Inside the Gwenlake lab
Working prototypes from the team that you can try in your browser, and what we release as open source: the framework behind our agent systems and a few smaller libraries.
Our experiments
Working prototypes the team builds along the way.
Agentic AI framework · Python
Gwenflow
Gwenflow runs AI agents: give an agent a goal, tools, a memory and a model, and it reasons, acts, observes and goes round again until the goal is met. We use it in every agentic system we build, and we wrote it ourselves to own every line of code our agents run, so that any decision taken on a client’s data can be opened, explained and changed.
from gwenflow import Agent, ChatMistralfrom gwenflow.tools import Tool def accounts_at_risk(period: str, min_drop: int = 10) -> list[dict]: """Accounts whose usage fell by at least `min_drop` percent.""" return crm.query(period=period, trend="down", min_drop=min_drop) agent = Agent( name="Account review", instructions="Rank the accounts at risk, with the figures.", llm=ChatMistral(), tools=[Tool(accounts_at_risk)],) response = agent.run("Which accounts are at risk this quarter?")Research libraries
Smaller and more focused. Each one came out of a problem we had to solve for ourselves.