Skip to main content

Baponi sandbox provider for LangChain Deep Agents

Project description

langchain-baponi

Baponi sandbox provider for LangChain Deep Agents.

Baponi runs your Deep Agent's code in isolated sandboxes, available as a managed cloud service or self-hosted inside your own Kubernetes cluster or VPC. Sandboxes have no network access by default, with egress opt-in.

This package is a thin wrapper: it installs baponi[deepagents], which registers the baponi sandbox provider for the Deep Agents Code CLI. You can also use baponi[deepagents] directly.

Install

pip install langchain-baponi

Use with Deep Agents

from langchain_baponi import BaponiSandbox
from deepagents import create_deep_agent

with BaponiSandbox() as sandbox:  # reads BAPONI_API_KEY
    agent = create_deep_agent("anthropic:claude-sonnet-4-6", backend=sandbox)
    result = agent.invoke({"messages": [{"role": "user", "content": "Analyze this dataset and summarize it"}]})
    print(result["messages"][-1].content)

Use with Deep Agents Code (dcode)

dcode --install langchain-baponi --package
export BAPONI_API_KEY=sk-...
dcode --sandbox baponi

Get an API key at console.baponi.ai. Full guide: baponi.ai/docs/guides/deep-agents.

License

Apache-2.0

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

langchain_baponi-0.1.1.tar.gz (7.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

langchain_baponi-0.1.1-py3-none-any.whl (6.5 kB view details)

Uploaded Python 3

File details

Details for the file langchain_baponi-0.1.1.tar.gz.

File metadata

  • Download URL: langchain_baponi-0.1.1.tar.gz
  • Upload date:
  • Size: 7.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.9.7

File hashes

Hashes for langchain_baponi-0.1.1.tar.gz
Algorithm Hash digest
SHA256 9eb3ab238e8b1d7ae89f16d70d67bf6eeb79f71d995e6dabe546b099c57a7fd6
MD5 f86a1c7d3861163b4493b36091bab5c9
BLAKE2b-256 0109778e391f4dd984460ee0f8894137885ff3f1ee685931182f647d7fb08912

See more details on using hashes here.

File details

Details for the file langchain_baponi-0.1.1-py3-none-any.whl.

File metadata

File hashes

Hashes for langchain_baponi-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 48d2d550b3ce384256f9e3410b48a3940e249d85813c744f763aefa6b0ab759a
MD5 68b7f065f21febf7f0dfad3a3b3e1259
BLAKE2b-256 0d259a92d2943b01da3f5f8ae97aebeb94640883c2da68fa82cef3f5d4d59f78

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page