deepseek-harness-brain
AgriciDaniel
把 DeepSeek Harness 架构变成可视化第二大脑,帮你快速理解、迁移和复用这套智能体框架。
luobosibing220721更新于 2 天前
给 DSH 智能体加一层「直觉」决策,自动挑选、监督并纠正 Agent 行为,还能管审批。
实用分
83 / 100
配置门槛
需要配置
协议
MIT
语言
JavaScript
复制命令,或者把整个安装任务交给你的 Harness 智能体。
git clone https://github.com/luobosibing2/dsh-jev-plugin.git请帮我安装 DeepSeek Harness 插件「dsh-jev-plugin」: - GitHub 仓库:luobosibing2/dsh-jev-plugin(https://github.com/luobosibing2/dsh-jev-plugin) - 类型:cordis 插件(装到 DSH profile) - 注意:该插件声明 DSH 版本要求 0.2.2-alpha.2,安装前请先确认我的版本是否满足。 - 注意:该插件可能需要额外配置(API Key / Token 等),装完后请告诉我如何配置…
来自项目自身文档的清洗摘录。
deepseek-harness-jev English 简体中文 中文功能与实测网站 Native DeepSeek Harness (DSH) plugin with Jev or Luna Decisions as its judgment model. deepseek-harness-jev connects DeepSeek Harness (DSH) to Jev by TypeSafe AI for agent skill and file selection, task supervision, shared-finding corrections, tool-output filtering, single-operation approval assistance, and historical stage navigation. Its 12 features are individually configurable from one Jev settings page and are all disabled by default. The main model continues to plan, generate answers, and call native tools. Enabled features use the saved Jev or Luna Decisions connection at DSH extension points for skill catalogs, agent lifecycle, tool results, and approvals, then apply results according to each feature. DSH configures the main model separately. Integration uses public Cordis / DSH plugin APIs without modifying the host source. This is an independent community project, not an official DeepSeek or Jev release.…
在 GitHub 打开来自同一生态方向的相似工具。
AgriciDaniel
把 DeepSeek Harness 架构变成可视化第二大脑,帮你快速理解、迁移和复用这套智能体框架。
yangdcm
把多个 AI 专家智能体组队干活,自动分工协作完成编码和复杂任务。
TGYD-helige
为 DeepSeek Harness 提供通用插件,支持 A2A 协议互联、会话存储镜像和 Langfuse 可观测性,无需改动核心。