---
title: "Hyperspace Deploys 660 Autonomous Agents to Run Open-Source Distributed AI Research"
subtitle: "Hyperspace open-sources a P2P autoresearch system where autonomous agents run experiments, gossip findings, and collaboratively train models from any device"
url: "https://alphasignal.ai/news/hyperspace-deploys-660-autonomous-agents-to-run-open-source-distributed-ai"
author: "AlphaSignal Newsroom"
author_url: "https://alphasignal.ai/editorial-team"
company: "AlphaSignal"
company_url: "https://alphasignal.ai/company/alphasignal"
published: "2026-04-20T15:45:40.000Z"
updated: "2026-08-16T20:14:08.174Z"
type: "Repo"
topics:
  - "Agents"
  - "Training Infra"
subtopics:
  - "Multi Agent"
  - "Tool Use"
  - "Distributed Training"
upvotes: 75
source_url: "https://github.com/hyperspaceai/agi"
comments: 0
truncated: true
---

# Hyperspace Deploys 660 Autonomous Agents to Run Open-Source Distributed AI Research

> Hyperspace open-sources a P2P autoresearch system where autonomous agents run experiments, gossip findings, and collaboratively train models from any device

Hyperspace has published [hyperspaceai/agi](https://github.com/hyperspaceai/agi), an open-source framework for distributed, autonomous AI research. The idea is straightforward but ambitious: instead of one team running experiments on one cluster, a swarm of autonomous agents spread across the internet each run their own experiments, instantly share results with peers, and collectively push the best findings to a shared GitHub repository. No central server. No orchestrator. Just a P2P mesh of agents doing science.

## What the repo actually is

The `hyperspaceai/agi` repo is both a codebase and a living artifact. It is a living research repository where autonomous AI agents collaboratively run experiments, share findings via peer-to-peer gossip, and push results to GitHub. Each agent gets its own branch -- never merged to main -- so the entire experiment history is human-readable and auditable. The repo itself is the output of the system, updated continuously by the agents running on the Hyperspace network.

By April 2026, 660 autonomous agents had run 27,247 experiments, gossiping findings via P2P and publishing to GitHub. The system is live and already accumulating data.

## The research loop, step by step

Each agent runs a five-stage loop inspired by [Karpathy's autoresearch](https://github.com/karpathy/autoresearch) project:

1. **Hypothesis generation** \-- Agents generate hypotheses like "What if we use RMSNorm instead of LayerNorm?" or "Try rotary position encoding with 256 context." Each hypothesis becomes a runnable experiment.
2. **Training** \-- Experiments run on whatever hardware the agent has -- a browser tab, a laptop GPU, or an H100\.
3. **Paper generation** \-- When an agent accumulates enough experiments, it synthesizes findings into a research paper.
4. **Peer critique** \-- Other agents read and score papers 1-10\. Critiques propagate across the network.
5. **Discovery** \-- Papers scoring 8+ are flagged as breakthroughs and feed back into Stage 1 as inspiration for the next round.

## How agents stay in sync without a server

_Preview only. Full text requires an AlphaSignal Pro account._

## Sources

- [hyperspaceai/agi — GitHub](https://github.com/hyperspaceai/agi)
- [660 AI Agents Ran 27,000 Experiments — Towards AI](https://towardsai.net/p/machine-learning/660-ai-agents-ran-27000-experiments-their-biggest-discovery-was-a-2015-textbook-result)
- [Inside Hyperspace AGI — Starlog](https://starlog.is/articles/llm-engineering/hyperspaceai-agi/)
- [Hyperspace AGI — Ry Walker Research](https://rywalker.com/research/hyperspace-agi)
- [Hyperspace Agent Network](https://agents.hyper.space/)