AI Agent Sandbox · Open Source · Apache 2.0 · ★ Star on GitHub · v0.4.2
Your AI agent can rm -rf / and you're fine.
Auto-approve on your bare machine means the agent sees your SSH keys, other repos,
every credential on disk.
devcell puts a container between your project and everything else.
Your code goes in. Nothing else comes along.
Claude Code · Sonnet 4.6 · Claude Max /myproject
Why it matters
"Run this in a container, not your actual machine."
— Anthropic, Claude Code documentation
SSH keys, other repos, host APIs: unreachable. The agent edits freely inside your project. Your host system stays untouched.
cd my-project && cell claude. Working directory mounted automatically, no per-project config needed. Works with Codex and OpenCode too.
Go, Node.js, Python, Terraform, and more. Nix-pinned at build time. No download URLs that go stale, no version drift between machines.
1Password secrets are resolved on the host, injected into the container as env vars, and written to a RAM-only tmpfs at /run/secrets/. When the container stops, they're gone. The LLM never sees actual credential values -- MCP tools resolve placeholder names server-side.
Not just config stubs. KiCad, Inkscape, and OpenTofu ship in the image alongside their MCP servers, so the agent can actually run tofu plan, analyze PCBs, or edit SVGs. 12 servers today, more with each release.
Anti-fingerprint Chromium with Playwright, ready for scraping and browser automation. Passes bot detection out of the box. Connect via VNC or RDP to watch it work.
Getting started
brew install DimmKirr/tap/devcell. Requires docker.
Platforms: macOS, Linux, Windows(not verified yet)
cd my-project && cell claude. First run picks a stack, scaffolds config, and builds. Works with cell codex and cell opencode too.
What's inside
Everything below ships in the ultimate stack. Pick a focused stack below and get exactly what you need.
Drop a .tool-versions for runtime versions, add packages via config, extend a stack with nix overlays, or fork nixhome and build your own. Upstream updates still merge cleanly.
Image stacks
Need a different mix? Set stack and modules in your devcell.toml to combine what you need.
| base | go | node | python | fullstack | electronics | ultimate | |
|---|---|---|---|---|---|---|---|
| Dev essentials | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| Go environment | — | ✓ | — | — | ✓ | — | ✓ |
| Node.js environment | — | — | ✓ | — | ✓ | — | ✓ |
| Python environment | — | — | — | ✓ | ✓ | — | ✓ |
| Infra tools | — | ✓ | — | — | ✓ | — | ✓ |
| Stealth browser | — | — | ✓* | ✓* | ✓* | — | ✓ |
| Electronics & DIY | — | — | — | — | — | ✓ | ✓ |
| GUI desktop | — | — | — | — | — | ✓ | ✓ |
| 12+ MCP servers | — | — | — | — | — | — | ✓ |
* Headless only. GUI desktop (VNC/RDP) available in electronics and ultimate stacks.
Multi-arch: linux/amd64 and linux/arm64. Published to ghcr.io/dimmkirr/devcell.
Base nix image size ~1.3 GB.
Common questions
Bring your own license or model. Claude Max, Pro, and API keys all work — devcell starts the same client you already use, just inside a container. Same goes for Codex and OpenCode.
Dev Containers are editor-first — you write a Dockerfile + devcontainer.json per project for VS Code or GitHub Codespaces. DevCell is agent-first: one command, 7 pre-built Nix-pinned stacks, 12+ MCP servers auto-merged at startup, stealth Chromium + Playwright, VNC/RDP built in, and 1Password secret injection. No per-project Dockerfile maintenance.
OpenClaw is a multi-channel messaging gateway (WhatsApp, Telegram, Slack) with AI features. DevCell is a sandboxed coding environment for AI agents. Key differences: DevCell has mandatory container isolation (OpenClaw is network-exposed by default with multiple critical CVEs in 2026), curated MCP servers with backing tools shipped in the image (OpenClaw has an open marketplace with 1,184 malicious skills found), and Claude Max/Pro subscriptions work directly (OpenClaw requires API keys since Anthropic blocked subscription auth in Jan 2026).
Yes. The agent can run apt, npm install, pip install, nix — whatever the project needs. Network access is unrestricted. Port forwarding and extra volume mounts are configurable in devcell.toml.
Permissions are pass-through. The container user matches your host UID, so files the agent creates are owned by you. No chown headaches.
Your project-level config (CLAUDE.md, .claude/) is mounted with your project. Host ~/.claude/skills is mounted read-write, the rest of ~/.claude is read-only. Your host-machine config stays safe. (Subject to change.)
You can. devcell saves you from maintaining a Dockerfile per project, wiring up MCP server configs, forwarding git identity, injecting secrets, and setting up entrypoint orchestration. One command instead of 20 minutes of Docker plumbing.
Base is ~1.3 GB, ultimate is ~20 GB. First run lets you pick a stack and builds automatically. Base builds in under 2 minutes, ultimate takes ~5 minutes.
Get started
One command. Pick your stack on first run.