深度研究了下 DeepSeek Harness 的开发经验和演进，有很多技巧值得Infra的项目学习。
This is a vibe coding post classified by AGK Intelligence as Agent infra & costs (a workflow), kept by the Vibe Coding Radar because it carries real work, not commentary.
深度研究了下 DeepSeek Harness 的开发经验和演进，有很多技巧值得Infra的项目学习。 在调研Raft里支持dsh，对agent的调研了下，于是做了一些手工的挑选和打磨来分享下 让A经特总结了好多个工程经验，里面很值得学习的几个点 ●AI Agent 作为一等公民，开发过程重度依赖 Git Worktree 并行并发；沉淀的 2,692 篇 .agents/notes 成为 Agent 的永久记忆。 ●实验先行+验证后收编：新特性均先以 experimental-* 插件存在，经多轮迭代成熟后才收编为内置能力。这里面很有趣的一点是系统还做了功能外拆，0.2.0的时候，自动化任务从内置包降级为插件包， 架构精髓： ●插件三大支柱：Service 注入、Typed Events（强类型事件通信）、Reversible Effects（插件卸载时生命周期与注册项自动撤销回滚）。这里面有很多关于 编程语言 相关的设计与理论，非常有学习价值， @pocket_js 我记得也有很多类似相关的设计。 ●Seam / Implementation 双层解耦，可以降低复杂度和方便项目维护：任何能力均拆解为 抽象（Seam） 与 实现（Implementation）。例如 dsh-fs（抽象）对应 fs-local 与 fs-sandbox。换实现无需改动任何调用方。 ●Profi
Posted by 卡比卡比 (25.7k followers) 1 days ago · 197 likes · 12.5k views · view the original post on X. Kept by the Vibe Coding Radar as Agent infra & costs.
More vibe coding work like this
- If you want to learn how to build self-improving harnesses, check out this paper. — @dair_ai
- Build an agent on @onkeiki to answer your customers while you sleep. — @orchid_hq
- how do you stop 20+ agents from colliding on the same client work? — @webjuice_ie
- Brilliant paper on optimizing agent environments. — @dair_ai
- Docker is one box. The coding agent can run in others, and switching is one line 🧰 — @marcelotryle
- Holy f*cking sh*t... everyone upgrades Claude and nobody builds the harness — @gippp69
- 1/9 — @TollyLabs
- As AI coding agents get more capable, knowing what they're doing becomes just as… — @EntelligenceAI
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 7.9k posts from 5k X accounts over the last 14 days, 2.6k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 16:07 UTC. Full method.