:1:1 的卡分配比例。听了以后，挑出来想单独写一篇的，是这期里被低估最严重...
Scaling Managed Agents: Decoupling the brain from the hands
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
State of Memory in Agent Harness
Agent harnesses are where AI software actually runs. Cursor, Devin, Claude Code, Codex: these environments handle context, orchestrate tools...
Effective harnesses for long-running agents
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
How we build evals for Deep Agents
LangChain 团队分享 Deep Agents 的评估方法论：如何设计、分类和运行 Agent 能力评估
使用 pi 打造属于你自己的 Coding CLI
当前主流的 AI 编程 CLI 工具，工程复杂度已经远超必要。 最基础的交互无非是发送 prompt、获取回答，但层层封装的 harness 架构把这些工具变成了吞金巨兽。发一句 hi 就消耗掉当天 10% 的模型配额；MCP 服务器空挂着不做事，常驻占用 15% 左右的上下文窗口；Plan Mode、Subagents 本质上只是上下文管理的技巧。 为了让 AI 辅助编程，你真的需要这些吗？ �…
Lessons from Building Claude Code: How We Use Skills
Creator of Kaku · Mole · Pake · MiaoYan
The Anatomy of an Agent Harness
TLDR: Agent = Model + Harness. Harness engineering is how we build systems around models to turn them into work engines. The model contains the intelligence and the harness makes that intelligence use…
How to design Experiments to evaluate your Agentic Systems
Our forefathers and foremothers laid down the script for improving any system: (1) Build, (2) Evaluate, (3) Refine. Step 1 is trivial now thanks to coding agents. Step 3 is also simple too once you fi…
everything is a ralph loop
I’ve been thinking about how I build software is so very very different how I used to do it three years ago.No, I’m not talking about acceleration through usage of AI but instead at a more fundamental level of approach, techniques and best practices.Standard software practices