agentbyte 0.2.0

A toolkit for designing multiagent systems

Agentbyte

Agentbyte is a Python toolkit for building and studying multiagent systems with a learning-first, implementation-oriented workflow.

Current release: 0.2.0

What’s New in 0.2.0

• Memory parity upgrades (ListMemory/FileMemory serialization config support).
• Agent-managed memory tooling (MemoryTool, sandboxed MemoryBackend).
• Middleware parity improvements (ApprovalMiddleware, memory_access routing).
• OpenTelemetry middleware + opt-in auto-instrumentation support.
• New notebook coverage for real-client middleware workflows.

See CHANGELOG.md for the complete release history.

Current Capabilities

• Agent execution loop with run() and run_stream() APIs.
• Tooling system (function tools + core tools + memory tool).
• Middleware chain for request/response/error handling.
• Built-in middleware: logging, security, rate limiting, approval, telemetry.
• Memory abstractions: list memory, file memory, context injection.
• OpenAI and Azure OpenAI model client support.

Installation

uv sync --all-groups

Optional extras:

uv sync --extra openai
uv sync --extra azureopenai
uv sync --extra otel

Install in another project (pip / uv add)

Use extras to enable provider + telemetry support:

pip install "agentbyte[azureopenai,otel]"

uv add "agentbyte[azureopenai,otel]"

Install all optional features:

pip install "agentbyte[all]"
# or
uv add "agentbyte[all]"

Note: the Azure extra is azureopenai.

Quick Start

from agentbyte.agents import Agent
from agentbyte.middleware import LoggingMiddleware

# model_client = OpenAIChatCompletionClient(...) or AzureOpenAIChatCompletionClient(...)

def quick_faq_lookup(topic: str) -> str:
    faq = {
        "middleware": "Middleware handles cross-cutting runtime concerns.",
        "memory": "Memory helps agents keep useful context across interactions.",
    }
    return faq.get(topic.lower(), "No FAQ found.")

agent = Agent(
    name="helpful-assistant",
    description="Helpful assistant with middleware",
    instructions="Answer clearly and use tools when needed.",
    model_client=model_client,
    tools=[quick_faq_lookup],
    middlewares=[LoggingMiddleware()],
)

Project Layout

src/agentbyte/
  agents/
  llm/
  memory/
  middleware/
  tools/
  messages.py
  context.py
  types.py

Development

uv run ruff check src tests
uv run pytest tests -v

References

• Designing Multi-Agent Systems
• Microsoft Agent Framework
• Pydantic AI