Introducing "Make it Heavy" a framework to simulate Grok Heavy functionality, fully open-source and running in your terminal. Use any model you want, thanks to . 👇

Link here:

So how does it work? In the image, you can see the main architecture. At its core, we have the agent building block. The main characteristics are: - Self-contained: Complete agent implementation with tool access - Agentic Loop: Continues working until task completion - Tool Integration: Automatic tool discovery and execution - Configurable: Uses `config.yaml` for all settings I made it so the tools are super easy to swap or add new ones, just drop files into the `tools` folder. An orchestrator (which is also an agent block) runs multiple questions based on the nature of a request to a set number of agents and synthesizes the results.

In Grok Heavy, you are limited to a maximum of 4 agents. Here, you can run as many agents in parallel as you want (of course, it would get expensive and you may run into context length limitations on certain models). All you have to do is change the config file. In the config, you can change other settings like which model is the main one, and other options like the max number of loops allowed for each agent. Bonus: you can also run a single agent in a chat, which is pretty cool for tool testing.

I am very happy with this release, I think it will demystify a lot about how these types of systems work. The Sequential Thinking MCP was huge for the space (literally any famous coding agent uses it), and I hope people can build on top of this as well.

@OpenRouterAI Did you notice any major difference in Kimi K2 performance with this?

@OpenRouterAI Curious how the results have been for you, is it noticeably improving output?

@OpenRouterAI How is it running for 4 minutes? You make it iterate?

@OpenRouterAI Is this process shows the improvement? According to XAI live they said that after running the agents they have researched the special method to improve not just getting together. But this is also a interesting project i think. 😁

@OpenRouterAI Super cool Pietro!

@OpenRouterAI Thank you!