Skip to main content

Everpod SDK for Python

The official Python client for the Everpod API.

Everpod is an easy way to get your own always-on, persistent cloud computer for AI agents, working in minutes: with a managed OpenClaw agent on it, or as a developer pod with Claude Code and Codex installed. A key lets an agent or an app you trust see your pods and start a new one for you, which you then pay for on everpod.ai. It can't pay, change or cancel a plan, delete anything, or open your agent's control panel.

If you are connecting an agent such as Claude Code or Codex, you do not need this library: point it at Everpod's MCP server, as the API reference shows.

Install

pip install everpod-ai

Python 3.9 or later. No dependencies.

Use

To make a key, open everpod.ai/account/keys and sign in with your email address and the code we send you. If you have no account yet, signing in makes one. Give the key to the library from an environment variable.

import os

from everpod_ai import Everpod

everpod = Everpod(os.environ["EVERPOD_API_KEY"])

# Start an OpenClaw pod under the name you want for its agent. Nothing is
# charged: the pod stays unpaid until you open pay_url in a browser and pay there.
pod = everpod.start_pod("Otto")
print(pod["status"], pod["pay_url"])

# Or a developer pod: the machine's name, and your username on it.
machine = everpod.start_pod("atlas", kind="developer", login="alex")

# The pods on your account, oldest first.
pods = everpod.list_pods()

# One pod by its id: how to check whether it has been paid for, and whether it is ready.
same = everpod.get_pod(pod["id"])

While your account has an unpaid pod, starting another returns that same pod, changed to the name and kind now asked for.

A pod's fields and what each status means are in the API reference.

When a request is refused

A refusal raises an EverpodError. Its message is the API's own sentence, which says what happened and what to do next; code and status are the refusal's.

from everpod_ai import EverpodError

try:
    everpod.get_pod(pod_id)
except EverpodError as error:
    print(error.code, error.status, error.message)

Questions

support@everpod.ai

License

MIT

Metadata

Release files for everpod-ai 0.2.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for everpod-ai 0.2.0
File Size Uploaded
everpod_ai-0.2.0.tar.gz 6.9 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for everpod-ai 0.2.0
File Interpreter ABI Platform
everpod_ai-0.2.0-py3-none-any.whl Python 3 none any Details

Total release size: 12.5 kB

Release files / everpod_ai-0.2.0.tar.gz

Download URL everpod_ai-0.2.0.tar.gz
Size 6.9 kB
Tags Source
SHA-256 checksum
How to use checksums
69a7a1407488a318e9ea574276a13d36375719c55f1bd98f5cbd5ff2e8535de4
BLAKE2b-256 checksum
How to use checksums
1112395a3bfff869bc810bdb5486e21f09fd1a7b6af0610769eaa46a9412d161
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.11.2

Release files / everpod_ai-0.2.0-py3-none-any.whl

Download URL everpod_ai-0.2.0-py3-none-any.whl
Size 5.6 kB
Tags Python 3
SHA-256 checksum
How to use checksums
05af8aa0ae72698d3735d13536b4c0fbe0d38f086ffd427f4757f8f2645e2200
BLAKE2b-256 checksum
How to use checksums
e506ec980932a001c02986a241c033d17a1135184693d2d7f01a2618f39afec3
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.11.2

Release history Release notifications | RSS feed

This release

0.2.0 This release

2 release files

0.1.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page