langchain-maritime
Run Deep Agents on a real cloud computer from Maritime.
Every file read, edit, search and shell command happens in the agent's own Linux sandbox, never on your machine.
Quickstart · Deep Agents Code · Options · Tested · More agents on Maritime
Quickstart
pip install langchain-maritime langchain-openai
export MARITIME_API_KEY=mk_... # maritime.sh/settings/api-keys
export OPENAI_API_KEY=sk-...
from deepagents import create_deep_agent
from langchain_openai import ChatOpenAI
from langchain_maritime import MaritimeSandbox
backend = MaritimeSandbox.create(idle_timeout_seconds=600)
try:
agent = create_deep_agent(model=ChatOpenAI(model="gpt-5.4"), backend=backend)
result = agent.invoke(
{
"messages": [
{
"role": "user",
"content": "Write primes.py that prints 10 primes, run it, show me the output.",
}
]
}
)
print(result["messages"][-1].content)
finally:
backend.kill()
MaritimeSandbox.create() starts a fresh sandbox in a few seconds. The agent's ls, read_file, write_file, edit_file, glob, grep and execute tools all run inside it.
Already have a sandbox? Wrap it:
from maritime import Maritime
sandbox = Maritime().sandboxes.get("sbx-...")
backend = MaritimeSandbox(sandbox=sandbox)
The runnable version is examples/deep_agent.py. No OpenAI account? Maritime LLM is OpenAI-compatible: set OPENAI_BASE_URL=https://api.maritime.sh/api/llm/v1 and use your Maritime LLM token as OPENAI_API_KEY.
Deep Agents Code
Installing this package adds a maritime sandbox to Deep Agents Code. No config needed:
dcode install langchain-maritime --package
export MARITIME_API_KEY=mk_...
dcode --sandbox maritime
Deep Agents Code starts a sandbox for the session, works in /home/user, and ends the sandbox when you quit. To keep working in the same machine, pass its id with --sandbox-id sbx-.... To start from a snapshot you saved, pass --sandbox-snapshot-name my-snapshot.
To set Maritime options for every session, declare the provider in ~/.deepagents/config.toml. Deep Agents Code reads params only from a declared provider, so keep the first three lines:
[sandboxes.providers.maritime]
class_path = "langchain_maritime.dcode:MaritimeProvider"
working_dir = "/home/user"
supports_snapshot_name = true
[sandboxes.providers.maritime.params]
size = "large"
idle_timeout_seconds = 3600
What the agent gets
- Its own Linux machine. Ubuntu 24.04 with Python 3.12, Node, git and curl, 2 vCPUs, 4 GiB of memory and 12 GiB of disk by default, up to 16 vCPUs and 64 GiB.
- Real isolation. Each sandbox is a microVM with its own kernel, filesystem, network and processes.
- Root when it needs it. Commands run as
user, with passwordlesssudofor installs. - Limits that clean up after you. An idle timeout pauses or ends a forgotten sandbox, and
time_limit_secondsends it no matter what.
Options
MaritimeSandbox.create() takes any Maritime sandbox option:
| Option | Default | What it does |
|---|---|---|
from_ |
base |
A saved snapshot, a template, or a public image to start from. |
size |
small |
A preset: small, medium, large or xlarge. |
vcpu, memory_mib, disk_gib |
from size |
Override the preset. |
env |
none | Environment variables for every command. |
idle_timeout_seconds |
Maritime's default | How long without activity before on_idle applies. |
on_idle |
pause |
pause keeps the disk and resumes on the next call. kill ends the sandbox. |
time_limit_seconds |
none | End the sandbox this long after it starts. |
metadata |
none | Labels you can filter on when you list sandboxes. |
The backend itself takes timeout, the default seconds a command may run (30 minutes). A timeout of 0 waits as long as Maritime allows.
Behavior
- Commands run with
bash -lc. Output is stdout followed by<stderr>...</stderr>when there is any. - A command that runs out of time returns exit code
124with the output it printed so far. - File errors use Deep Agents' codes (
file_not_found,is_directory,invalid_path,permission_denied). Anything else, such as an ended sandbox or a billing limit, keeps Maritime's own message so the agent sees what really went wrong. - Maritime's file API acts as the machine's administrator, so
download_filescan read a file the shell user cannot.
Tested
The Deep Agents standard sandbox suite runs against a real Maritime sandbox:
MARITIME_API_KEY=mk_... uv run pytest -m live
On 2026-11-17, with deepagents 0.7.39, maritime 0.12 and langchain-tests 1.1.9, 77 of the 86 standard tests pass. The other 9 are marked as expected failures in conftest.py, each with its reason:
- 7 glob and write tests:
langchain-tests1.1.9 expects relative glob paths and awritethat refuses existing files, whiledeepagents0.7.x returns absolute paths and overwrites. A plain localBaseSandboxfails them the same way. - 2 large-output tests call
python, and the Maritime base image shipspython3only.
The live tests also cover the Deep Agents Code provider: create, reconnect by id, delete, and a new sandbox from a saved snapshot.
The unit tests run without an account. They swap only the network calls, so commands really run and Deep Agents' read, write, edit and ls helpers execute for real:
uv run pytest
Compatibility
| Package | Versions |
|---|---|
| Python | 3.11 to 3.14 |
deepagents |
0.7.34 and later 0.7.x |
deepagents-code (optional) |
0.2.5 and later, on Python 3.14 |
maritime |
0.11.x and 0.12.x |
License
Metadata
Release files for langchain-maritime 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| langchain_maritime-0.1.0.tar.gz | 14.9 kB | Without provenance | Details for langchain_maritime-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| langchain_maritime-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for langchain_maritime-0.1.0-py3-none-any.whl |
Total release size: 25.8 kB
Release files / langchain_maritime-0.1.0.tar.gz
| Download URL | langchain_maritime-0.1.0.tar.gz |
|---|---|
| Size | 14.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
17a06eca15bc19378111aecf30eceddd9f87dc1ff927140c60115b4554e73d0a
|
|
BLAKE2b-256 checksum How to use checksums |
ddfe530307d2febfae24e919a52f57cf0d3d90ca46ae19e48b8b0e9d0fd68bca
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.6.11
|
Release files / langchain_maritime-0.1.0-py3-none-any.whl
| Download URL | langchain_maritime-0.1.0-py3-none-any.whl |
|---|---|
| Size | 11.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
66a2fcf413b089698d905d783298cfa510015901794975de43f3b365ce2b0824
|
|
BLAKE2b-256 checksum How to use checksums |
165e4f5740773ad9f5567c1b2469ec1f65209c6b03e6d469ed1ff98a892e5bce
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.6.11
|
Security for langchain-maritime 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.