langchain-ai/deepagents:從 README 釐清功能入口、限制與導入條件
包括電池的代理安全帶。當您想要一個更輕的安全帶而不需要捆綁中間件時,請使用 LangChain 的 create_agent。
秒懂
- 它是什麼?
- The batteries-included agent harness. Use LangChain's createagent when you want a lighter harness without the bundled middleware.。本文依 langchain-ai/deepagents 官方 README 整理命令、資料流、版本和授權邊界。
- 適合誰用?
- deepagents 適合工作需求與 README 明確範圍相符,且能管理 langchain-ai/deepagents 的依賴、權限與外部服務的人員;不適合把文件未說明的效能、相容性或安全結果當成承諾。先用 https://docs.langchain.com/oss/python/deepagents/overview#deep-agents-overview">;https://opensource.org/licenses/MIT";https://pypistats.org/packages/deepagents";https://pypi.org/project/deepagents/#history";https://x.com/langchainoss" 建立最小案例,對照輸入、輸出、錯誤與版本,再決定是否納入正式流程。
- 可以商用嗎?
- 可以。MIT 是寬鬆授權:你可以使用、修改並販售以它為基礎的軟體,只需保留著作權與授權聲明。
- 還在維護嗎?
- 有在維護。儲存庫在最近一天內有新的提交。
- 用什麼語言寫的?
- 主要是 Python(依據 GitHub 的語言統計)。
以上回答依據專案的 GitHub 資料(最近同步於 2026年9月15日)與我們的分析,不構成法律意見。
開源專案深度解析
deepagents:README 宣告的責任邊界
deepagents(langchain-ai/deepagents)的 README 將專案範圍寫成「The batteries-included agent harness. Use LangChain's createagent when you want a lighter harness without the bundled middleware.」。這一節從「README 宣告的責任邊界」切入,並把判斷限縮在 README 和倉庫資料可直接核對的內容。舊稿提到的 專案定位 langchain-ai/deepagents 的 README 將專案描述為「The batteries-included agent harness.」。本文只整理倉庫可直接核對的內容,不把 star、Fork 或宣傳語當成品 只能作為線索,不能替代目前素材中的原文。README 片段:<div align="center"> <a href="https://docs.langchain.com/oss/python/deepagents/overview#deep-agents-overview"> <picture> <source media="(prefers-color-scheme: dark)" srcset=".github/images/logo-dark.svg"> <source media="(prefers-color-scheme: light)" srcset=".github/images/logo-light.svg"> </picture> </a> </div> <div align="center"> <h3>The batteries-included agent harness.</h3> </div> <div align="center"> <a href="https://opensource.org/licenses/MIT" target="blank"></a> <a href="https://pypistats.org/packages/deepagents" target="blank"></a> <a href="https://pypi.org/project/deepagents/#history" target="blank"></a> <a href="https://x.com/langchainoss" target="blank"></a> </div> <br> Deep Agents is an open source agent harness , an opinionated agent that runs out of the box. Extend, override, or replace any piece. Principles: - Opinionated
langchain-ai-deepagents-deep-analysis-S1:對實際使用者而言,deepagents 的價值在於它把哪些輸入接到哪些輸出,以及哪些工作仍由外部服務、作業系統或開發者負責。文件列出的 https://docs.langchain.com/oss/python/deepagents/overview#deep-agents-overview">;https://opensource.org/licenses/MIT";https://pypistats.org/packages/deepagents";https://pypi.org/project/deepagents/#history";https://x.com/langchainoss" 應逐項對照;README 沒有說明的效能、相容性、權限預設值和支援承諾,本文不延伸成保證。這個界線對 langchain-ai/deepagents 很具體,因為同一個命令換到不同版本或平台後,依賴、憑證、資料格式和錯誤處理都可能改變。
langchain-ai-deepagents-deep-analysis-S1:第 1 節的核驗焦點是 deepagents 的 README 宣告的責任邊界:可在隔離環境執行 https://docs.langchain.com/oss/python/deepagents/overview#deep-agents-overview">;https://opensource.org/licenses/MIT";https://pypistats.org/packages/deepagents";https://pypi.org/project/deepagents/#history";https://x.com/langchainoss" 中與本節相關的入口,記下命令列、輸入檔、輸出檔、錯誤碼和 main 分支版本。若 deepagents 需要模型、網路、資料庫、GPU、SSH 或其他服務,應把該條件和產物一併記錄,觀察結果是否真的符合 README 的這一項描述。這不是把一次成功當成普遍結論,而是針對 deepagents 自身的輸入與輸出留下可追溯證據。
deepagents:第一個可執行入口
deepagents(langchain-ai/deepagents)的 README 將專案範圍寫成「The batteries-included agent harness. Use LangChain's createagent when you want a lighter harness without the bundled middleware.」。這一節從「第一個可執行入口」切入,並把判斷限縮在 README 和倉庫資料可直接核對的內容。舊稿提到的 質證明。README 在「README」下寫到:Deep Agents is an open source agent harness , an opinionated agent that runs out of the box. Ext 只能作為線索,不能替代目前素材中的原文。README 片段: or local - Production-ready , built on LangGraph (streaming, persistence, checkpointing) with first-class tracing, evaluation, and deployment via LangSmith Features include: - Sub-agents , delegate tasks to agents with isolated context windows - Filesystem , read, write, edit, or search over pluggable local, sandboxed, or remote backends - Context management , summarize long threads and offload tool outputs to disk - Shell access , run commands in your sandbox of choice - Persistent memory , pluggable state and store backends for cross-session recall - Human-in-the-loop , approve, edit, or reject tool calls before they run - Skills , reusable behaviors the agent can load on demand - Tools , bring your own functions or any MCP server Deep Agents is available as a JavaScript/TypeScript library , see [deepagents.js](https://github.com/langc
langchain-ai-deepagents-deep-analysis-S2:對實際使用者而言,deepagents 的價值在於它把哪些輸入接到哪些輸出,以及哪些工作仍由外部服務、作業系統或開發者負責。文件列出的 https://docs.langchain.com/oss/python/deepagents/overview#deep-agents-overview">;https://opensource.org/licenses/MIT";https://pypistats.org/packages/deepagents";https://pypi.org/project/deepagents/#history";https://x.com/langchainoss" 應逐項對照;README 沒有說明的效能、相容性、權限預設值和支援承諾,本文不延伸成保證。這個界線對 langchain-ai/deepagents 很具體,因為同一個命令換到不同版本或平台後,依賴、憑證、資料格式和錯誤處理都可能改變。
langchain-ai-deepagents-deep-analysis-S2:第 2 節的核驗焦點是 deepagents 的 第一個可執行入口:可在隔離環境執行 https://docs.langchain.com/oss/python/deepagents/overview#deep-agents-overview">;https://opensource.org/licenses/MIT";https://pypistats.org/packages/deepagents";https://pypi.org/project/deepagents/#history";https://x.com/langchainoss" 中與本節相關的入口,記下命令列、輸入檔、輸出檔、錯誤碼和 main 分支版本。若 deepagents 需要模型、網路、資料庫、GPU、SSH 或其他服務,應把該條件和產物一併記錄,觀察結果是否真的符合 README 的這一項描述。這不是把一次成功當成普遍結論,而是針對 deepagents 自身的輸入與輸出留下可追溯證據。
deepagents:資料流與核心元件
deepagents(langchain-ai/deepagents)的 README 將專案範圍寫成「The batteries-included agent harness. Use LangChain's createagent when you want a lighter harness without the bundled middleware.」。這一節從「資料流與核心元件」切入,並把判斷限縮在 README 和倉庫資料可直接核對的內容。舊稿提到的 end, override, or replace any piece.。這說明的是專案邊界,不是已完成的生產驗證。 適用場景 從 README 的「README」與相關條目,可以先判斷它是否處理你的實際問題:Extensible , ov 只能作為線索,不能替代目前素材中的原文。README 片段: bash`. See the [documentation](https://docs.langchain.com/deepagents-code) for the full feature set. ## Quickstart ```bash uv add deepagents ``` ```python from deepagents import createdeepagent agent = createdeepagent( model="openai:gpt-5.5", tools=[mycustomtool], systemprompt="You are a research assistant.", ) result = agent.invoke({"messages": "Research LangGraph and write a summary"}) ``` The agent can plan, read/write files, and manage its own context. Add your own tools, swap models, customize prompts, configure sub-agents, and more. See the [documentation](https://docs.langchain.com/oss/python/deepagents/overview) for full details. > [!TIP] > For developing, debugging, and deploying AI agents and LLM applications, see [LangSmith](https://docs.langchain.com/langsmith/home). ## FAQ ### How is this different from LangGraph or LangChai
langchain-ai-deepagents-deep-analysis-S3:對實際使用者而言,deepagents 的價值在於它把哪些輸入接到哪些輸出,以及哪些工作仍由外部服務、作業系統或開發者負責。文件列出的 https://docs.langchain.com/oss/python/deepagents/overview#deep-agents-overview">;https://opensource.org/licenses/MIT";https://pypistats.org/packages/deepagents";https://pypi.org/project/deepagents/#history";https://x.com/langchainoss" 應逐項對照;README 沒有說明的效能、相容性、權限預設值和支援承諾,本文不延伸成保證。這個界線對 langchain-ai/deepagents 很具體,因為同一個命令換到不同版本或平台後,依賴、憑證、資料格式和錯誤處理都可能改變。
langchain-ai-deepagents-deep-analysis-S3:第 3 節的核驗焦點是 deepagents 的 資料流與核心元件:可在隔離環境執行 https://docs.langchain.com/oss/python/deepagents/overview#deep-agents-overview">;https://opensource.org/licenses/MIT";https://pypistats.org/packages/deepagents";https://pypi.org/project/deepagents/#history";https://x.com/langchainoss" 中與本節相關的入口,記下命令列、輸入檔、輸出檔、錯誤碼和 main 分支版本。若 deepagents 需要模型、網路、資料庫、GPU、SSH 或其他服務,應把該條件和產物一併記錄,觀察結果是否真的符合 README 的這一項描述。這不是把一次成功當成普遍結論,而是針對 deepagents 自身的輸入與輸出留下可追溯證據。
deepagents:整合和設定的實際限制
deepagents(langchain-ai/deepagents)的 README 將專案範圍寫成「The batteries-included agent harness. Use LangChain's createagent when you want a lighter harness without the bundled middleware.」。這一節從「整合和設定的實際限制」切入,並把判斷限縮在 README 和倉庫資料可直接核對的內容。舊稿提到的 erride or replace any piece without forking。若需求不同,不應只因專案熱度就採用。本文保留原始專案名、命令與元件名,方便回到一手來源核對。 README 另外列出一項可核對的資訊:Opinionat 只能作為線索,不能替代目前素材中的原文。README 片段:filesystem, sub-agents, context management, and skills bundled in. For how the three relate, see the [LangChain ecosystem overview](https://docs.langchain.com/oss/python/concepts/products). ### Does this work with open-weight or local models? Yes. Any model that supports tool calling works , frontier APIs (OpenAI, Anthropic, Google), open-weight models hosted on providers like Baseten or Fireworks, and self-hosted models via Ollama, vLLM, or llama.cpp. Use any [LangChain chat model](https://docs.langchain.com/oss/python/langchain/models). ### Can I use this in production? Yes! Deep Agents is built on LangGraph, designed for production agent deployments. Pair it with [LangSmith](https://docs.langchain.com/langsmith/home) for tracing, evaluation, and monitoring. See [Going to production](https://docs.langchain.com/oss/python/deepagents/goin
langchain-ai-deepagents-deep-analysis-S4:對實際使用者而言,deepagents 的價值在於它把哪些輸入接到哪些輸出,以及哪些工作仍由外部服務、作業系統或開發者負責。文件列出的 https://docs.langchain.com/oss/python/deepagents/overview#deep-agents-overview">;https://opensource.org/licenses/MIT";https://pypistats.org/packages/deepagents";https://pypi.org/project/deepagents/#history";https://x.com/langchainoss" 應逐項對照;README 沒有說明的效能、相容性、權限預設值和支援承諾,本文不延伸成保證。這個界線對 langchain-ai/deepagents 很具體,因為同一個命令換到不同版本或平台後,依賴、憑證、資料格式和錯誤處理都可能改變。
langchain-ai-deepagents-deep-analysis-S4:第 4 節的核驗焦點是 deepagents 的 整合和設定的實際限制:可在隔離環境執行 https://docs.langchain.com/oss/python/deepagents/overview#deep-agents-overview">;https://opensource.org/licenses/MIT";https://pypistats.org/packages/deepagents";https://pypi.org/project/deepagents/#history";https://x.com/langchainoss" 中與本節相關的入口,記下命令列、輸入檔、輸出檔、錯誤碼和 main 分支版本。若 deepagents 需要模型、網路、資料庫、GPU、SSH 或其他服務,應把該條件和產物一併記錄,觀察結果是否真的符合 README 的這一項描述。這不是把一次成功當成普遍結論,而是針對 deepagents 自身的輸入與輸出留下可追溯證據。
deepagents:版本與維護訊號
deepagents(langchain-ai/deepagents)的 README 將專案範圍寫成「The batteries-included agent harness. Use LangChain's createagent when you want a lighter harness without the bundled middleware.」。這一節從「版本與維護訊號」切入,並把判斷限縮在 README 和倉庫資料可直接核對的內容。舊稿提到的 ed , defaults tuned for long-horizon, multi-step work。這類原文條目可用來設計試跑步驟,但不能取代實際環境測試。 運作方式 README 將運作方式分散在「README」等段落。可確認的線 只能作為線索,不能替代目前素材中的原文。README 片段:langchain.com/oss/python/concepts/products) for how they relate. Use Deep Agents when you want the full harness , planning, context management, delegation , out of the box. Use [LangChain's `createagent`](https://docs.langchain.com/oss/python/langchain/agents) when you want a lighter harness without the bundled middleware. Drop to [LangGraph](https://docs.langchain.com/oss/python/langgraph/overview) when the agent loop itself isn't the right shape and you need a custom graph. The layers compose: any LangGraph `CompiledStateGraph` can be passed in as a sub-agent to a Deep Agent, so custom orchestration plugs in alongside the harness's defaults. --- ## Resources - [Examples](examples/) , working agents and patterns - [Documentation](https://docs.langchain.com/oss/python/deepagents/overview) , conceptual overviews and guides - [LangChain eco
langchain-ai-deepagents-deep-analysis-S5:對實際使用者而言,deepagents 的價值在於它把哪些輸入接到哪些輸出,以及哪些工作仍由外部服務、作業系統或開發者負責。文件列出的 https://docs.langchain.com/oss/python/deepagents/overview#deep-agents-overview">;https://opensource.org/licenses/MIT";https://pypistats.org/packages/deepagents";https://pypi.org/project/deepagents/#history";https://x.com/langchainoss" 應逐項對照;README 沒有說明的效能、相容性、權限預設值和支援承諾,本文不延伸成保證。這個界線對 langchain-ai/deepagents 很具體,因為同一個命令換到不同版本或平台後,依賴、憑證、資料格式和錯誤處理都可能改變。
langchain-ai-deepagents-deep-analysis-S5:第 5 節的核驗焦點是 deepagents 的 版本與維護訊號:可在隔離環境執行 https://docs.langchain.com/oss/python/deepagents/overview#deep-agents-overview">;https://opensource.org/licenses/MIT";https://pypistats.org/packages/deepagents";https://pypi.org/project/deepagents/#history";https://x.com/langchainoss" 中與本節相關的入口,記下命令列、輸入檔、輸出檔、錯誤碼和 main 分支版本。若 deepagents 需要模型、網路、資料庫、GPU、SSH 或其他服務,應把該條件和產物一併記錄,觀察結果是否真的符合 README 的這一項描述。這不是把一次成功當成普遍結論,而是針對 deepagents 自身的輸入與輸出留下可追溯證據。
deepagents:專案化核驗路徑
deepagents(langchain-ai/deepagents)的 README 將專案範圍寫成「The batteries-included agent harness. Use LangChain's createagent when you want a lighter harness without the bundled middleware.」。這一節從「專案化核驗路徑」切入,並把判斷限縮在 README 和倉庫資料可直接核對的內容。舊稿提到的 索包括:> [!NOTE] > Deep Agents Code , a pre-built coding agent in your terminal, similar to Claude Code or Cursor, powered 只能作為線索,不能替代目前素材中的原文。README 片段:epagents/) , complete reference for all public classes, functions, and types - [Discussions](https://forum.langchain.com/c/oss-product-help-lc-and-lg/deep-agents/18) , community forum for technical questions, ideas, and feedback - [LangChain Academy](https://academy.langchain.com/) , Comprehensive, free courses on LangChain libraries and products, made by the LangChain team. - [Contributing Guide](https://docs.langchain.com/oss/python/contributing/overview) , how to contribute and find good first issues - [Code of Conduct](https://github.com/langchain-ai/langchain/?tab=coc-ov-file) , community guidelines and standards --- ## Acknowledgements Inspired by Claude Code: an attempt to identify what makes it general-purpose, and push that further. ## Security Deep Agents follows a "trust the LLM" model. The agent can do anything its tools allow
langchain-ai-deepagents-deep-analysis-S6:對實際使用者而言,deepagents 的價值在於它把哪些輸入接到哪些輸出,以及哪些工作仍由外部服務、作業系統或開發者負責。文件列出的 https://docs.langchain.com/oss/python/deepagents/overview#deep-agents-overview">;https://opensource.org/licenses/MIT";https://pypistats.org/packages/deepagents";https://pypi.org/project/deepagents/#history";https://x.com/langchainoss" 應逐項對照;README 沒有說明的效能、相容性、權限預設值和支援承諾,本文不延伸成保證。這個界線對 langchain-ai/deepagents 很具體,因為同一個命令換到不同版本或平台後,依賴、憑證、資料格式和錯誤處理都可能改變。
langchain-ai-deepagents-deep-analysis-S6:第 6 節的核驗焦點是 deepagents 的 專案化核驗路徑:可在隔離環境執行 https://docs.langchain.com/oss/python/deepagents/overview#deep-agents-overview">;https://opensource.org/licenses/MIT";https://pypistats.org/packages/deepagents";https://pypi.org/project/deepagents/#history";https://x.com/langchainoss" 中與本節相關的入口,記下命令列、輸入檔、輸出檔、錯誤碼和 main 分支版本。若 deepagents 需要模型、網路、資料庫、GPU、SSH 或其他服務,應把該條件和產物一併記錄,觀察結果是否真的符合 README 的這一項描述。這不是把一次成功當成普遍結論,而是針對 deepagents 自身的輸入與輸出留下可追溯證據。
編輯結論
deepagents 適合工作需求與 README 明確範圍相符,且能管理 langchain-ai/deepagents 的依賴、權限與外部服務的人員;不適合把文件未說明的效能、相容性或安全結果當成承諾。先用 https://docs.langchain.com/oss/python/deepagents/overview#deep-agents-overview">;https://opensource.org/licenses/MIT";https://pypistats.org/packages/deepagents";https://pypi.org/project/deepagents/#history";https://x.com/langchainoss" 建立最小案例,對照輸入、輸出、錯誤與版本,再決定是否納入正式流程。
社群筆記