CLI ToolsMay 13, 2026·2 min read

Hyperspace AGI — P2P Agent Network CLI

hyperspaceai/agi is the Hyperspace network repo and CLI entrypoint. README shows Pods, distributed training, and a one-line installer.

Agent ready

Safe staging for this asset

This asset is staged first. The copied prompt tells the agent to inspect the staged files and ask before activating scripts, MCP config, or global config.

Stage only · 17/100Policy: stage
Agent surface
Any MCP/CLI agent
Kind
CLI Tool
Install
Stage only
Trust
Trust: Established
Entrypoint
Asset
Safe staging command
npx -y tokrepo@latest install ec5c276d-1845-5cc0-8729-0fd333a30a62 --target codex

Stages files first; activation requires review of the staged README and plan.

Intro

hyperspaceai/agi is the Hyperspace network repo and CLI entrypoint. README shows Pods, distributed training, and a one-line installer.

Best for: Teams experimenting with distributed agent pods and shared model providers

Works with: macOS/Linux shell, Hyperspace network, optional GPU/VM providers

Setup time: 5-15 minutes

Key facts (verified)

  • GitHub: 1661 stars · 181 forks · pushed 2026-05-13.
  • License: MIT · owner avatar + repo URL verified via GitHub API.
  • README-verified entrypoint: curl -fsSL https://agents.hyper.space/api/install | bash.

Main

  • Use Pods when you want a private cluster: one member creates a pod, shares an invite link, and peers form a mesh.

  • Treat training as opt-in experimentation: README presents hyperspace train and a --solo mode to run locally.

  • If you want to expose a local OpenAI-compatible endpoint, README lists a localhost base URL and endpoint set for agent usage.

Source-backed notes

  • README shows Pod management commands (hyperspace pod create, invite, members, models).
  • README includes a one-line installer: curl -fsSL https://agents.hyper.space/api/install | bash.
  • README documents a local OpenAI-compatible base URL (http://localhost:8080/v1) and endpoints like /chat/completions.

FAQ

  • Is this production-stable?: README frames it as experimental and a ‘Day 1’ research repo; treat it as a fast-moving project.
  • What’s the first thing to try?: Create a Pod, invite a second machine, and verify you can list members and models.
  • Can I use it as an API?: README lists a local OpenAI-compatible base URL and endpoints for agents.
🙏

Source & Thanks

Source: https://github.com/hyperspaceai/agi > License: MIT > GitHub stars: 1661 · forks: 181

Discussion

Sign in to join the discussion.
No comments yet. Be the first to share your thoughts.

Related Assets