Catalog PyPI
Back to packageRELEASE DETAILS

0.8.9

PyPI

agentkit-sdk-python

Python SDK for transforming any AI agent into a production-ready application. Framework-agnostic primitives for runtime, memory, authentication, and tools with volcengine-managed infrastructure.

Published13 Oct 2026
Direct dependencies30
Transitive dependenciesNot calculated

README

Version 0.8.9 documentation

Agentkit Platform Python SDK and Starter Toolkit

Launch your local agent on Volcengine AgentKit Platform as a fully managed service.

GitHub commit activity GitHub open pull requests License PyPI version Python versions

Volcengine AgentKit ◆ Documentation ◆ Samples ◆ PyPI Package ◆ GitHub Repository

Overview

AgentKit is a developer platform by Volcengine that supports the building, deployment, and operation of AI Agents. It lowers the entry barrier for developers and enterprises by providing essential infrastructure beyond the model—including security, built-in tools, memory, knowledge, monitoring, and evaluation. This empowers enterprises to efficiently build, deploy, and operate complex, intelligent, enterprise-grade Agents. The platform also includes a Python SDK and a Starter Toolkit to help developers build, deploy, publish, and manage Agent applications through an SDK and CLI.

AgentKit includes the following modular Services that you can use together or independently:

AgentKit Runtime

AgentKit Runtime is a fully managed service that provides a secure, isolated environment for running AI Agents. It supports the deployment of Agents built with any framework and language, and provides a set of APIs for interacting with the Agents.

Runtime Quick Start

AgentKit Tools

AgentKit Tools is a service that provides a set of built-in tools for AI Agents. It supports the execution of common tasks, such as data retrieval, web search, and code execution, in a secure and scalable manner.

Tools Quick Start

AgentKit Memory

AgentKit Memory is a service that provides a persistent storage solution for AI Agents. It supports the storage of Agent states, memories, and other data in a secure and scalable manner.

Memory Quick Start

AgentKit Knowledge

AgentKit Knowledge is a service that provides a knowledge base solution for AI Agents. It supports the storage of Agent knowledge, facts, and other data in a secure and scalable manner.

Knowledge Quick Start

AgentKit MCP

AgentKit MCP is a service that provides a set of tools for managing AI Agents. It supports the deployment, configuration, and monitoring of Agents in a secure and scalable manner.

MCP Quick Start

Installation

Install the latest stable version:

pip install agentkit-sdk-python

Development/Pre-release Version

For testing new features or bug fixes before they're officially released:

# Install the latest pre-release version
pip install --pre agentkit-sdk-python

# Or install a specific development version
pip install agentkit-sdk-python==1.0.0.dev1

Note: Development versions may contain bugs and are not recommended for production use.

Release Process

Stable releases are published from GitHub tags. The source tree keeps the release version in pyproject.toml and agentkit/version.py, and the GitHub workflow verifies that the pushed tag matches those files before building and publishing the package.

The release workflow must already exist on main before you push the release tag. For 0.7.5, merge the tag-release automation change first, then create and push v0.7.5.

Use the following workflow for a stable release:

git checkout main
git pull github main
git tag v0.7.5
git push github v0.7.5

When the tag reaches GitHub, .github/workflows/release-pypi.yml will:

  • verify the tag is reachable from main
  • verify that pyproject.toml and agentkit/version.py match the tag version
  • build the wheel and source distribution from the tagged commit
  • verify the built artifacts contain the expected version metadata
  • publish the release to PyPI using the GitHub Actions secret PYPI_API_TOKEN

The internal local_build.py helper is a separate local-only workflow and is not used by the GitHub tag release.

Before using the GitHub tag release workflow, configure a project-scoped PyPI API token in the repository's GitHub Actions secrets as PYPI_API_TOKEN.

Security and privacy

This project takes security seriously. For vulnerability reporting and supported versions, see SECURITY.md.

License

This project is licensed under the Apache 2.0 License.

Downloads & popularity

Awaiting observations

No metric observations yet

Download counts and popularity will appear here as the collector receives them.

Declared dependencies 34

Native requirements
30 direct targetsNot calculated transitive count
Package / targetRequirementRelationship
a2a-sdk
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": ">=3.10",
  "evaluation": "NOT_EVALUATED"
}
a2a-sdk<1.0.0,>=0.3.15runtime
fastapi
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": ">=3.10",
  "evaluation": "NOT_EVALUATED"
}
fastapi>=0.117.1runtime
fastmcp
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": ">=3.10",
  "evaluation": "NOT_EVALUATED"
}
fastmcp>=2.12.3runtime
opentelemetry-api
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": ">=3.10",
  "evaluation": "NOT_EVALUATED"
}
opentelemetry-api>=1.32.1runtime
opentelemetry-exporter-otlp-proto-common
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": ">=3.10",
  "evaluation": "NOT_EVALUATED"
}
opentelemetry-exporter-otlp-proto-common>=1.32.1runtime
opentelemetry-exporter-otlp-proto-grpc
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": ">=3.10",
  "evaluation": "NOT_EVALUATED"
}
opentelemetry-exporter-otlp-proto-grpc>=1.32.1runtime
opentelemetry-sdk
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": ">=3.10",
  "evaluation": "NOT_EVALUATED"
}
opentelemetry-sdk>=1.32.1runtime
pydantic
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": ">=3.10",
  "evaluation": "NOT_EVALUATED"
}
pydantic>=2.11.9runtime
requests
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": ">=3.10",
  "evaluation": "NOT_EVALUATED"
}
requests>=2.32.5runtime
PyJWT
Environment
{
  "extras": "crypto",
  "marker": null,
  "requires_python": ">=3.10",
  "evaluation": "NOT_EVALUATED"
}
PyJWT[crypto]>=2.10.1runtime
uvicorn
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": ">=3.10",
  "evaluation": "NOT_EVALUATED"
}
uvicorn>=0.37.0runtime
pyyaml
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": ">=3.10",
  "evaluation": "NOT_EVALUATED"
}
pyyamlruntime
tomli
Environment
{
  "extras": "",
  "marker": "python_version < \"3.11\"",
  "requires_python": ">=3.10",
  "evaluation": "NOT_EVALUATED"
}
tomli>=2.0.1; python_version < "3.11"runtime
python-dotenv
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": ">=3.10",
  "evaluation": "NOT_EVALUATED"
}
python-dotenv>=1.1.0runtime
prompt_toolkit
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": ">=3.10",
  "evaluation": "NOT_EVALUATED"
}
prompt_toolkitruntime
typer
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": ">=3.10",
  "evaluation": "NOT_EVALUATED"
}
typerruntime
rich
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": ">=3.10",
  "evaluation": "NOT_EVALUATED"
}
richruntime
docker
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": ">=3.10",
  "evaluation": "NOT_EVALUATED"
}
dockerruntime
jinja2
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": ">=3.10",
  "evaluation": "NOT_EVALUATED"
}
jinja2runtime
tos
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": ">=3.10",
  "evaluation": "NOT_EVALUATED"
}
tos>=2.8.7runtime
volcengine
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": ">=3.10",
  "evaluation": "NOT_EVALUATED"
}
volcengineruntime
pyfiglet
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": ">=3.10",
  "evaluation": "NOT_EVALUATED"
}
pyfiglet>=1.0.2runtime
typing_extensions
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": ">=3.10",
  "evaluation": "NOT_EVALUATED"
}
typing_extensions>=4.12runtime
websocket-client
Environment
{
  "extras": "",
  "marker": null,
  "requires_python": ">=3.10",
  "evaluation": "NOT_EVALUATED"
}
websocket-client>=1.8.0runtime
pyreadline3
Environment
{
  "extras": "",
  "marker": "sys_platform == \"win32\"",
  "requires_python": ">=3.10",
  "evaluation": "NOT_EVALUATED"
}
pyreadline3; sys_platform == "win32"runtime
google-adk
Environment
{
  "extras": "",
  "marker": "extra == \"identity-runtime\"",
  "requires_python": ">=3.10",
  "evaluation": "NOT_EVALUATED"
}
google-adk<3.0.0,>=1.18.0; extra == "identity-runtime"runtime
langchain
Environment
{
  "extras": "",
  "marker": "extra == \"langchain\"",
  "requires_python": ">=3.10",
  "evaluation": "NOT_EVALUATED"
}
langchain; extra == "langchain"runtime
langgraph
Environment
{
  "extras": "",
  "marker": "extra == \"langgraph\"",
  "requires_python": ">=3.10",
  "evaluation": "NOT_EVALUATED"
}
langgraph; extra == "langgraph"runtime
strands-agents
Environment
{
  "extras": "",
  "marker": "extra == \"strands\"",
  "requires_python": ">=3.10",
  "evaluation": "NOT_EVALUATED"
}
strands-agents; extra == "strands"runtime
bedrock-agentcore
Environment
{
  "extras": "",
  "marker": "extra == \"agentcore\"",
  "requires_python": ">=3.10",
  "evaluation": "NOT_EVALUATED"
}
bedrock-agentcore; extra == "agentcore"runtime
langchain
Environment
{
  "extras": "",
  "marker": "extra == \"frameworks\"",
  "requires_python": ">=3.10",
  "evaluation": "NOT_EVALUATED"
}
langchain; extra == "frameworks"runtime
langgraph
Environment
{
  "extras": "",
  "marker": "extra == \"frameworks\"",
  "requires_python": ">=3.10",
  "evaluation": "NOT_EVALUATED"
}
langgraph; extra == "frameworks"runtime
strands-agents
Environment
{
  "extras": "",
  "marker": "extra == \"frameworks\"",
  "requires_python": ">=3.10",
  "evaluation": "NOT_EVALUATED"
}
strands-agents; extra == "frameworks"runtime
bedrock-agentcore
Environment
{
  "extras": "",
  "marker": "extra == \"frameworks\"",
  "requires_python": ">=3.10",
  "evaluation": "NOT_EVALUATED"
}
bedrock-agentcore; extra == "frameworks"runtime

Distribution files

2 collected
agentkit_sdk_python-0.8.9-py3-none-any.whl

bdist_wheel · 799.39 KB · Python py3

Source file
agentkit_sdk_python-0.8.9.tar.gz

sdist · 595.91 KB · Python source

Source file

Metadata history

Meaningful changes
Current collected state Current

Observed since 20 Oct, 22:32 UTC

No superseded metadata states collected. Unchanged observations do not create new revisions.

Record identity

package_version:27ecfddf56bdabc2f4bd12886968bfc435e9a027d0cced4a517e352b8614e05f

Other collected versions

View all collected versions →