Hello, Zip!

ZipperGen is a Python DSL and runtime for structured multi-agent LLM coordination. You write a single global protocol describing what messages flow between which agents and who owns each decision. ZipperGen projects it onto each agent and runs them concurrently — with deadlock-freedom guaranteed by construction.

Quick start

git clone https://github.com/zippergen-io/zippergen.git
cd zippergen
pip install -e .

Python 3.11 or later required.

Hello, World!

Define lifelines, write a global workflow, and call it like a normal Python function:

from zippergen.syntax import Lifeline, Var
from zippergen.actions import pure
from zippergen.builder import workflow

User    = Lifeline("User")
Compute = Lifeline("Compute")
number  = Var("number", int)

@pure
def inc(x: int) -> int:
    return x + 1

@workflow
def increment(number: int @ User) -> int:
    User(number) >> Compute(number)
    Compute: number = inc(number)
    Compute(number) >> User(number)
    return number @ User

result = increment(number=1)   # -> 2

Using real LLMs

Set your API key, pass a provider name, and run:

export OPENAI_API_KEY=...

my_workflow.configure(llms="openai", ui=True)
result = my_workflow(notes="...", diagnosis="...")

Built-in providers: openai, mistral, claude. Different agents can use different providers:

my_workflow.configure(llms={"LLM1": "mistral", "LLM2": "openai"})

ZipperChat

Pass ui=True to open a live message-sequence-chart in your browser as the agents run. Watch who sends what, who is thinking, and where the workflow currently is.

Learn more

• GitHub — zippergen-io/zippergen
• About