Claude Blog 3 min

Run Claude Code sessions on your own compute

🔗 https://claude.com/blog/run-claude-code-sessions-on-your-own-compute

📌 【Anthropic 公布】Claude Code 支援私有運算環境,讓 Agent 深入企業內部網路

TL;DR:Claude Code 推出公測版私有化部署,讓 AI Agent 能在企業內部基礎設施執行。

隨著 AI Agent 逐漸深入開發流程,安全性與網路存取權限成為企業導入的核心考量。Anthropic 正式宣布,現已開放公測「自託管環境(Self-hosted environments)」,讓 Claude Code 的執行運算能直接在企業自己的基礎設施上運行。

🤔 為什麼企業需要將 Claude Code 部署在自己的基礎設施?

根據 Anthropic 在預覽計畫中的觀察,企業選擇自託管主要基於三大需求:

  • 網路存取權:Session 直接在企業網路內執行,可以存取內部的服務、資料庫與 Registry,無需將這些資源暴露於公開網路。
  • 高度客製化:開發者可以在環境中預先安裝編譯器 (compilers)、SDK 以及內部的 CLI 工具,確保每個 Session 一啟動即可直接進行建置。
  • 合規性與安全性:原始碼 (source code) 與建置產出物 (build artifacts) 都能保留在企業可控的基礎設施中。

🧩 架構設計:Runner 模式與隔離機制

在自託管模式下,企業需要部署一系列的 Runner(長駐程序),當使用者從 Web、Mobile 或 Desktop 發起 Session 時,Runner 會接手並啟動對應的 Claude Code 程序。

Runner 提供兩種運作模式:

  • 固定模式 (Fixed):維持固定數量的 Runner 運行,並將 Session 分配至其中。
  • 按需模式 (On-demand):透過編排器 (orchestrator) 監控排隊的 Session,隨需求啟動 Runner 並在工作結束後停止,以實現容量隨需求變動。

⚠️ 資料流向:對話內容仍需傳送至 Anthropic

需要特別注意的是,雖然程式碼與建置產出物留在本地,但對話過程(包含 Prompt、回應以及工具執行結果)仍會傳送到 Anthropic 進行推理 (inference),且 Session 的對話紀錄會被儲存,以便使用者能從不同介面接續工作。

💡 與 Remote Control 的差異

這項功能與「遠端控制 (Remote Control)」不同:

  • Remote Control:讓開發者能從手機或瀏覽器接續在「自己電腦上」執行的 Session,Session 會隨電腦關機而結束。
  • Self-hosted environments:由平臺團隊營運的共享基礎設施,任何使用者皆可使用。

🎯 實務啟示:準備好工程人力進行維護

對於 Claude Team 與 Enterprise 計畫的組織,此功能目前處於公測階段(預設為關閉狀態)。由於需要負責建立與維護 Runner 映像檔 (runner image)、更新 Runner 以及運行編排器,建議企業應指派專門的平臺 (Platform) 或開發者體驗 (DevEx) 團隊來負責設定與持續維護。

🔗 來源

#Anthropic #ClaudeCode #AIAgent #SelfHosted #DevOps #SoftwareEngineering #EnterpriseAI #LLM #DeveloperTools #Infrastructure

原始資料 Claude Blog · 收集於 2026-08-07
來源原標題
Run Claude Code sessions on your own compute
機構
Anthropic
原始標籤
Product announcements
原始連結
https://claude.com/blog/run-claude-code-sessions-on-your-own-compute

摘要原文

Run Claude Code sessions on your own compute Category Product announcements Product Claude Code Date August 6, 2026 Reading time 5 min Share Copy link https://claude.com/blog/run-claude-code-sessions-on-your-own-compute Now in public beta, self-hosted environments let you run Claude Code sessions on your own infrastructure. Start a session from the web, mobile, desktop, or a routine, and it runs inside your network, next to your internal services, toolchains, and security controls, rather than on Anthropic-hosted infrastructure. For most enterprises, we strongly recommend our hosted offering for operational simplicity with no infrastructure to run or maintain. Self-hosted environments are for teams whose network, tooling, or compliance requirements call for keeping agent execution on infrastructure they control. If you go this route, plan to staff engineering to own setup and ongoing maintenance. Why self-host We saw organizations in our preview program adopt self-hosted environments for a few key reasons: Network access: sessions run inside your network and can reach internal services, databases, and registries without exposing them to the public internet Customizability: pre-install compilers, SDKs, and internal CLIs in your environment so every session starts ready to build Compliance: source code and build artifacts stay on infrastructure you control “Self-hosted environments let us integrate Claude Code into our existing development workflows while maintaining our security and operational controls. This setup means Claude can generate PRs, help fix CI issues, and respond to developer workflow events, with compute that can scale based on demand. Claude understands our codebase, making it a strong fit for how our engineering teams build.” George Jacob, Senior Engineering Manager Prev Prev 0 / 5 Next Next eBook Data stays on your infrastructure Repository checkouts, build artifacts, secrets, and any files a session creates or modifies all stay on infrastructure you provision. The conversation itself, including prompts, responses, and tool results (which can include code that Claude reads), is sent to Anthropic for inference, and the session transcript is stored so a session can be picked up from any surface. How it works When using self-hosted environments, you deploy a set of runners . These long-lived processes pick up sessions and start a Claude Code process for each session . Runners come in two modes. Fixed: you keep a set number running and sessions are distributed across them. On-demand: an orchestrator watches for queued sessions, starts a runner as sessions arrive, and stops them when work finishes so capacity tracks demand. Runners can serve more than one session, but each session runs in its own checkout, so work stays isolated between developers and accounts. Sessions from every supported surface route to the same environment, so you set it up once and it works wherever your team starts a session. Note : Self-hosted environments differ from Remote Control , which lets developers continue sessions running on their own machines from a phone or browser. Sessions using Remote Control end when that machine stops running the session and are tied to the user who ran claude , whereas self-hosted environments run sessions on shared infrastructure your platform team operates and can be used by any user. Getting started Self-hosted environments are available in public beta to organizations on Claude Team and Enterprise plans. They are off by default and not available for organizations using ZDR. Plan on a platform, developer experience, or developer productivity team owning setup and ongoing operation, including building and maintaining the runner image, updating runners, and running the orchestrator if you use on-demand mode. See the documentation to learn more. Share feedback via GitHub or through your Anthropic account team. FAQ No items found. Transform how your organization operates with Claude See pricing See pricing See pricing Contact sales Contact sales Contact sales Get the developer newsletter Product updates, how-tos, community spotlights, and more. Delivered monthly to your inbox.

tencent/hy3:free 自動生成