Files
bot-bottle/README.md
T
didericis ccfdb141dd
test / unit (pull_request) Successful in 13s
test / integration (pull_request) Successful in 22s
feat(manifest)!: enforce cwd-manifest trust boundary (PRD 0011)
Splits `Manifest.resolve` into a two-phase load:

1. $HOME/claude-bottle.json parses under the full schema as today.
   This file owns bottle infrastructure (cred_proxy.routes, git,
   env, egress).
2. $CWD/claude-bottle.json parses under the new CwdExtension schema
   — agents-only. Any `bottles:` section dies at parse with a
   pointer at the home file. Each cwd agent's `bottle:` must
   resolve against a home-defined bottle name.

When CWD == HOME (running from $HOME directly) the resolver
short-circuits to home-only — no false trust-boundary error from
parsing the same file twice.

Closes the exfil vector documented in PRD 0011: a cloned repo's
claude-bottle.json can no longer redefine cred-proxy routes, and
therefore can't redirect $CLAUDE_BOTTLE_OAUTH_TOKEN /
$GITHUB_TOKEN / etc. to an attacker-named upstream on first
launch.

Preflight surfaces the boundary positively: print() shows
`bottle: <name>  (from $HOME/claude-bottle.json)`, and to_dict
emits `"bottle_source": "home"`. README + the existing dry-run
integration test pick that up.

BREAKING: existing cwd manifests that define bottles now fail.
The error message names the file path, the offending field, and
the fix ("move bottles section to $HOME/claude-bottle.json").

Tests:
- tests/unit/test_manifest_trust_boundary.py — 10 cases covering
  PRD 0011's success criteria (bottles rejected, agents allowed,
  cwd overrides agent fields, no silent fallback, home-only
  unchanged, etc.).
- tests/integration/test_dry_run_plan.py picks up the
  bottle_source assertion.
2026-05-24 15:22:58 -04:00

382 lines
18 KiB
Markdown

<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. All HTTP and HTTPS egress — from the agent
*and* from cred-proxy when it dials an upstream — funnels through
pipelock, where the egress allowlist, TLS interception, and
request-body DLP scanner enforce the manifest before any byte leaves
the host. The only egress that doesn't traverse pipelock is git-gate's
SSH push/fetch to `bottle.git` upstreams — pipelock can't proxy SSH,
so git-gate is its own L4-style egress path with gitleaks doing the
pre-receive scan.
```
host ( ./cli.py )
starts │ stops
┌─────────────────────────── bottle ──────────────────────────────────┐
│ │
│ ┌──────────────────┐ │
│ │ agent image │ HTTPS_PROXY │
│ │ (claude-code, │ ────────────────────────┐ │
│ │ built locally) │ │ │
│ │ │ plain HTTP │ │
│ │ skills, env, │ (token injection) ┌────▼─────────┐ │
│ │ ~/.gitconfig, │ ──────────────────►│ cred-proxy │ │
│ │ ~/.npmrc, tea │ │ (strips/inj │ │
│ │ │ │ Authoriz.) │ │
│ │ environ: URLs │ └─────┬────────┘ │
│ │ only, no real │ HTTPS_PROXY │ │
│ │ tokens │ ▼ │
│ │ │ ┌────────────────┐ │ HTTPS to
│ │ │ │ pipelock image │──────────┼──► allowlisted
│ │ │ │ (TLS bump, DLP │ │ hosts (incl.
│ │ │ │ body scan, │ │ cred-proxy
│ │ │ │ allowlist) │ │ upstreams)
│ │ │ └────────────────┘ │
│ │ │ │
│ │ │ git:// ┌────────────────┐ │ SSH push/fetch
│ │ │ ────────────────►│ git-gate image │──────────┼──► to bottle.git
│ │ │ │ (gitleaks + │ │ upstreams
│ └──────────────────┘ │ git daemon) │ │ (direct — not
│ └────────────────┘ │ via pipelock)
│ │
│ agent on internal network (no default route); pipelock, │
│ cred-proxy, and git-gate straddle internal + egress networks. │
│ pipelock is the single HTTP/HTTPS chokepoint — cred-proxy's │
│ outbound traverses it too. git-gate's SSH egress is direct │
│ because pipelock is HTTP-only. │
└─────────────────────────────────────────────────────────────────────┘
```
- **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
Two locations, two roles (PRD 0011):
- **`$HOME/claude-bottle.json`** — owns *bottles*. Defines the
per-bottle infrastructure: `cred_proxy.routes` (which API tokens
the bottle holds, pointing at host env vars), `git` (SSH upstreams
+ identity files), `env` (literal/interpolated values), `egress`
(pipelock's allowlist + DLP action). This is your trusted file.
- **`$CWD/claude-bottle.json`** *(optional)* — declares *agents*
that reference home-defined bottles. Useful for shipping a
repo-specific prompt or skill list with a project. A cwd manifest
that tries to define `bottles:` dies at parse with a pointer at
this rule.
The boundary is intentional: a cloned repo's `claude-bottle.json`
cannot redirect your `CLAUDE_BOTTLE_OAUTH_TOKEN` / `GITHUB_TOKEN`
to an attacker-named upstream, because it cannot define
infrastructure — only your home file can, and it lives on your
own machine. The y/N preflight prints
`bottle: <name> (from $HOME/claude-bottle.json)` as a positive
audit signal.
The full schema lives in `$HOME`:
```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 — copy it
to `$HOME/claude-bottle.json`, not into the repo you're working in.
A repo can add its own `claude-bottle.json` that declares only
`agents:`, each referencing a bottle name from `$HOME`:
```jsonc
// $CWD/claude-bottle.json — repo-shipped agents, no bottles
{
"agents": {
"implementer": {
"bottle": "gitea-dev",
"skills": ["init-prd"],
"prompt": "Implement features against this repo's PRDs..."
}
}
}
```
Pipelock's design lives in
`docs/prds/0001-per-agent-egress-proxy-via-pipelock.md` and the
rationale in `docs/research/pipelock-assessment.md`. The trust
boundary rationale lives in
`docs/prds/0011-cwd-manifest-trust-boundary.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>"
```
The bottle reaches the Anthropic API only through the cred-proxy
sidecar. To let `claude` authenticate, declare a route in
`bottle.cred_proxy.routes` with `role: "anthropic-base-url"` and
`token_ref: "CLAUDE_BOTTLE_OAUTH_TOKEN"`:
```jsonc
{
"path": "/anthropic/",
"upstream": "https://api.anthropic.com",
"auth_scheme": "Bearer",
"token_ref": "CLAUDE_BOTTLE_OAUTH_TOKEN",
"role": "anthropic-base-url"
}
```
At launch, `cli.py` reads `CLAUDE_BOTTLE_OAUTH_TOKEN` from the host
env and forwards it into the cred-proxy container's environ — never
into the agent's. The agent receives `ANTHROPIC_BASE_URL` pointing at
`http://cred-proxy:9099/anthropic` and a non-secret placeholder for
`CLAUDE_CODE_OAUTH_TOKEN` (claude-code refuses to start without one;
the proxy strips and replaces the header on every request). `printenv`
inside the agent does not surface the real token, and the value is
never written to disk or placed on argv on the host.
A bottle without an `anthropic-base-url` route has no path to the
Anthropic API — there is no fallback that forwards the token directly
to the agent. 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.