Skip to main content

Agentbase Python SDK

This SDK is compatible with Agentbase server version latest.

Agentbase SDK for integrating your app with Agentbase APIs and tools.

Installation

To install via PyPI:

pip install agentbase-python-sdk

Or with uv:

uv add agentbase-python-sdk

Getting Started

Init your SDK

Initialize your SDK with your Agentbase server API endpoint and project ID which can be found on your project settings page and your new API secret Key from project's API keys section.

from agentbase.client import Client
from agentbase.services.users import Users

client = Client()

(client
  .set_endpoint('https://[HOSTNAME_OR_IP]/v1') # Your API Endpoint
  .set_project('5df5acd0d48c2') # Your project ID
  .set_key('919c2d18fb5d4...a2ae413da83346ad2') # Your secret API key
  .set_self_signed() # Use only on dev mode with a self-signed SSL cert
)

Make Your First Request

Once your SDK object is set, create any of the Agentbase service objects and choose any request to send. Full documentation for each service method is available in the API reference provided by your Agentbase deployment.

All service methods return typed Pydantic models, so you can access response fields as attributes:

users = Users(client)

user = users.create(ID.unique(), email = "email@example.com", phone = "+123456789", password = "password", name = "Walter O'Brien")

print(user.name)   # "Walter O'Brien"
print(user.email)  # "email@example.com"
print(user.id)     # The generated user ID

Full Example

from agentbase.client import Client
from agentbase.services.users import Users
from agentbase.id import ID

client = Client()

(client
  .set_endpoint('https://[HOSTNAME_OR_IP]/v1') # Your API Endpoint
  .set_project('5df5acd0d48c2') # Your project ID
  .set_key('919c2d18fb5d4...a2ae413da83346ad2') # Your secret API key
  .set_self_signed() # Use only on dev mode with a self-signed SSL cert
)

users = Users(client)

user = users.create(ID.unique(), email = "email@example.com", phone = "+123456789", password = "password", name = "Walter O'Brien")

print(user.name)       # Access fields as attributes
print(user.to_dict())  # Convert to dictionary if needed

Type Safety with Models

The Agentbase Python SDK provides type safety when working with database rows through generic methods. Methods like get_row, list_rows, and others accept a model_type parameter that allows you to specify your custom Pydantic model for full type safety.

from pydantic import BaseModel
from datetime import datetime
from typing import Optional
from agentbase.client import Client
from agentbase.services.tables_db import TablesDB

# Define your custom model matching your table schema
class Post(BaseModel):
    postId: int
    authorId: int
    title: str
    content: str
    createdAt: datetime
    updatedAt: datetime
    isPublished: bool
    excerpt: Optional[str] = None

client = Client()
# ... configure your client ...

tables_db = TablesDB(client)

# Fetch a single row with type safety
row = tables_db.get_row(
    database_id="your-database-id",
    table_id="your-table-id",
    row_id="your-row-id",
    model_type=Post  # Pass your custom model type
)

print(row.data.title)     # Fully typed - IDE autocomplete works
print(row.data.postId)    # int type, not Any
print(row.data.createdAt) # datetime type

# Fetch multiple rows with type safety
result = tables_db.list_rows(
    database_id="your-database-id",
    table_id="your-table-id",
    model_type=Post
)

for row in result.rows:
    print(f"{row.data.title} by {row.data.authorId}")

Error Handling

The Agentbase Python SDK raises AgentbaseException object with message, code and response properties. You can handle any errors by catching AgentbaseException and present the message to the user or handle it yourself based on the provided error information. Below is an example.

users = Users(client)
try:
  user = users.create(ID.unique(), email = "email@example.com", phone = "+123456789", password = "password", name = "Walter O'Brien")
  print(user.name)
except AgentbaseException as e:
  print(e.message)

Learn more

Refer to the documentation and API reference provided by your Agentbase deployment.

Contribution

This library is generated from the Agentbase API specs in this repository. See docs/sdks/monorepo-generation.md for the supported generation, versioning, and publishing workflow.

License

This SDK is distributed under the BSD-3-Clause license. See the bundled LICENSE file.

Metadata

Release files for agentbase-python-sdk 15.5.0

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

Source distribution (sdist)

Source distribution for agentbase-python-sdk 15.5.0
File Size Uploaded Provenance
agentbase_python_sdk-15.5.0.tar.gz 229.6 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for agentbase-python-sdk 15.5.0
File Interpreter ABI Platform
agentbase_python_sdk-15.5.0-py3-none-any.whl Python 3 none any Details

Total release size: 599.7 kB

Release files / agentbase_python_sdk-15.5.0.tar.gz

Download URL agentbase_python_sdk-15.5.0.tar.gz
Size 229.6 kB
Tags Source
SHA-256 checksum
How to use checksums
6c175c49abefb5f956db029ea18eaed42ff68bb17ef942c9fee84c2aaca9509b
BLAKE2b-256 checksum
How to use checksums
cdb1a76372325c19b823b29460f4829c1dcb4976ab0d22dff88715851d732ba9
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.13.9

Release files / agentbase_python_sdk-15.5.0-py3-none-any.whl

Download URL agentbase_python_sdk-15.5.0-py3-none-any.whl
Size 370.1 kB
Tags Python 3
SHA-256 checksum
How to use checksums
d94f0b1c3506e862e47a3ff5b3fc03106f7c1d727cc0e43d0ec4b66cc8424eda
BLAKE2b-256 checksum
How to use checksums
7340dcb860f154879b7f7d261aca5bb57a5356dcfc9293dd570454726476fc6e
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.13.9

Security for agentbase-python-sdk 15.5.0

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.

Release history Release notifications | RSS feed

This release

15.5.0 This release

2 release files No provenance

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