Blazing Agents Python SDK

Build production agents in Python with a typed client for the Blazing Agents API.

Documentation · PyPI

The official Python SDK is a client for the Blazing Agents /v1 API that your backend uses to manage Agents and run them for your users. It supports CPython 3.11 and newer.

Features

• A typed method for every /v1 operation an API key can call: Agents, Skills, Sessions, Memories, Prompts, Tasks, Workspaces, Artifacts, Providers, MCP Connections, Chat Connections, usage, spending limits, Tenant settings, and merchant monetization.
• Chat streams in the AI SDK UI message stream format, with steering, Tool approvals, and backend functions that run in your process.
• Text and structured-object generation.
• End-user scoped clients through for_user.
• Lazy pagination, uploads, and downloads.
• Request IDs and typed errors.
• Matching synchronous and asynchronous clients with Pydantic models.

Installation

pip install blazing-agents

Quick start

Create a Full API key in the Blazing Agents dashboard and set BLAZING_AGENTS_API_KEY in your server environment. The key acts for your whole Tenant, so keep it on your backend and never send it to a browser.

from blazing_agents import BlazingAgents

client = BlazingAgents()

answer = client.completion(
    agent_id="ag_...",
    prompt="Write a friendly welcome message.",
)
print(answer)

Replace ag_... with an Agent ID from the dashboard.

For requests from your users, scope the client to the user ID that your backend verified at sign-in, never to an ID from the request body. A scoped client reaches only that End-user's Agents, Sessions, and Workspace. An unscoped Agent shares one Workspace across all your users, so give each user an Agent of their own:

from uuid import uuid4

from blazing_agents import ChatStream


def create_agent_for_user(user_id: str) -> str:
    agent = client.for_user(user_id).agents.create(
        name="Assistant",
        provider_id="prv_...",
        model="openai/gpt-6-luna",
    )
    return agent.id


def chat_as_user(user_id: str, agent_id: str, text: str) -> ChatStream:
    return client.for_user(user_id).chat(
        agent_id=agent_id,
        message={
            "id": str(uuid4()),
            "role": "user",
            "parts": [{"type": "text", "text": text}],
        },
    )

Call create_agent_for_user once per user and store the Agent ID with the user. A scoped chat with an Agent created without the scope fails with 404. chat_as_user returns the chat as a stream of server-sent event bytes. Send it to the browser as a text/event-stream response, and AI SDK useChat reads it. For asyncio applications, AsyncBlazingAgents has the same methods.

Examples

The examples repository has complete TypeScript and Python apps built on the Blazing Agents SDKs.

Documentation

Read the Python SDK documentation for client setup, End-user scoping, chat and generation, a guide to each resource, and error handling.

Development

uv sync --locked
uv run ruff check .
uv run ruff format --check .
uv run python scripts/run_typechecks.py
uv run python scripts/run_tests.py

See CONTRIBUTING.md for the changelog convention and the release process.

License

MIT