English · 简体中文

WebCodex

Give cloud AI agents a real development environment on your own machines.

Connect ChatGPT, Claude, and other MCP clients to the repositories, Git checkout, and tools you already use.

One computer · Several computers · Documentation · Issues · Contribute · Security

Ask your assistant to inspect a repository, modify code, run tests, use Git, or investigate a failure. Your repository stays on the machine where it already lives; you do not need to move the project into a hosted workspace just to use an AI coding agent.

Start using WebCodex

The unified installer workflow below is under development; see the validation status before choosing an artifact. Once a validated installer is available, choose the setup that matches where your code lives:

• One computer: install WebCodex on your personal workstation, open Desktop, and follow Unified installation. This setup includes Desktop, CLI, Server, and Runner in one platform package.
• Several computers: install the same package on the machine that will host the WebCodex Server and on each machine that owns repositories. Follow Unified installation and Deployment validation.

This branch defines unified Windows NSIS, macOS package, and Debian 12 / Ubuntu 22.04+ .deb installer targets for x64 and arm64. The six installer variants still require native build and installation acceptance before release. Real-machine installation, reboot persistence, GUI behavior, and upgrade have not been accepted across all three platforms; this branch makes no claim of identical cross-platform behavior. Published files are listed in GitHub Releases. The download/ directory contains static page source only; the download-page workflow builds a Release-manifest-based GitHub Actions artifact after publication, but does not host or deploy a page. For a source preview, check out the exact feature or release revision you intend to evaluate and follow Desktop development.

For temporary one-repository trials, advanced self-hosting, npm/runtime archives, Docker, or historical release artifacts, see Deployment.

What can it do?

• Understand and edit code — read, search, inspect, and make guarded changes inside configured projects.
• Use the real toolchain — run commands, tests, formatters, compilers, and project-specific tooling on the machine that owns the repository.
• Work with Git — inspect status and diffs while keeping repository operations visible and reviewable.
• Handle long-running work — keep jobs observable instead of requiring one model turn to stay open indefinitely.
• Support human review — use the Runtime Console, Workflow Session evidence, Jobs, and Git/diff review without a separate task/result acceptance subsystem.

Why WebCodex?

• Your code stays on your machine. The repository does not need to be copied into the chat service.
• The agent gets a real development environment. It can use the same files, Git checkout, compilers, tests, and tools you already use.
• Work survives beyond a single request. Long-running execution and evidence remain observable through WebCodex.
• Start temporary or run it long-term. Use one-command sharing for a quick session, or connect machines to a self-hosted Server for a durable setup.

How it works

AI client
   |
   | MCP / HTTPS
   v
WebCodex
   |
   v
your machine
   |
   +-- repository
   +-- Git
   +-- compilers / tests / developer tools

For the internal Server/Runner architecture, protocol surfaces, and authority boundaries, see Architecture, MCP, and Authentication.

Star History

This chart tracks the upstream yyjeqhc/webcodex repository.

Platform packages

The unified installer targets Windows NSIS, macOS, and Debian 12 / Ubuntu 22.04+ .deb on x64 and arm64. The branch defines the build pipeline; the six installer variants still require native build and installation acceptance before release. See Unified installation and the validation checklist. Existing release artifacts and npm/Docker deployment paths remain documented as advanced historical/current compatibility references in Deployment.

Documentation

• Unified installation — personal and multi-computer setup for the unified package
• Deployment validation — platform acceptance status and required native checks
• Legacy Desktop installation — existing release-specific detailed guide
• Using Desktop — projects, connections, activity, and background operation
• Desktop development — run from source on Linux, Windows, and macOS; build local packages
• Full Setup — CLI, existing Server, Linux, and advanced regular Server + Runner setup
• Quick Trial — temporarily try one repository with share
• MCP — ChatGPT, Claude, authentication choices, and MCP reference
• Deployment — production, self-hosting, and advanced operations
• Troubleshooting — ChatGPT/MCP Host, connection, and runtime problems
• CLI — command and credential reference
• AI-assisted setup — have an AI agent help configure WebCodex
• Security — security model and operational guidance
• Documentation index — all user and contributor documentation

Security

WebCodex can read and modify files and execute commands inside configured project boundaries. Use version control, keep credentials out of prompts/logs/Git, and register only project roots the assistant should access. Tool results, including requested file excerpts, may be returned to the AI client. Read SECURITY.md for the complete model.

Build from source

If a release has a problem, you do not need to wait for a maintainer to produce a new build. Reproducing the issue on current main, testing a focused fix locally, and submitting the result as a pull request are all welcome.

For CLI / Server / Runner development, install Git and the stable Rust toolchain through rustup, then build the normal dogfood profile:

cargo build --locked --profile dogfood --workspace --bins

The binaries are written under target/dogfood/. For Desktop/frontend work, also install Node.js 22 + npm and the native platform toolchain. Windows Desktop development needs an MSVC/Windows SDK environment; macOS development needs Xcode Command Line Tools. The complete prerequisites and source-build workflow are in the Desktop development guide.

For local Desktop installer testing, use the repository helpers rather than a raw Tauri bundle command:

# Windows: clean committed source
.\scripts\build_desktop_windows_local.ps1

# Windows: explicitly package uncommitted local work as dirty dogfood
.\scripts\build_desktop_windows_local.ps1 -AllowDirty

# macOS
bash scripts/build_desktop_macos_local.sh

These are development/dogfood builds, not public release artifacts.

Contributing

Issues and focused pull requests are welcome. Maintainer response time may vary, so users who can reproduce a problem on current main are especially encouraged to investigate it, build and test a fix locally, and submit a PR rather than waiting for the fix to be implemented upstream. WebCodex itself, Codex, ChatGPT, Claude, or other coding agents may be used to help inspect, edit, and validate the repository.

For what to include in a bug report, the self-service fix workflow, validation expectations, and pull request guidance, see CONTRIBUTING.md.

Acknowledgements

Thanks to the LINUX DO community for its welcoming space for technical discussion and support for open-source sharing.

License

Licensed under the Apache License, Version 2.0. See LICENSE.

Desktop Shell and Runtime upgrades

Desktop can keep its existing shell while using a separately selected compatible Runtime folder. Build revisions and package versions are diagnostic identity, not compatibility gates. See Desktop Runtime compatibility for custom builds, safe switching/rollback, diagnostics, tracing and update notifications.