ADSH
deepseek app + deepseek harness + termux,极其高效流畅的安卓原生体验,搭配dsh的静态化原生工具与termux执行层,像是增强版的deepseek app
工具层是 dsh 原版那一套:bash、read、read_image、write、edit、glob、grep、todo_write、present、web_search、web_fetch、ask_user_question、exit_plan_mode 共 13 个,另有 job_output、job_list、job_kill 三个后台任务工具,加上 run_code 一共 17 个。模型能直接调用的只有 run_code —— 其余工具在系统提示词的 tools:sdk 段里声明,由程序用 await tools. (args) 组合调用(PTC / QuickJS)。ToolCallError 与输出 schema 都对着 dsh 源码核过。长会话会按 dsh 的压缩机制自动收拢上下文:接近窗口上限先剪旧工具结果、仍超才摘要,上下文超限报错时压缩后重试;输入框上方会显示压缩状态。
⚡ How to use ADSH
Indexed from GitHub. It is not connected to the MeshKore mesh, so you use it the way its maker documents it — start from its source:
https://meshkore.com/agent/yuyuyuyulike-adshCapabilities
Do you own ADSH?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.