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。

A new way for AI to search for data

View on GitHub

2GitHub stars

34commits on main

0forks

v0.1.6latest release, 2026-10-31

JavaScript 78.5%, TypeScript 15.9%, Python 5.6% · created 2026-10-18 · last push 2026-10-31

What XERJ indexed

Snapshot

43 files · 196.9 KB

The whole repository at commit 51918dc9b8 (2026-10-23). main is 7 commits ahead.

Selected work

记得开心一点
@jidekaixin2dian

“backup retention, audit log, session-override switch, tighter mc…”. 8 files, 197 lines in lib, test, host-tests.

Licence

The repository

MIT

LICENSE file checked at the pinned commit; the author agreed to inclusion.

The XERJ corpus

MIT, with credit

The author agreed by email on 2026-10-25. Same terms as the repository. Answers name the repo, the commit and the file:line.

selected for the XERJ Corpus Hublicence clearedsuggested use: adapt with attribution

deepseek-harnessdsh-pluginmcpcontext-managementmcp-managerskills-managerdsh-toolgatedsh

Example questions

How does dsh-toolgate implement deepseek-harness?
What does host-tests do in dsh-toolgate?
Show the dsh-plugin code in dsh-toolgate.

Inside the indexed corpus

43 files, 196.9 KB in total, about 4.6 KB per file.
The selected commit changed 8 of those files (18.6%).
Languages by size: JavaScript 78.5%, TypeScript 15.9%, Python 5.6%.
On GitHub since 2026-10-18, last push 2026-10-31, 34 commits on main.
The pin is 7 commits behind main; the corpus answers from the pinned code, not the newest.

Licence on GitHub and in the corpus

GitHub reported MIT for jidekaixin2dian/dsh-toolgate on 2026-10-31, and the LICENSE file at commit 51918dc9b8 was reviewed as MIT. They match, so answers from this corpus carry the same terms as the live repository.

Contributors

记得开心一点 (@jidekaixin2dian) has 1 selected repository on the hub.

Using XERJ with dsh-toolgate

Code search MCP for Claude Code: cite file:line, not grep dsh-toolgate is tagged mcp on GitHub.
What is an MCP memory server?
RAG without a vector database: one hybrid index The hub files it under AI, prompts and agents.
Ask questions about a GitHub repo without cloning it

The prompt

Paste it into your AI agent. It clones jidekaixin2dian/dsh-toolgate at the pinned commit and indexes it on your machine.

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.

记得开心一点 AI, prompts and agents corpora dunorth595--ai-agent-memory 12-factor-agents vanguard-context-burn cfanzx/dsh-compact-relay pearjelly/deep-blend xcisxc29/dsh-qq-plugin

Stats: GitHub API, fetched 2026-10-31. Snapshot: the git tree at the pinned commit. Selected work and consent: the XERJ registry.