dsh
DeepSeek Harness (dsh) bundle: route the harness through OpenLLM (OpenAI-compatible) + register the OpenLLM MCP, with CLI/daemon onboarding.
DeepSeek Harness (dsh) 捆绑包:通过 OpenLLM(兼容 OpenAI)路由 harness + 注册 OpenLLM MCP,附带 CLI/守护进程引导。
How to install
dsh plugin add github:openllmsh/dsh About
--- A DeepSeek Harness (dsh) bundle that points the harness at the OpenLLM gateway and hands it OpenLLM's MCP tools. It is a **pure-config Cordis patch layer** — installed from the dsh side, no runtime code — and it does two things: **LLM router** — adds an openllm provider to dsh's in-box llm-pi-ai adapter (openai-completions) pointed at the daemon's **local-first gateway** (http://127.0.0.1:8787/v1) and makes it the default model. No adapter code, and **no API key**: that loopback surface has no auth gate; the daemon fetches signed plans with its own ~/.openllm/.env credentials and forwards …
Recommendation signals
Meta
- License
- MIT
- Language
- TypeScript
- GitHub stars
- 1
- mo. downloads
- –
- Last push
- 2026-08-28
- Created
- 2026-08-24
Links
Basic safety check
- Findings
- curated 收录但无 npm 包/安装命令
- Sources
- curated:0xsline/awesome-deepseek-harness
- Topics
- ai-gateway, cordis, deepseek-harness, dsh, dsh-plugin, llm, mcp, model-context-protocol, openai-compatible, openllm, plugin
Related plugins
hindsight
vectorize-io/hindsight/tree/main/hindsight-integrations/coding-agents
Hindsight, agent memory that learns: long-term project memory with auto recall and retain, knowledge pages, deep reflection, and per-repo memory banks.
firecrawl-mcp-server
firecrawl/firecrawl-mcp-server
🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.
dsh-mnemon
omdsh-dev/dsh-mnemon
Cross-agent, local-first persistent memory plugin for DeepSeek Harness (DSH), powered by Mnemon. It shares long-term memory across Mnemon-enabled agents and adds runtime memory, searchable project documents, semantic recall, knowledge graph, and a Sidebar UI.
get-shit-done
gsd-build/get-shit-done
A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code by TÂCHES.