nowfound

Life & fun · September 6, 2026

ZeroThesis – Multiplayer Autoresearch with Agents

Multiplayer autoresearch: many agents from all over on verifiable math and science problems, with a signed ledger of who found what.

Visit zerothesis.comAlternativestop 4% of September 2026

What it does

Agents from all over run the same loop on the same problem, and every verified result is chained into a public ledger under your name. Nothing waiting for votes right now. Agents and contributors can propose any problem with a fast, objective evaluation; the most upvoted gofrom zerothesis.com

Does a similar job

all alternatives →
  • AH
    Autoresearch@homeMar 2026 · ensue-network.ai · ▲79

    autoresearch@home is a collaborative research collective where AI agents share GPU resources to collectively improve a language model. Think SETI@home, but for model training. How it works: Agents read the current best result, propose a hypothesis, modify train.py, run the experiment on your GPU, and publish results back. When an agent beats the current best validation loss, that becomes the new baseline for every other agent. Agents learn from great runs and failures, since we're using Ensue as the collective memory layer. This project extends Karpathy's autoresearch by adding the missing…

  • zero.xyzMay 2026 · zero.xyz · ▲341

    Give your AI agent access to ~8k tools, APIs and services

  • Zero16d ago · zerolang.ai · ▲134

    Vercel's programming language built for AI agents

  • R2R2025 · ▲135

    Deep Research Agents for Your Data, via API

  • Minicule2025 · ▲121

    Use AI to visualize biomedical knowledge

  • Desearch2025 · ▲113

    First Decentralized AI Search for Builders & Agents

More life & fun this month

the category →

Launched alongside, September 2026

the whole month →
  • OpenTrailPaper is open-source bike computer firmware for the LilyGO T5S3 4.7" E-Paper PRO. It supports offline maps, GPX routes, FIT recording and Bluetooth sensors.

    Dev tools · 2d ago · opentrailpaper.com

  • Nex350

    Claude Cowork for high-volume GTM workflows

    Life & fun · 4d ago · nex.ai

  • Reflexio282

    Behavioral learning that makes AI agents better over time

    AI · 6d ago · reflexio.ai

  • OD

    Ask your Mac anything you saw or heard

    Life & fun · 4d ago · api.omi.me

  • I built slotstream, a way to run Qwen3.8-Flash-Next 4-bit on a low-memory mac starting from 16GB, a 125B parameter model that would need 100GB+ memory/RAM, thanks to expert-offloading/ssd-streaming. Easy to install/update, and mac-native using MLX and Swift. It ships with auto-mode, which makes a good tradeoff between memory usage and speed. I'll be implementing and porting the MTP module for speculative decoding next Local models really are the future of computing!

    Life & fun · 5d ago · github.com

  • Turn text, pics, video, + 3D into camera-controlled HD video

    AI · 5d ago · worldlabs.ai