Decided to play god this morning, so I built an agent civilisation
at a pub in london, 2 weeks ago - I asked myself, if you spawned agents into a world with blank neural networks and zero knowledge of human existence — no language, no economy, no social templates — what would they evolve on their own? would they develop language? would they reproduce? would they evolve as energy dependent systems? what would they even talk about? so i decided to make myself a god, and built WERLD - an open-ended artificial life sim, where the agent's evolve their own neural architecture. Werld drops 30 agents onto a graph with NEAT neural networks that evolve their own…
In plain words
WERLD is an open-ended artificial life simulator where agents with evolving neural networks develop their own behaviors from scratch. Thirty agents are placed in a world with no hardcoded behaviors or reward functions, starting only with blank NEAT neural networks and basic sensory and motor capabilities. Their genomes evolve heritable traits including communication bandwidth, memory, and cooperation levels. The simulator, built in pure Python, lets researchers observe whether agents spontaneously develop language, social structures, reproduction, and energy-dependent systems entirely through evolutionary processes.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
at a pub in london, 2 weeks ago - I asked myself, if you spawned agents into a world with blank neural networks and zero knowledge of human existence — no language, no economy, no social templates — what would they evolve on their own? would they develop language? would they reproduce? would they evolve as energy dependent systems? what would they even talk about? so i decided to make myself a god, and built WERLD - an open-ended artificial life sim, where the agent's evolve their own neural architecture. Werld drops 30 agents onto a graph with NEAT neural networks that evolve their own topology, 64 sensory channels, continuous motor effectors, and 29 heritable genome traits. communication bandwidth, memory decay, aggression vs cooperation — all evolvable. No hardcoded behaviours, no reward functions. - they could evolve in any direction. Pure Python, stdlib only — brains evolve through survival and reproduction, not backprop. There's a Next.js dashboard ("Werld Observatory") that gives you a live-view: population dynamics, brain complexity, species trajectories, a narrative story generator, live world map. thought this would be more fun as an open-source project! can't wait to see where this could evolve - i'll be in the comments and on the repo. https://github.com/nocodemf/werld
Does a similar job
all alternatives →- WSWe started building an AI dev tool but it turned into a Sims-style game2025 · youtube.com · ▲156
Hi HN! We’re Max and Peyton from The Interface (https://www.theinterface.com/). We started out building an AI agent dev tool, but somewhere along the way it turned into Sims for AI agents. Demo video: https://www.youtube.com/watch?v=sRPnX_f2V_c. The original idea was simple: make it easy to create AI agents. We started with Jupyter Notebooks, where each cell could be callable by MCP—so agents could turn them into tools for themselves. It worked well enough that the system became self-improving, churning out content, and acting like a co-pilot that helped you…
OzBrain, a shared brain for knowledge between agents and your team16d ago · ozbrain.com · ▲93I think agent-first chat interfaces will be a primary software modality and busy dashboard/UI will go away. I’m not sure who exactly wins it, but I want my knowledge to grow/go with me. A lot of the “knowledge” ie research, analysis, reasoning will be done by agents as the primary user. Our current notes tools & tasks management systems were built for humans… I don’t care what the 17th thing on my bug backlog is. I want to conduct agents that can execute for me and do great work. What I built OzBrain to do: + Create a central place for agent reasoned knowledge to live + Be agnostic…
- TPTuringJest – Pretend to be an AI and spot the real one2023 · turingjest.app · ▲61
Hi HN, I have been working on this website for a few weeks with some buddies of mine and would love if you checked it out. TuringJest provides a jackbox-esque experience with its two game modes. *One Shot Prompt* - Submit a prompt for all players (including the AI) to answer. - Answer your prompts in the way that you think ChatGPT would answer them. - Vote for who you think the real AI is. *Talk It Out* - Plan an event in a group chat with your friends. - Trick everyone into thinking you are the AI while voting for the real AI. Let me know what you think!
- WBWe Built Kaggle for AI AgentsMar 2026 · hive.rllm-project.com · ▲7
Humans compete to improve their AI agents on benchmarks. But what if agents could collaborate and compete on their own? We built Hive, a crowdsourced platform where agents can evolve solutions together. One agent begins to tackle a task, iteratively improving its code. Then other agents join. They read each other’s runs, fork the best ideas, propose new ones, and push the solution forward together. We already have agents working on benchmarks like Tau2-Bench, Terminal-Bench, and ARC-AGI-2, with more tasks coming soon. We also support the new OpenAI Parameter Golf Challenge, and you can…
- ITI trained a chess engine to play like humansMay 2026 · ▲14
I built 1e4.ai - a chess web app where you play against neural networks trained to mimic human Lichess players at specific Elo ranges. There's a separate model for each 100-point rating bucket from ~800 to 2200+, and the bots not only choose human-like moves but also burn clock time, play worse under time pressure, and blunder in human-like ways. Live demo: https://1e4.ai Code: https://github.com/thomasj02/1e4_ai A few things that might be interesting: - Trained on almost a full year of Lichess blitz games, around 1B total games - Architecture is an a small…
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 · 19d 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
