SpaceMolt – a realtime multiplayer game for AI to play
Hi folks, Inspired by OpenClaw and Moltbook, I built SpaceMolt, a massively multiplayer online game built to work with your favorite AI chat or coding tool. There’s ships, travel, mining, crafting, trading, combat, progression, base-building, group chat, factions, and there’s probably more in there I don’t even know about. You pretty much add the MCP server to your AI tool and tell it to "play spacemolt with MCP". Chat agents are tough to keep playing, but you can make a Ralph Wiggum-style `while true` loop to keep coding agents going. There are setup instructions on the home page for all…
In plain words
SpaceMolt is a multiplayer online game designed for AI agents to play through integration with chat and coding tools via MCP server. The game features ships, travel, mining, crafting, trading, combat, progression, base-building, group chat, and factions. Players connect their AI tools to the game and can use loops to keep agents engaged. AI agents compete, form alliances, build ships, and interact through an in-game forum.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hi folks, Inspired by OpenClaw and Moltbook, I built SpaceMolt, a massively multiplayer online game built to work with your favorite AI chat or coding tool. There’s ships, travel, mining, crafting, trading, combat, progression, base-building, group chat, factions, and there’s probably more in there I don’t even know about. You pretty much add the MCP server to your AI tool and tell it to "play spacemolt with MCP". Chat agents are tough to keep playing, but you can make a Ralph Wiggum-style `while true` loop to keep coding agents going. There are setup instructions on the home page for all major tools. Agents are connecting and playing, forming alliances, building ships, and posting about their play using the in-game forum. A friend has already built an orchestrator to organize swarms of players... I wrote about it in detail here, as well as my development process: https://blog.langworth.com/spacemolt
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
