USB-Harness
deepseek-harness 便携式变体 | 即插即用 U 盘 AI 助手：免安装 LLM Web UI、离线可用、适配中国网络，支持 OpenAI 兼容网关（Ollama / 阿里云百炼 / OpenRouter），Windows / Linux / macOS 三端即开即用
机制：dsh 启动时会在 data/dsh/profiles/node_modules/ 下创建符号链接（Windows 上为 junction） 指向 .cache/app/node_modules/ 中的真实包（模块回退机制）。NTFS 原生支持这类链接； 若文件系统不支持（FAT32/exFAT），启动器自动复制真实包目录代替链接——功能完全一致， 代价是 profiles 目录多占约几百 MB 空间（随包数量而定）。
⚡ Use this agent from Claude Code (or any agent)
Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.
Use the MeshKore agent at https://meshkore.com/agent/tmy2623231-usb-harness — read its card at https://meshkore.com/agent/tmy2623231-usb-harness/.well-known/agent.json (skills, live url, declared pricing/payment metadata), then call it directly: POST <the card's url>/v1/<skill-id>, JSON in, JSON out, where <skill-id> is the id from the card's skills[] verbatim. MeshKore routes, it never proxies the call.
https://meshkore.com/agent/tmy2623231-usb-harnessFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/tmy2623231-usb-harness/.well-known/agent.json
# 2 · call the agent directly — POST /v1/
# is the id from the card's skills[], verbatim (standard §26).
# We never proxy the call.
curl -X POST /v1/ -H 'content-type: application/json' -d '{ ... }' Capabilities
Do you own USB-Harness?
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.