bot-bottle/README.md

<p align="center">
  <img src="docs/logo.svg" alt="claude-bottle logo" width="140">
</p>

# claude-bottle

[![test](https://gitea.dideric.is/didericis/claude-bottle/actions/workflows/test.yml/badge.svg?branch=main)](https://gitea.dideric.is/didericis/claude-bottle/actions?workflow=test.yml)

Run multiple Claude Code agents on your own machine, each scoped to its own secrets, skills, and egress allowlist.

![pipelock and git-gate blocking exfil attempts against a live bottle](docs/demo.gif)

Four prompts to the agent inside a real bottle:
claude replies to `hello there` — proof api.anthropic.com routes
through pipelock's bumped TLS end-to-end;
asked to GET a non-allowlisted host, the agent's curl gets 403 back
from pipelock;
asked to POST a credential-shaped body to an allowlisted host, the
same 403 — pipelock's DLP body scanner caught it;
asked to commit and push an AKIA-shaped key, git-gate's gitleaks
pre-receive hook rejects the ref.
Run it yourself with `bash scripts/demo.sh`.

## Why "claude-bottle"?

Each container is a bottle; Claude is the genie inside. The genie's
powers are exactly what the manifest grants it — a specific set of
skills, a specific set of secrets, and a specific set of hosts it can
reach — nothing more. You uncork one bottle per agent
(`./cli.py start <agent>`), many bottles run in parallel, and each is
scoped to its task. When the session ends the bottle is destroyed and
the genie does not persist.

## Goals

- Scope each agent to the minimum credentials and network egress its task actually needs
- Run multiple agents in parallel, isolated from each other
- Keep code, credentials, and agent activity on infrastructure I control — no third-party agent runtime

## Security model

Each agent runs in its own bottle: its own container, its own internal
Docker network, and its own pipelock sidecar. Bottles don't share
state, don't talk to each other, and only get the env vars, skills,
SSH identities, and egress hosts the manifest grants them — nothing
more. Any one agent only has the access it needs to do its job.

The bottle limits both what an agent can see and where it can send
it. Each bottle gets only the secrets and SSH identities the manifest
grants it — a Gitea token but not a GitHub token, a deploy key but
not a personal SSH key — so even a compromised or misbehaving agent
only handles credentials it was already trusted with for its job.
Egress flows through pipelock, which constrains where those
credentials can travel: an agent with a Gitea token can reach
`gitea.dideric.is`, not arbitrary attacker-controlled hosts. The same
constraint blocks DNS-over-HTTPS as an exfil channel — a DoH resolver
like `cloudflare-dns.com` would have to be on the allowlist for the
agent to reach it at all. The container itself adds a layer between
the agent and the host, but the v1 design leans more on secret
minimization and egress allowlisting than on the container as a
hardened boundary. On Linux hosts where [gVisor](https://gvisor.dev/)
is registered with Docker, claude-bottle auto-detects it and launches
every bottle under `runsc` for a userspace syscall barrier — no
manifest configuration required. The broader v2 discussion lives in
`docs/research/stronger-isolation-alternatives.md`.

The egress proxy and OAuth-token handling below are the load-bearing
pieces of v1.

## Architecture

A bottle is the agent container plus up to three per-protocol egress
sidecars on a per-agent Docker `--internal` network. The agent has no
default route off-box; its only way out is through the pipelock
sidecar (for HTTP/HTTPS), the git-gate sidecar (for git operations
against declared upstreams), or the cred-proxy sidecar (for API
calls that need a manifest-declared token — Anthropic OAuth, GitHub
PAT, Gitea PAT, npm). Each sidecar also sits on an egress network
that does have internet access, so the agent's traffic always passes
through a container that enforces the manifest before it leaves the
host.

```
                            host  ( ./cli.py )
                                  │
                          starts  │  stops
                                  ▼
   ┌─────────────────────────── bottle ──────────────────────────┐
   │                                                             │
   │   ┌──────────────────┐                                      │
   │   │ agent image      │   HTTPS_PROXY    ┌────────────────┐  │  HTTPS to
   │   │ (claude-code,    │ ───────────────► │ pipelock image │──┼──►  allowlisted
   │   │  built locally)  │                  │ (TLS bump, DLP,│  │     hosts
   │   │                  │                  │  allowlist)    │  │
   │   │ skills, env,     │                  └────────────────┘  │
   │   │ ~/.gitconfig,    │                                      │
   │   │ ~/.npmrc, tea    │   git ops        ┌────────────────┐  │  SSH (push/
   │   │                  │ ───────────────► │ git-gate image │──┼──►  fetch) to
   │   │                  │                  │ (gitleaks +    │  │     bottle.git
   │   │ environ: URLs    │                  │  git daemon)   │  │     upstreams
   │   │ only, no real    │                  └────────────────┘  │
   │   │ tokens           │   bearer-auth    ┌────────────────┐  │  HTTPS to
   │   │                  │ ───────────────► │ cred-proxy     │──┼──►  bottle.tokens
   │   │                  │  HTTP, plain     │ (strips/injects│  │     upstreams
   │   │                  │                  │  Authorization)│  │     (with the
   │   └──────────────────┘                  └────────────────┘  │     real token)
   │                                                             │
   │   agent on internal network (no default route);             │
   │   sidecars also attached to an egress network.              │
   └─────────────────────────────────────────────────────────────┘
```

- **agent image** — built from the repo `Dockerfile` (`node:22-slim`
  base) on first run; runs `claude` with the manifest-granted skills,
  env vars, and `~/.gitconfig` (the latter for the git-gate's
  `insteadOf` rules when `bottle.git` is set).
- **pipelock image** — per-agent sidecar. Terminates the agent's
  outbound HTTP/HTTPS, enforces the resolved allowlist, runs DLP
  scanning. Design in `docs/prds/0001-per-agent-egress-proxy-via-pipelock.md`
  and `docs/prds/0006-pipelock-tls-interception.md`.
- **git-gate image** — per-agent sidecar built on `zricethezav/gitleaks`
  (alpine + gitleaks + git-daemon + openssh-client). Runs
  `git daemon` over `git://` as a bidirectional mirror of each
  declared upstream. A pre-receive hook gitleaks-scans incoming
  refs and forwards clean refs to the real upstream over SSH; an
  access-hook runs `git fetch origin --prune` against the upstream
  before every upload-pack so an agent fetch returns whatever the
  upstream has *now* (fail-closed if unreachable). The agent's
  `~/.gitconfig` rewrites the real URL to the gate via `insteadOf`,
  so push, fetch, clone, and pull all route through. The agent
  never sees the upstream credential. If the upstream's hostname
  isn't resolvable from the gate container (e.g. a Tailscale-only
  host whose public DNS points elsewhere), pin its IP via
  `ExtraHosts: { "<hostname>": "<ip>" }` on the `bottle.git` entry —
  the gate's `/etc/hosts` gets the override while the agent's
  `insteadOf` rewrite still keys off the original hostname. Brought
  up only when `bottle.git` has entries. Design in
  `docs/prds/0008-git-gate.md`.
- **cred-proxy image** — per-bottle sidecar (`python:3.13-alpine`
  base, stdlib-only) that holds API tokens declared in
  `bottle.cred_proxy.routes`. Each route names a `path`,
  `upstream`, `auth_scheme`, and `token_ref` (host env var); the
  agent dials `http://cred-proxy:9099<path>...` over plain HTTP
  and the proxy strips any inbound `Authorization`, injects
  `<auth_scheme> <token>` using the value held only in its own
  container's environ, and forwards to the real upstream over
  HTTPS. SSE responses stream back unbuffered. The cred-proxy's
  outbound HTTPS routes through pipelock (it trusts pipelock's
  per-bottle CA), so pipelock's egress allowlist + body scanner
  apply to cred-proxy traffic the same way they apply to direct
  agent traffic. Smart-HTTP push paths (`/git-receive-pack`,
  `/info/refs?service=git-receive-pack`) are refused at the
  proxy — push must go through `bottle.git` / git-gate where
  gitleaks runs. Optional per-route `role` tags drive agent-side
  rewrites: `anthropic-base-url`, `npm-registry`, `git-insteadof`,
  `tea-login`. The agent's `printenv` shows only proxy URLs —
  none of the real token values. Design in
  `docs/prds/0010-cred-proxy.md`.

When the agent exits, `cli.py` tears down every sidecar that was
brought up and the two networks; nothing about a bottle persists
between runs.

## Quickstart

Requires Docker on the host and a long-lived Claude Code OAuth token in
your shell env.

```sh
./cli.py start <agent>   # builds the image on first run, drops you into claude
```

The container is removed automatically when the session ends. If the script
is killed with SIGKILL the exit trap won't fire and the container may be
left running; remove it with `docker rm -f <container-name>`.

## Manifest

Agents and the bottles they run in are declared in `claude-bottle.json`
in your project root or `$HOME` (both files merge if present, with
project entries overriding home entries on key conflict).

```jsonc
{
  "bottles": {
    "gitea-dev": {
      "env": {
        "GITEA_TOKEN":     "?paste your Gitea API token",
        "GITHUB_TOKEN":    "${GH_PAT}",
        "GIT_AUTHOR_NAME": "didericis"
      },

      "git": [
        {
          "Name":         "claude-bottle",
          "Upstream":     "ssh://git@gitea.dideric.is:30009/didericis/claude-bottle.git",
          "IdentityFile": "/Users/didericis/.ssh/id_ed25519_gitea",
          "KnownHostKey": "ssh-ed25519 AAAA..."
        }
      ],

      // Routes declared here are held by a per-bottle cred-proxy
      // sidecar, not the agent. Each route names a path the agent
      // dials, the upstream the proxy forwards to, an auth_scheme,
      // and a token_ref (host env var). The value goes into the
      // sidecar's environ via `docker create -e`, never touches
      // argv or disk. Optional `role` tags drive agent-side
      // rewrites: `anthropic-base-url` (sets ANTHROPIC_BASE_URL),
      // `npm-registry` (writes ~/.npmrc), `git-insteadof` (writes
      // ~/.gitconfig), `tea-login` (writes ~/.config/tea/config.yml).
      // See `docs/prds/0010-cred-proxy.md`.
      "cred_proxy": {
        "routes": [
          { "path": "/anthropic/", "upstream": "https://api.anthropic.com",
            "auth_scheme": "Bearer", "token_ref": "CLAUDE_BOTTLE_OAUTH_TOKEN",
            "role": "anthropic-base-url" },
          { "path": "/gh-api/", "upstream": "https://api.github.com",
            "auth_scheme": "Bearer", "token_ref": "GITHUB_PAT" },
          { "path": "/gh-git/", "upstream": "https://github.com",
            "auth_scheme": "Bearer", "token_ref": "GITHUB_PAT",
            "role": "git-insteadof" },
          { "path": "/npm/", "upstream": "https://registry.npmjs.org",
            "auth_scheme": "Bearer", "token_ref": "NPM_TOKEN",
            "role": "npm-registry" }
        ]
      },

      // Egress is forced through a per-agent
      // [pipelock](https://github.com/luckyPipewrench/pipelock) sidecar
      // on a Docker `--internal` network — without the proxy the agent
      // has no route off-box. The effective allowlist is the union of
      // baked-in defaults (api.anthropic.com, claude.ai, ...) and the
      // hostnames listed here. Pipelock also runs DLP scanning and
      // detects URL-embedded high-entropy secrets. The resolved
      // allowlist is shown in the y/N preflight before launch.
      "egress": {
        "allowlist": [
          "github.com",
          "registry.npmjs.org",
          "pypi.org"
        ]
      }
    }
  },

  "agents": {
    "gitea-helper": {
      "bottle": "gitea-dev",
      "skills": ["init-prd"],
      "prompt": "You help maintain Gitea-hosted projects."
    }
  }
}
```

Comments are illustrative; the file itself must be valid JSON. See
`claude-bottle.example.json` for a working starting point. Pipelock's
design lives in `docs/prds/0001-per-agent-egress-proxy-via-pipelock.md`
and the rationale in `docs/research/pipelock-assessment.md`.

## Auth: OAuth token, not API key

claude-bottle authenticates `claude` inside the container with the same
Pro/Max subscription you already use on the host, via a long-lived OAuth
token. No `ANTHROPIC_API_KEY` is needed.

**Why a token instead of mounting `~/.claude.json`:** on macOS, Claude
Code stores OAuth credentials in the encrypted Keychain, not in
`~/.claude.json`. Mounting that file into a Linux container does not
carry the credentials with it. Linux hosts keep credentials in
`~/.claude/.credentials.json`, but to keep the launcher portable
claude-bottle uses the env-var path on every host.

**One-time setup on the host:**

```sh
claude setup-token   # browser login, prints a ~1-year OAuth token
```

Stash the token in your shell env (e.g. `~/.zshrc` or a secret manager)
as `CLAUDE_BOTTLE_OAUTH_TOKEN`:

```sh
export CLAUDE_BOTTLE_OAUTH_TOKEN="<token>"
```

By default `cli.py` forwards the token into the agent container as
`CLAUDE_CODE_OAUTH_TOKEN`. Declare a `bottle.cred_proxy.routes` entry
with `role: "anthropic-base-url"` and `token_ref:
"CLAUDE_BOTTLE_OAUTH_TOKEN"` to route via cred-proxy instead: the
token then lives only in the cred-proxy sidecar's environ, the agent's
`ANTHROPIC_BASE_URL` points at the proxy, and `printenv` inside the
agent does not surface the real token. Either way the value is never
written to disk or placed on argv on the host.

Inside the container, `claude` picks up `CLAUDE_CODE_OAUTH_TOKEN` and
authenticates against your subscription. Caveats: the token is bound
to your subscription tier (Pro/Max/Team/Enterprise), it does not work
with `claude --bare` (which only reads `ANTHROPIC_API_KEY`), and if it
leaks, regenerate via `claude setup-token` again. Reference:
<https://code.claude.com/docs/en/authentication>.

## Trademarks

claude-bottle is an independent project and is not affiliated with,
endorsed by, or sponsored by Anthropic, PBC. "Claude" and "Claude
Code" are trademarks of Anthropic, PBC; the project name uses
"claude" descriptively to indicate that the tool runs Claude Code
inside a sandbox.

## License

Copyright 2026 Eric Bauerfeld

Licensed under the Apache License, Version 2.0. See [LICENSE](LICENSE)
for the full text.