Apache-2.0 的 AI Agent 統一虛擬檔案系統，把約 50 個服務掛載成一棵 bash 友善的目錄樹，可透過原生轉接器、外掛、MCP 或 FUSE 接入 DeepSeek Harness。
DSH 整合
相容
作者聲明
安全稽核
未稽核
最後核實
2026-08-21
授權條款
Apache-2.0
01它能幫你完成什麼？
Give DeepSeek Harness bash-level access to S3, Google Drive, Slack, Gmail, Redis and ~50 more services as one virtual filesystem
A single mounted workspace where read, grep and pipe commands sweep every backend out of the box, with zero new vocabulary
Developers running DeepSeek Harness (dsh) who want their agent to query real cloud and SaaS data without wiring up separate SDKs or MCP servers
Compose cross-service pipelines and keep agent runs portable on DeepSeek Harness
bash pipelines that span backends (e.g. run a script stored in Slack and file the report into Redis), plus clone / snapshot / version of portable workspaces that move between machines
Teams building agent workflows on DeepSeek Harness that need reproducible, portable workspaces across services
02如何將外掛接入 DeepSeek Harness？
先決條件
- Python ≥ 3.11 for the `mirage-ai` package and the `mirage` CLI
- Node.js ≥ 20 for the TypeScript SDK
- macOS or Linux (FUSE-based mounts require platform support)
安裝步驟
- 01
Python: run `uv add mirage-ai` — installs the `mirage` library and the `mirage` CLI binary
- 02
TypeScript: run `npm install @struktoai/mirage-node` (Node.js servers and CLIs), `npm install @struktoai/mirage-browser` (browser / edge runtimes), and optionally `npm install @struktoai/mirage-agents` (OpenAI / Vercel AI / LangChain / Mastra adapters)
$ npm install @struktoai/mirage-node
- 03
CLI: run `curl -fsSL https://strukto.ai/mirage/install.sh | sh`, or `npm install -g @struktoai/mirage-cli`, or `uvx mirage-ai`, or `npx @struktoai/mirage-cli`
$ curl -fsSL https://strukto.ai/mirage/install.sh | sh
驗證整合成功
作者未說明
03DSH 整合程度與能力邊界
Used inside DeepSeek Harness as a coding-agent tool layer via native adapter, installable plugin, MCP, or FUSE mount
Unified virtual filesystem with ~50 built-in backends
S3 / R2 / GCS / Supabase, Gmail / GDrive / GDocs / GSheets / GSlides, GitHub / Linear / Notion / Trello, Slack / Discord / Email, MongoDB / Postgres / LanceDB / Qdrant, Redis, SSH, RAM, Disk→one filesystem tree under a single root, readable with standard bash semantics (read, grep, pipe)
reads and writes are executed against the mounted remote services using your own credentials/tokensPortable workspaces (clone / snapshot / version)
a configured Mirage workspace→snapshot archives (e.g. demo.tar) that can be loaded on another machine to restore the workspace
snapshot files are written to diskTwo-layer cache for remote backends
repeated reads against remote backends→index cache (listings/metadata, default TTL 10 minutes) and file cache (object bytes, default 512 MB) served from local state
cache state is held in-process RAM by default; an optional Redis store shares cache state across workers, processes, and machinesEmbeddable Python and TypeScript SDKs
a Python ≥ 3.11 or Node.js ≥ 20 application→workspaces running in-process inside FastAPI, Express, browser apps, or any async runtime — no separate process required
04適合誰？何時不該用？
適合
- Developers running DeepSeek Harness (dsh) who want their agent to query real cloud and SaaS data without wiring up separate SDKs or MCP servers
- Teams building agent workflows on DeepSeek Harness that need reproducible, portable workspaces across services
不適合
- Mirage targets macOS or Linux; FUSE-based mounts additionally require platform support, so FUSE mounting is not guaranteed on every machine.
- Mounted remote backends (Slack, S3, Gmail, Redis, ...) are reached over the network with your own credentials — e.g. a Slack bot token is passed in the resource config — so writes can mutate the underlying services.
05相容性、維護與安全提醒
- Mirage targets macOS or Linux; FUSE-based mounts additionally require platform support, so FUSE mounting is not guaranteed on every machine.
- The Python SDK and CLI require Python ≥ 3.11, and the TypeScript SDK requires Node.js ≥ 20 — older runtimes cannot run Mirage.
- Mounted remote backends (Slack, S3, Gmail, Redis, ...) are reached over the network with your own credentials — e.g. a Slack bot token is passed in the resource config — so writes can mutate the underlying services.
Apache-2.0 · actively maintained (latest release v0.0.5, 2026-08-15)
06常見問題
Mirage 如何接入 DeepSeek Harness？
DeepSeek Harness 被列在 Mirage 官方的程式碼撰寫代理整合表中，可透過原生轉接器、可安裝外掛、MCP 或 FUSE 掛載接入；Mirage 文件中還有專門的 DeepSeek Harness 快速上手頁（docs.mirage.strukto.ai/typescript/agents/dsh）。
是原生整合還是走 MCP？
兩條路都有：程式碼撰寫代理可以透過原生轉接器和可安裝外掛接入，也可以走 MCP 或 FUSE，依你在 DeepSeek Harness 中的工作流程選擇即可。
安裝前需要準備什麼？
`mirage-ai` 套件和 `mirage` CLI 需要 Python ≥ 3.11，TypeScript SDK 需要 Node.js ≥ 20；如果要使用以 FUSE 為基礎的掛載，還需要 macOS 或 Linux 且平台相容 FUSE。
可以掛載哪些服務？
內建約 50 個後端：RAM、Disk、Redis、S3 / R2 / OCI / Supabase / GCS、Gmail / GDrive / GDocs / GSheets / GSlides、GitHub / Linear / Notion / Trello、Slack / Discord / Email、MongoDB / GridFS / Postgres / LanceDB / Qdrant、SSH 等，全部並排掛載在同一個根目錄下。
讀寫操作的資料去向是什麼？
指令直接作用於掛載的後端：遠端服務透過網路存取，使用你自己的憑證（例如 Slack bot token）；雙層快取（索引快取＋檔案快取，預設在程序內 RAM，可選 Redis）會讓重複讀取走本機而不重複存取網路。
07相關的 DSH 工作流程
weknora
作者 tencent
開源的 LLM 知識庫平臺：把原始文件轉化為可檢索的 RAG 知識庫、自主推理智慧體和自動維護的 Wiki 系統，支援多租戶部署。
honcho
作者 plastic-labs
用於構建有狀態 AI 智慧體的記憶庫，支援跨會話連續學習與上下文工程。
reme
作者 agentscope-ai
ReMe：面向 AI Agent 的記憶管理套件——幫 Agent「記住我、最佳化我」，支援 RAG 與長期記憶。
memsearch
作者 zilliztech
為 Claude Code、Codex 等 AI Agent 提供持久化、統一的多層記憶：基於 Markdown 與 Milvus 向量庫，支援語義檢索與混合搜尋。
08資料與來源
**Agent integrations:** OpenAI Agents SDK, Vercel AI SDK, LangChain, Pydantic AI, CAMEL, and OpenHands via the SDKs; cod…
| Coding agents | [Claude Code](https://docs.mirage.strukto.ai/python/agents/claude-code), [Codex](https://docs.mirage.s…
此頁面根據專案公開文件、儲存庫中繼資料與 DSH Plugins 的結構化解析所產生；最後核實於 2026-08-21。發現錯誤？提交更正。
最佳 DeepSeek Harness 外掛
從全目錄挑出的 12 個值得優先安裝的外掛，涵蓋各個分類。