Apache-2.0 自主 AI 科研平台（從文獻到完成評審的論文），透過 Docker Compose 部署；其唯讀 MCP 伺服器可作為 DeepSeek Harness 生態夥伴銜接編碼代理。
DSH 整合
生態系相關
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？
Run the full research lifecycle — literature survey, idea generation and review, GPU experiments, LaTeX paper writing, and paper review — as one platform
Cross-linked research wiki, scored and deduplicated ideas with Elo-ranked review, experiment runs with streamed logs and metric curves, multi-file LaTeX papers with live PDF preview, and citation-verified reviews
Research labs and AI research teams that want an autonomous AI-scientist platform covering the whole pipeline
Let agents run long experiments on lab GPU servers with self-verification and human gates
Automated experiment Voyages: study plan, compute-budget check, generated code, smoke test, streamed runs with live metric curves, and auto-iteration that repairs failures under a time budget
ML researchers who want agents to execute and iterate on real GPU servers under budgets and audit
Expose Polaris's research knowledge to external coding agents via MCP
An MCP server (Streamable HTTP and stdio) of read-only tools over literature, knowledge, project state, manuscripts, and external search
Users of coding agents (Claude Code, Codex, Cursor) who want research context inside their agent workflow
02如何將外掛接入 DeepSeek Harness？
先決條件
- Docker and Docker Compose only — the README says no local Python, Node, or database is needed for the recommended Docker Compose setup
- LLM provider keys and secrets configured in .env
安裝步驟
- 01
Run `cp .env.example .env` and set provider keys and secrets
- 02
Run `make dev` to start the full stack via docker compose with hot reload (frontend at http://localhost:5173, backend API docs at http://localhost:8000/docs)
- 03
Production alternative: deploy pre-built images — set POLARIS_ENV=prod and POLARIS_IMAGE_TAG in .env, run `docker compose --env-file .env -f docker/docker-compose.yml pull`, then `up -d`, then `docker compose -f docker/docker-compose.yml exec api alembic upgrade head` (required on first run)
驗證整合成功
作者未說明
03DSH 整合程度與能力邊界
DSH-ecosystem AI research platform (tagged dsh-plugin on GitHub): run Polaris as a standalone web app via Docker Compose; its MCP server exposes read-only research tools to external coding agents
Voyage agent core
any long-running research task (literature backfill, experiment run, paper drafting)→resumable, auditable runs with a persisted planning → executing → verifying loop that resumes from checkpoint after a crash
retains every plan, action, and verdict, replayable in the UI; auto-pauses when budgets are exceededResearch Wiki (compile, don't retrieve)
papers from OpenAlex, Semantic Scholar, and arXiv→one cross-linked wiki per paper shared platform-wide (TL;DR, method, reusable ideas, concept backlinks), research digests, and Obsidian vault sync
queries external literature APIs (OpenAlex, Semantic Scholar, arXiv) and writes wiki/Obsidian artifactsExperiment Lab over SSH
per-user, Fernet-encrypted SSH credentials to the lab's GPU servers→planned, budget-checked experiment runs with streamed logs, live metric curves, generated figures, and a file-based memory kept across steps
writes and runs code on remote GPU servers under gated remote writes, command allow/deny lists, and triple budget capsMCP tool layer
Polaris project data (literature, knowledge, project state, manuscripts)→an MCP server (Streamable HTTP and stdio) exposing read-only tools to Claude Code, Codex, and Cursor, with a self-check playground
exposes project data over the network (Streamable HTTP / stdio); strictly read-only and project-isolated
04適合誰？何時不該用？
適合
- Research labs and AI research teams that want an autonomous AI-scientist platform covering the whole pipeline
- ML researchers who want agents to execute and iterate on real GPU servers under budgets and audit
- Users of coding agents (Claude Code, Codex, Cursor) who want research context inside their agent workflow
不適合
- The README does not document running inside DeepSeek Harness (dsh): Polaris is deployed as a standalone web app via Docker Compose; its connection point to external agents is a read-only MCP server documented for Claude Code, Codex, and Cursor.
- The recommended deployment is a full multi-container stack (PostgreSQL 16 with pgvector, Redis 7, API, worker, frontend), and the first-run `alembic upgrade head` migration is mandatory since Postgres tables are not auto-created.
05相容性、維護與安全提醒
- The README does not document running inside DeepSeek Harness (dsh): Polaris is deployed as a standalone web app via Docker Compose; its connection point to external agents is a read-only MCP server documented for Claude Code, Codex, and Cursor.
- The recommended deployment is a full multi-container stack (PostgreSQL 16 with pgvector, Redis 7, API, worker, frontend), and the first-run `alembic upgrade head` migration is mandatory since Postgres tables are not auto-created.
- Desktop builds are neither signed nor notarized: macOS needs `xattr -dr com.apple.quarantine`, Windows SmartScreen requires Run anyway, and the Linux AppImage needs extra system libraries.
Apache-2.0 · actively maintained (latest release v0.3.8, 2026-08-17)
06常見問題
Polaris 如何與 DeepSeek Harness 銜接？
README 未提供 dsh 原生整合說明。Polaris 以獨立的 Web 應用程式執行，透過 Docker Compose 部署；它對外部編碼代理的存取點是唯讀 MCP 伺服器（Streamable HTTP 與 stdio），文件中以 Claude Code、Codex 和 Cursor 為例。
執行 Polaris 需要準備什麼？
推薦方式只需 Docker 和 Docker Compose，無須在本機安裝 Python、Node 或資料庫。把 `.env.example` 複製為 `.env`，填入 LLM 供應商金鑰與機密資訊，然後執行 `make dev`（正式環境可部署 Docker Hub 上的預先建置映像）。
代理能在真實 GPU 伺服器上跑實驗嗎？
可以。實驗中心使用按使用者 Fernet 加密的 SSH 憑證，先規劃研究方案、通過算力預算檢查，再撰寫並執行程式碼，提供串流日誌與即時指標曲線，並在受控的遠端寫入、命令允許/拒絕清單與三重預算上限下自動迭代。
Voyage 是什麼？
每個長時間任務都是一次 Voyage：由 Navigator（規劃）、Helm（執行）、Sextant（自我驗證）三段循環驅動的持久化、可恢復、人工把關的代理執行。工作行程崩潰後可從檢查點續跑，預算超限時會自動暫停。
安裝桌面客戶端要注意什麼？
建置未經簽署與公證，各系統首次執行需放行一次：macOS 執行 `xattr -dr com.apple.quarantine /Applications/Polaris.app`，Windows 在 SmartScreen 選擇「更多資訊 → 仍要執行」，Linux AppImage 需要 libnss3、libgtk-3-0 和 libasound2。
07相關的 DSH 工作流程
openviking
作者 volcengine
為 AI 智慧體打造的自進化上下文資料庫，統一智慧體記憶、知識 RAG 與技能。
colleague-skill
作者 titanwings
將冰冷的離別化為溫暖的 Skill，歡迎加入數字生命1.0！Transforming cold farewells into warm skills? It's giving rebirth era. Welcome to Digital Life 1.0. 🫶
archify
作者 tt-a1i
為編碼智慧體生成美觀可驗證的架構圖、時序圖與資料流圖，輸出自包含 HTML，支援動效與清晰匯出。
learn-harness-engineering
作者 walkinglabs
Harness 工程新手教程，從 0 到 1 系統學習智慧體工作流框架。
08資料與來源
is exposed both internally to the agent loop and externally as an **MCP server** (Streamable HTTP and stdio) for Claud…
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。