记得开心一点

What an agent can do with the dsh-toolgate corpus

jidekaixin2dian/dsh-toolgate: DeepSeek Harness（DSH）插件：管理 MCP 服务器与 Skills，按组控制工具可见性和上下文预算。

• Look up how dsh-toolgate implements deepseek-harness, dsh-plugin, mcp, with answers cited to file and line.
• Reuse a worked example: the commit “backup retention, audit log, session-override switch, tighter mc…” (8 files · JavaScript, TypeScript).
• Answer from dsh-toolgate's real JavaScript source instead of memory (AI, prompts and agents).

• How does dsh-toolgate implement deepseek-harness?
• What does lib do in dsh-toolgate?

Search the GitHub repository jidekaixin2dian/dsh-toolgate with XERJ (https://hub.xerj.org/corpus/jidekaixin2dian--dsh-toolgate).
Run these in a shell, in order, and check each result before the next:
1. xerj --help  (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh
2. git clone https://github.com/jidekaixin2dian/dsh-toolgate dsh-toolgate && git -C dsh-toolgate checkout 51918dc9b8d9f7ee3e3f8546437febf01c43ffa8
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./dsh-toolgate --url http://127.0.0.1:9200 --prefix dsh-toolgate --progress plain
5. xerj autoindex map --url http://127.0.0.1:9200
Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt
Licence: MIT. Keep the copyright notice and credit the authors.

corpus jidekaixin2dian--dsh-toolgate · AI, prompts and agents
Related corpora: dunorth595--ai-agent-memory, 12-factor-agents, cfanzx/dsh-compact-relay, pearjelly/deep-blend
AI search and retrieval with XERJ · Case study: reference coding for agents