|
| 1 | +# deva.sh |
| 2 | + |
| 3 | +> Docker-first launcher for AI coding agents — Claude Code, Codex, Gemini, and Grok. |
| 4 | +> The container is the sandbox, mounts are the explicit contract, and one warm |
| 5 | +> project container serves all four agents. A bash script, not a framework. MIT. |
| 6 | + |
| 7 | +deva.sh is a single entry point installed on the host; agents run inside |
| 8 | +`ghcr.io/thevibeworks/deva` images (`:latest`, `:rust` for stable, `:nightly`, |
| 9 | +`:nightly-rust` refreshed daily). Agent-level permission prompts are disabled by |
| 10 | +design (`claude --dangerously-skip-permissions`, `codex |
| 11 | +--dangerously-bypass-approvals-and-sandbox`, `gemini --yolo`, `grok |
| 12 | +--always-approve`) — isolation comes from Docker, not permission theater. Auth |
| 13 | +lives in per-agent config homes under `~/.config/deva/` with OAuth (default) or |
| 14 | +API-key modes per agent; nothing crosses the host boundary except what you |
| 15 | +mount. Known sharp edge: mounting `/var/run/docker.sock` is host-root with |
| 16 | +extra steps, and deva will tell you so. |
| 17 | + |
| 18 | +Full docs: https://docs.deva.sh — if you can fetch one URL, fetch that one. |
| 19 | + |
| 20 | +## Install |
| 21 | + |
| 22 | +```bash |
| 23 | +curl -fsSL https://raw.githubusercontent.com/thevibeworks/deva/main/install.sh | bash |
| 24 | + |
| 25 | +cd your-project |
| 26 | +deva.sh # Claude Code (the default) |
| 27 | +deva.sh codex # same container shape, other agents |
| 28 | +deva.sh gemini |
| 29 | +deva.sh grok |
| 30 | +deva.sh claude --debug --dry-run # inspect the docker run before trusting it |
| 31 | +``` |
| 32 | + |
| 33 | +## Entry points |
| 34 | + |
| 35 | +- [Quick Start](https://docs.deva.sh/quick-start/): install to first agent run, about 60 seconds |
| 36 | +- [Authentication](https://docs.deva.sh/authentication/): OAuth vs API-key per agent, config homes, auth isolation, what gets masked and why |
| 37 | +- [How It Works](https://docs.deva.sh/how-it-works/): container lifecycle, mount dispatch, config resolution order |
| 38 | +- [Advanced Usage](https://docs.deva.sh/advanced-usage/): extra mounts, env wiring, multiple identities per project |
| 39 | +- [Troubleshooting](https://docs.deva.sh/troubleshooting/): common failures and how to diagnose them |
| 40 | +- [Philosophy](https://docs.deva.sh/philosophy/): why the container is the sandbox and agent permission prompts are theater |
| 41 | +- [Custom Images](https://docs.deva.sh/custom-images/): extending the base image for your stack |
| 42 | +- [Security Policy](https://github.com/thevibeworks/deva/blob/main/SECURITY.md): what deva protects against and what it explicitly does not |
0 commit comments