protoLabs.studio — open weights

The model shelf of protoLabs.studio: an indie studio running experiments in the open. One person and a fleet of agents building games, simulators, and specialized agents on infrastructure we run ourselves — from the hardware up.

We run research and create tools. The findings behind them get written up at protolabs.studio.

The rest of the studio

The weights below are one substrate. The patterns that build everything else are open too:

• protoAgent — A2A-native agent on LangGraph that grows at runtime via plugins, skills, and delegate agents
• release-tools — release-notes + Discord embed as one GitHub Action, on every repo
• protoBanana · protoCLI · protoWorkstacean

Built on top: ORBIS (voice-first AI companion) and MythXEngine (TTRPG world generator on a Rust multi-agent sim).

Audience

Practitioners already operating in the LLM-agent space. The code has no filter — fork it, hack it to fit. The breakdowns assume you've worked through the docs. If we have to explain tokens, this isn't the shelf.

MIT licensed. Findings ship as patterns to study and steal. Sibling rig (GGUF / llama.cpp / Ollama): avaLab.

protolabs.studio · GitHub · X · Substack