Claude Code can now run entirely inside your own network — Anthropic opens self-hosted environments to enterprise

Anthropic's 6 August 2026 public beta lets Claude Team and Enterprise customers run Claude Code sessions on their own infrastructure instead of Anthropic's servers, giving compliance-sensitive organisations like healthcare and financial services a route to AI-assisted development that keeps source code, secrets and build artifacts inside their own network.

Anthropic opened a public beta for self-hosted environments for Claude Code on 6 August 2026, letting organisations on Team and Enterprise plans move the coding agent’s cloud sessions off Anthropic’s own servers and onto infrastructure inside their own network. A single command turns an organisation’s own machines or containers into the compute layer where sessions actually run — whether started from the web, mobile, desktop, the terminal or a scheduled routine — sitting alongside internal services, toolchains and security controls that were previously off-limits to a cloud-hosted agent.

Two runner modes are on offer: a fixed pool that keeps a set number of runners running with sessions spread across them, or an on-demand mode that spins capacity up when work queues and shuts it down once it’s done, so cost tracks usage rather than sitting idle. Each session runs in an isolated checkout, so one developer’s work can’t leak into another’s. Repository checkouts, build artifacts, secrets and any files a session creates or modifies stay on infrastructure the organisation controls — though it’s worth being precise about the boundary: prompts, model responses and tool results still transmit to Anthropic for inference, so this is a network and data-residency control for code and artifacts, not a fully air-gapped setup.

The intended audience is specific: financial services firms, healthcare organisations and defence contractors with compliance or data-residency requirements that previously ruled out cloud-hosted AI coding agents entirely. For teams without those constraints, Anthropic itself still recommends the standard hosted option — this is a beta aimed at unlocking adoption for a segment that couldn’t say yes before, not a wholesale architecture change for everyone.

So what

If your organisation sits in a regulated sector — healthcare, finance, or anywhere source code and patient or customer data can’t leave your network — “we can’t use AI coding tools because of compliance” is no longer automatically true. The gap between what AI-assisted development can do and what your governance team will sign off on has been closing steadily all year, and self-hosted execution is a meaningful step in that direction, not a marketing claim. We build regulated and healthcare software with this kind of infrastructure-aware approach from day one — see our healthcare software development work or get in touch to talk through what a compliant AI-assisted setup could look like for your team.

← All research

More research.

GitHub Copilot adds Supabase, Webflow, Wix and five more connectors in public preview

GitHub Copilot now connects to eight more services, including Supabase, Webflow, Wix and Mixpanel, through verified MCP connectors in public preview. They join more than 25 existing ones.

Read ›

Gemini 4 Neon is generally available in GitHub Copilot, aimed at lower-cost agentic coding

Gemini 4 Neon is now generally available in GitHub Copilot for agentic coding. Google says its quality is close to Gemini 4 Carbon at a lower token cost per task.

Read ›

Claude Code 2.1.328 brings auto mode to Bedrock, Vertex and Foundry, and narrows /code-review to bugs

Claude Code 2.1.328 extends auto mode to Claude Opus 4.6 and Sonnet 4.6 on Amazon Bedrock, Google Cloud and Microsoft Foundry. /code-review now reports only bugs and CLAUDE.md violations.

Read ›

GitHub Copilot Evals: repeatable tests for AI agents, now in public preview

GitHub Copilot Evals lets teams write repeatable tests for AI coding skills, custom agents and MCP tools. It checks both the result and the path the agent took, and is in public preview.

Read ›

GitHub Copilot can now drive your browser: browser use enters public preview

GitHub Copilot browser use lets an AI coding agent control Chrome to debug web apps and run browser tests. It is in public preview across the CLI, the Copilot app, VS Code and JetBrains.

Read ›

Claude Code 2.1.327 refuses some symbolic links and lists broken setup in /status

Claude Code 2.1.327 tightens file and package permissions again and adds a /status list of broken agent, skill and hook settings. A short read for teams using AI coding tools on a live product.

Read ›

Start a project

Building with AI? Let's talk.

Tell us what you are building. We'll give you an honest view of the right approach.

Start a projectSee our work