🍄

Turn forgotten hardware
into a thinking network

mycoSwarm connects your machines — old laptops, mini PCs, Raspberry Pis, GPU workstations — into a single AI swarm. No cloud. No API keys. No data leaves your network.


                    $ curl -fsSL https://mycoswarm.org/install.sh | bash

                    $ mycoswarm chat

                    # that's it. you're running local AI.

Capabilities

What the swarm can do

💬

Chat with memory

Persistent facts and session history across conversations. Your AI remembers what you tell it.

🔍

Parallel research

Plans multiple searches, distributes them across CPU workers, synthesizes a cited answer on the GPU. Faster than any single machine.

📚

Document library

Drop files into a folder. The swarm indexes them and answers questions about your documents with citations. Local Perplexity.

🤖

Agentic routing

The model decides when it needs web search or document lookup, shows you what it's doing, and uses the results automatically.

🔌

Plugin system

Drop a folder, restart the daemon. Your node advertises a new capability. No core code changes needed.

🌐

Zero config discovery

Nodes find each other via mDNS. No IP addresses to configure, no config files to edit. Plug in and the swarm grows.

Real hardware

A working 5-node swarm

Node	Hardware	Role	Cost
Miu	RTX 3090, 64GB RAM	GPU inference — runs 27B models	~$850
naru	Lenovo M710Q, 8GB RAM	Web search, file processing	$50
uncho	Lenovo M710Q, 8GB RAM	Web search, coordination	$50
boa	Lenovo M710Q, 8GB RAM	Web search, code execution	$50
raspberrypi	Raspberry Pi 2, 1GB RAM	Search, lightweight tasks	$35

Total: ~$1,035 · Zero monthly fees · Every node counts

How it works

Task flow

User asks question on Node A
  → Node A checks: can I handle this locally?
    → Yes: execute locally
    → No: orchestrator scores all peers
      → Dispatch to best peer
      → Stream response back to Node A

Research task on Node A
  → GPU node plans 4 searches
  → CPU worker 1 searches query 1  CPU worker 2 searches query 2
    CPU worker 3 searches query 3  CPU worker 1 searches query 4
  → GPU node synthesizes with citations
  → Stream answer to Node A

The manifesto

"If a student in Lagos with two old laptops can't participate, the framework has failed."

Named after mycelium — the underground network connecting a forest.
It doesn't centralize. It finds what's available and connects it.

Turn forgotten hardwareinto a thinking network