MIT 授權的 Agent OS，把訪談 → Seed → 執行 → 評估 → 進化的可回放 AI 編碼工作流程接入 DeepSeek Harness：透過 dsh-ouroboros 外掛在 dsh 內原生執行 `ooo` 工具，或用 `--llm-backend dsh` 呼叫 DeepSeek 模型。
DSH 整合
原生執行環境
作者聲明
安全稽核
未稽核
最後核實
2026-08-21
授權條款
MIT
01它能幫你完成什麼？
Turn a vague idea into a verified, working codebase with a spec-first workflow
Immutable Seed specification (ambiguity scored, ≤ 0.2 gate), Double Diamond execution, and code verified by a 3-stage evaluation gate: Mechanical → Semantic → Multi-Model Consensus
Developers and teams using AI coding agents — including DeepSeek Harness — who want verified results instead of rework from vague prompts
Run interview / auto workflows natively inside DeepSeek Harness chat
The same `ouroboros_interview` / `ouroboros_auto` tools driven turn by turn in dsh, with advisory fan-out results submitted between rounds
DeepSeek Harness (dsh) users who want structured, policy-bound AI agent automation without leaving dsh chat
Automate multi-stage verification instead of manual QA
3-stage automated evaluation gate — Mechanical (free) → Semantic → Multi-Model Consensus — whose output feeds an evolutionary loop until ontology convergence
Engineering teams that need replayable, observable verification of agent-generated code rather than "looks good" reviews
02如何將外掛接入 DeepSeek Harness？
先決條件
- DeepSeek Harness (dsh) with a profile, for the dsh-ouroboros plugin direction
- Python >= 3.12 for pip/uv-based installs (LiteLLM-bearing profiles support 3.12–3.13); the one-command installer auto-detects available runtimes
安裝步驟
- 01
Install Ouroboros with one command: `curl -fsSL https://raw.githubusercontent.com/Q00/ouroboros/main/scripts/install.sh | OUROBOROS_INSTALL_REF=readme bash` (alternatives: `pipx install 'ouroboros-ai[mcp]'` or Homebrew `brew tap q00/tap && brew install ouroboros-ai`)
$ curl -fsSL https://raw.githubusercontent.com/Q00/ouroboros/main/scripts/install.sh | OUROBOROS_INSTALL_REF=readme bash
- 02
Run `ooo setup` once inside your coding agent — a one-time configuration step (`ouroboros setup` from a plain terminal)
- 03
Add the plugin to DeepSeek Harness: `dsh plugin --profile <your-profile> add "github:Q00/ouroboros#main&path:integrations/dsh-plugin"`
$ dsh plugin --profile <your-profile> add "github:Q00/ouroboros#main&path:integrations/dsh-plugin"
- 04
Type `ooo interview` / `ooo auto` directly in the DeepSeek Harness chat
驗證整合成功
作者未說明
復原
- Run `ouroboros uninstall` — removes all configuration, MCP registration, and data (details in UNINSTALL.md)
03DSH 整合程度與能力邊界
Official dsh-ouroboros plugin installed via `dsh plugin add` — `ooo interview` / `ooo auto` tools run natively inside DeepSeek Harness chat; also works in reverse via `--llm-backend dsh`, driving Harness's ACP server
Socratic interview + ambiguity-gated Seed
a vague idea or task description (`ooo interview` in an agent session, or `ouroboros init start` from the terminal)→hidden assumptions exposed and an immutable Seed specification; ambiguity must score ≤ 0.2 before Seed generation (or an explicit `force`)
3-stage evaluation gate & evolutionary loop
executed codebase produced from a Seed→Mechanical (free) → Semantic → Multi-Model Consensus verdicts; evaluation output feeds the next generation until ontology similarity >= 0.95
LLM calls to the configured model backend for the semantic and consensus stagesPersistent loop with replayable event sourcing (`ooo ralph`)
a Seed lineage to evolve→persistent, stateless evolution across session boundaries until convergence; the EventStore reconstructs the full lineage after restarts
persists execution events locally via event sourcing (SQLAlchemy + aiosqlite)Multi-runtime MCP integration (13 hosts)
any supported coding-agent runtime: Claude Code, Codex CLI, GitHub Copilot CLI, OpenCode, Hermes, Gemini, Kiro, Pi, Zcode, Goose, GJC, Antigravity, Grok→MCP server registered where the host supports it; the same workflow spec runs across execution engines
setup writes host configuration files (e.g. ~/.kiro/settings/mcp.json, ~/.copilot/mcp-config.json) and registers the MCP server
04適合誰？何時不該用？
適合
- Developers and teams using AI coding agents — including DeepSeek Harness — who want verified results instead of rework from vague prompts
- DeepSeek Harness (dsh) users who want structured, policy-bound AI agent automation without leaving dsh chat
- Engineering teams that need replayable, observable verification of agent-generated code rather than "looks good" reviews
不適合
- Python >= 3.12 is required; LiteLLM-bearing profiles (`[litellm]`, `[all]`) only support Python 3.12–3.13.
- When installing as an MCP server, use 0.51.1 or later — earlier versions can fail at startup with `Failed to reconnect to plugin:ouroboros:ouroboros: -32000`, and downstream packages can lag PyPI.
- Never install `[mcp,claude]`, `[mcp,claude-sdk]`, or `[all,mcp]` in one interpreter; host registration requires `uvx --isolated --python '>=3.12'` or `pipx`, otherwise setup exits without changing runtime configuration.
05相容性、維護與安全提醒
- Python >= 3.12 is required; LiteLLM-bearing profiles (`[litellm]`, `[all]`) only support Python 3.12–3.13.
- When installing as an MCP server, use 0.51.1 or later — earlier versions can fail at startup with `Failed to reconnect to plugin:ouroboros:ouroboros: -32000`, and downstream packages can lag PyPI.
- Never install `[mcp,claude]`, `[mcp,claude-sdk]`, or `[all,mcp]` in one interpreter; host registration requires `uvx --isolated --python '>=3.12'` or `pipx`, otherwise setup exits without changing runtime configuration.
MIT · actively maintained (latest release v0.51.13, 2026-08-19)
06常見問題
如何在 DeepSeek Harness 裡使用 Ouroboros？
執行 `dsh plugin --profile <your-profile> add "github:Q00/ouroboros#main&path:integrations/dsh-plugin"` 安裝 dsh-ouroboros 外掛，然後在 dsh 對話中直接輸入 `ooo interview` / `ooo auto` —— 同一套 `ouroboros_interview` / `ouroboros_auto` 工具會在 dsh 內原生運作。
DeepSeek Harness 整合是原生還是 MCP？
兩個方向都支援。在 dsh 內，外掛工具原生運作，以 `mcp__ouroboros__ouroboros_interview` 的形式逐輪驅動；反過來，Ouroboros 也能用 `--llm-backend dsh` 或 `OUROBOROS_LLM_BACKEND=dsh` 把流水線指向 DeepSeek 模型，底層驅動 DeepSeek Harness 的 ACP server。
安裝前需要準備什麼？
走外掛方向需要 DeepSeek Harness（dsh）；走 pip/uv 安裝需要 Python >= 3.12。一行指令的安裝程式會自動偵測本機既有的執行階段；若作為 MCP server 安裝，請使用 0.51.1 以上版本。
有哪些需要注意的限制？
不要在同一個直譯器混裝 `[mcp]` 與 `[claude]`/`[all]` extras；主機註冊需要 `uvx --isolated` 或 `pipx`。工作流程層面，模糊度評分高於 0.2 會阻擋 Seed 產生，除非明確傳入 `force`。
我的資料和模型呼叫去了哪裡？
Ouroboros 是 local-first 執行階段：執行事件透過 event sourcing（SQLAlchemy + aiosqlite）保存在本機。模型呼叫會發往你設定的後端——使用 `--llm-backend dsh` 時，就是經由 DeepSeek Harness 呼叫 DeepSeek 自家模型。
07相關的 DSH 工作流程
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。
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。
nocobase
作者 nocobase
開源的 AI + 無程式碼應用搭建平臺：AI 在久經生產驗證的底層基礎設施與所見即所得的無程式碼介面之上工作，幫你快速構建 CRM、ERP 等業務系統，兼顧速度與可靠性。
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
and type `ooo interview` / `ooo auto` directly in the DeepSeek Harness chat — the same `ouroboros_interview` / `ouroboro…
Ouroboros speaks DeepSeek two ways. Point the interview/Seed/QA pipeline at DeepSeek's own models with `--llm-backend ds…
driven from a dsh chat: <code>mcp__ouroboros__ouroboros_interview</code> turn by turn, fan-out results submitted between…
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。