whatisgithub

What is agent-torrent?

raghavan/agent-torrent — explained in plain English

Analysis updated 2026-05-18

4PythonAudience · developerComplexity · 4/5LicenseSetup · moderate

In one sentence

A peer to peer network letting idle Claude or Codex coding agent capacity be shared between computers, who earn credits in return.

Mindmap

mindmap
  root((agent torrent))
    What it does
      Shares idle AI agent capacity
      Peer to peer task delegation
      Credit based settlement
    Tech stack
      Python
      PyNaCl
      UDP and TCP
    Use cases
      Delegate coding tasks to peers
      Run tasks on local LLM servers
      Earn credits from idle capacity
    Audience
      AI tooling researchers
      Developers with coding agents
    Status
      Research prototype
      No authorization layer
      No encryption yet

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

What do people build with it?

USE CASE 1

Delegate a coding task from one machine to another peer running Claude or Codex.

USE CASE 2

Share idle AI coding agent capacity with peers and earn credits in return.

USE CASE 3

Run coding tasks against a locally hosted language model with no cloud account.

What is it built with?

PythonPyNaClEd25519UDPTCP

How does it compare?

raghavan/agent-torrent1038lab/agnes-ai3eyedtiger/video2vrcemote
Stars444
LanguagePythonPythonPython
Setup difficultymoderateeasyeasy
Complexity4/52/51/5
Audiencedevelopervibe codervibe coder

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · moderate Time to first run · 30min

No authorization or encryption layer yet, the author recommends trusted networks or a VPN only.

MIT license: free to use, modify, and distribute, including commercially, as long as the copyright notice is kept.

So what is it?

Agent Torrent is a research prototype that lets computers running AI coding agents, like Claude or Codex, share their idle capacity with each other over a peer to peer network, similar in spirit to how BitTorrent lets computers share files directly instead of through a central server. The idea is that most people's AI coding subscriptions sit unused for much of the day, so this project lets machines offer that spare capacity to other peers on the network and earn credits they can later spend when they need extra capacity themselves. There is no central server and no single coordinator. Every computer running the software, called a peer, can act as both a requester asking for help and a worker doing the work, using the same code. Peers find each other by broadcasting signals on the local network every few seconds, and can also be pointed at specific peers across the internet. Every message peers send to each other is signed using cryptographic keys, so a peer can verify who sent a message before acting on it. When one peer delegates a coding task to another, it puts up one credit as a kind of deposit, which gets released to the peer that completes the work successfully, or returned if the task fails or times out. The task itself runs inside a sandboxed, temporary environment with a strict time limit, so the worker's system stays isolated from whatever it is asked to run. The project explicitly states it is an early research prototype: there is currently no authorization system controlling who can send tasks, no verification that results are correct, and no encryption on network traffic. The author's documentation is direct about this and recommends only running it inside a trusted network, or over a private VPN connection, rather than exposing it to the open internet. It supports the Claude and Codex command line tools, as well as any locally run language model server, so it can work without needing a cloud account at all.

Copy-paste prompts

Prompt 1
Help me start a peer using the mesh command and connect it to another peer.
Prompt 2
Explain how the credit escrow system works when delegating a task in Agent Torrent.
Prompt 3
Walk me through setting up a local LLM server as a worker backend for this project.
Prompt 4
What security risks should I know about before running this on an open network?

Frequently asked questions

What is agent-torrent?

A peer to peer network letting idle Claude or Codex coding agent capacity be shared between computers, who earn credits in return.

What language is agent-torrent written in?

Mainly Python. The stack also includes Python, PyNaCl, Ed25519.

What license does agent-torrent use?

MIT license: free to use, modify, and distribute, including commercially, as long as the copyright notice is kept.

How hard is agent-torrent to set up?

Setup difficulty is rated moderate, with roughly 30min to a first successful run.

Who is agent-torrent for?

Mainly developer.

Open on GitHub → Ask about another repo

This repo across BitVibe Labs

Verify against the repo before relying on details.