Skip to main content

CLI and SDK for Superserve hosted agent infrastructure

Project description





Deploy AI agents to sandboxed cloud containers. One command, no infrastructure config.

Docs License Python Discord

Features

  • Sandboxed execution — Every agent runs in a gVisor-isolated container with its own compute, filesystem, and network
  • Persistent workspace — Storage that survives restarts. Agents pick up where they left off
  • Encrypted secrets — API keys are encrypted and injected at runtime. Values are never exposed
  • Real-time streaming — Stream tokens and tool calls as they happen
  • Sub-second cold starts — Pre-provisioned containers mean your agent starts almost instantly
  • Built for Claude Agent SDK — Write with the Claude Agent SDK, deploy with Superserve

Quick Start

pip install superserve
superserve login

Initialize from the root of your project where your dependencies and agent code live:

superserve init

This creates a superserve.yaml:

name: my-agent
command: python main.py  # edit to match your agent's start command

Deploy:

superserve deploy

Set your secrets:

superserve secrets set my-agent ANTHROPIC_API_KEY=sk-ant-...

Run your agent:

superserve run my-agent
You > What is the capital of France?

Agent > The capital of France is Paris.

Completed in 1.2s

You > And what's its population?

Agent > Paris has approximately 2.1 million people in the city proper.

Completed in 0.8s

CLI Reference

Command Description
superserve login Authenticate with Superserve
superserve init Generate superserve.yaml for your project
superserve deploy Deploy your agent
superserve run AGENT Run an interactive session
superserve secrets set AGENT KEY=VALUE Set encrypted environment variables
superserve secrets list AGENT List secret key names
superserve agents list List deployed agents
superserve agents get AGENT Get agent details
superserve agents delete AGENT Delete an agent
superserve sessions list List sessions

See the full CLI Reference for all flags and options.

Requirements

Contributing

Contributions are welcome! See CONTRIBUTING.md for guidelines.

License

This project is licensed under the Open Core Ventures Source Available License (OCVSAL) 1.0 - see the LICENSE file for details.


If you find Superserve useful, please consider giving us a star!

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

superserve-0.1.5.tar.gz (38.0 kB view details)

Uploaded Source

Built Distribution

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

superserve-0.1.5-py3-none-any.whl (37.0 kB view details)

Uploaded Python 3

File details

Details for the file superserve-0.1.5.tar.gz.

File metadata

  • Download URL: superserve-0.1.5.tar.gz
  • Upload date:
  • Size: 38.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.0

File hashes

Hashes for superserve-0.1.5.tar.gz
Algorithm Hash digest
SHA256 20c2d659224b9f71e550cbf831a4e71a44cf26fae1bb8e793b0b2baeab8f287c
MD5 54604fc8bbe8210d288aa9956330eec2
BLAKE2b-256 e8208761a9d996f9cf98197fb87dfdc39db0f65c71c544683faadfdbfc613914

See more details on using hashes here.

File details

Details for the file superserve-0.1.5-py3-none-any.whl.

File metadata

  • Download URL: superserve-0.1.5-py3-none-any.whl
  • Upload date:
  • Size: 37.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.0

File hashes

Hashes for superserve-0.1.5-py3-none-any.whl
Algorithm Hash digest
SHA256 44f54e0c7de33df78653e8cd9ac37b7f3f1d4c50ffed3fc35402f46a973b6d8f
MD5 851ae2030e236ebaec3c6c98582c4cb3
BLAKE2b-256 e48c31bf2a4aa170f4e07794901536be73750a0e272577ef0d20d6c40455f4a3

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