LazyBridge

Zero-boilerplate, multi-provider Python framework for LLM agents. One Agent class, swappable engines, and one tool contract — plain Python functions, other agents, MCP servers, and full pipelines all compose through tools=[…].

python 📋

from lazybridge import Agent, LLMEngine

agent = Agent(
    engine=LLMEngine("claude-opus-4-7"),
)
result = agent("hello")
print(result.text())

That's the whole surface when you start. It grows only when your problem grows. Parallelism is automatic when the engine emits N tool calls in a turn; deterministic when you declare it.

Note · v0.7.9

Until 0.7.9 is published to PyPI, install from source with pip install "git+https://github.com/selvaz/LazyBridge.git#egg=lazybridge[anthropic]".

The mental model

Every Agent is the composition Engine + Tools + State:

Engine — what decides next. LLMEngine is the common case; swap for Plan, HumanEngine, or SupervisorEngine.
Tools — anything the agent can invoke. Functions, other agents, MCP servers, native provider tools.
State — Memory (in-prompt history), Store (durable blackboard), Session (event bus).

Pick your tier

LazyBridge grows with you — every tier is additive.

Tier	For	Key imports
Basic	one-shot or tool-calling agents	`Agent · LLMEngine · Tool · NativeTool · Envelope`
Mid	real apps with memory, tracing, guardrails, composition	`Memory · Store · Session · Guard* · verify= · MCP`
Full	production pipelines: typed hand-offs, routing, resume, OTel	`Plan · Step · sentinels · SupervisorEngine · checkpoint`
Advanced	extending the framework	`BaseProvider · Plan.to_dict · custom engines · OpenTelemetry`

Function becomes a tool, auto-schema

No decorators, no JSON schemas. Type hints + docstring become the tool's LLM-facing schema automatically.

python 📋

from lazybridge import Agent, LLMEngine, Tool


def get_weather(city: str) -> str:
    """Return current temperature and conditions for ``city``."""
    return f"{city}: 22°C, sunny"


agent = Agent(
    engine=LLMEngine("claude-opus-4-7"),
    tools=[Tool.wrap(get_weather, name="get_weather")],
)
result = agent("what's the weather in Rome and Paris?")
print(result.text())