The Distributed Open Llama Network

Your GPU is idle.
Someone's agent needs it.

Share spare compute with the network. Use Llama 3.1 8B for free in Claude Code, Continue, and other agentic tools. No tokens, no fees — just a community.

Install dollama How it works
llama3.1:8b 8B parameters Ollama-native Anthropic API
dollama mascot
0 nodes online
Llama 3.1 8B
0 requests
0 tokens
How it works

Folding@Home, but for LLM inference

01

Install & choose your role

Grab the dollama CLI. Run as a user to consume inference, as a contributor to share compute, or both to do it all.

02

Smart routing, not random

  • Nodes report hardware benchmarks (tokens/sec, RAM, VRAM)
  • Coordinator routes to the best available node
  • When busy, you queue by contribution balance
  • Heartbeat monitoring drops stale nodes automatically
03

Free inference, fair priority

No billing, no blockchain. A simple token ledger tracks what you've served minus what you've consumed. Contribute more and your requests jump the queue. When the network is idle, everyone gets instant service.

Your machine
Claude Code / IDE dollama proxy
Has: your files, context, repo
prompt (HTTPS)
Coordinator relay
Routes requests Manages queue
Sees: prompt plaintext (v1)
prompt (HTTPS)
Contributor node
Ollama runtime Llama 3.1 8B
Sees: raw prompt only
v1: all traffic flows through the coordinator. Direct peer connections with end-to-end encryption are planned for Phase 4.
Trust & security

Know exactly what you're sharing

Stays on your machine

  • Your files, repos, and working directory
  • Context assembly happens locally
  • Only the inference prompt leaves your machine

Visible in transit (v1)

  • The coordinator sees prompts in plaintext
  • Contributor nodes see the raw prompt
  • Not yet encrypted end-to-end
  • We don't log prompt content

Use it for

  • Open-source and hobby projects
  • Learning and experimentation
  • Non-sensitive coding tasks

Don't send secrets, credentials, or proprietary code you wouldn't share with a cloud API.

Full privacy details · Source code · End-to-end encryption planned for Phase 4
Choose your mode

Install once, pick how you participate

After installing, dollama lives in your system tray. Switch modes anytime from the menu — or use the terminal commands below.

USE
I need inference

Use the network

Runs a local proxy that your coding tools connect to. Get LLM inference from the network while your code and context stay on your machine — only the inference prompt is sent.

GIVE
I have spare compute

Contribute cycles

Donates idle GPU/CPU when your machine isn't busy. Runs quietly in the background and pauses automatically when you need your resources. Your contribution builds your priority balance.

BOTH
Recommended

Use & contribute

The default for most people. Use the network for inference and contribute your idle cycles back. You build priority while you help others — the network works best when everyone does both.

Terminal commands

$ dollama connect
$ dollama serve
$ dollama both

Add --auto-start to launch on boot. See dollama --help for all options.

Priority

The more you give, the faster you go

No tokens, no blockchain, no marketplace. Just a running tally that rewards generosity.

Balance model

balance = tokens served − tokens consumed
  • Single queue — sorted by balance. Higher balance = served first.
  • Idle network — everyone gets instant service regardless of balance.
  • New users — start at zero. Use immediately, but contributors get priority when busy.

Concurrency & groups

  • Burst usage — 1–3 concurrent requests cost 1x each. 4+ cost 2x to discourage hogging.
  • Team pooling — groups share a balance. Run nodes on office machines, everyone benefits.
  • No speculation — balances can't be traded or sold. Coordination, not finance.

Your Hardware First

  • Unmetered — inference on your own node doesn't count against your balance.
  • Preemptive — your requests jump the queue on your own node, always.
  • Zero-cost local — no tokens deducted when your node handles your request.

Network behavior

Idle network Busy network
Response time Instant Queued by balance
Balance needed? No — everyone served Higher balance = faster
New users Full access Lower priority
Privacy

What we see, what we don't

Transparency over marketing. Here's exactly how your data flows through the network today.

What stays on your machine

Your files, repository context, and working directory never leave your machine. The local proxy assembles context locally — only the final inference prompt is sent to the network.

What the coordinator sees

  • All traffic routes through the coordinator relay in v1
  • Prompts are visible in plaintext — a known tradeoff for simplicity
  • We don't log prompt content
  • Treat it like any cloud API when deciding what to send

What contributor nodes see

Only the raw inference prompt and generated tokens. No file access, no user identity, no conversation history beyond the current request. Nodes are stateless — they process a prompt and move on.

Data Your machine Coordinator Contributor node
Files & repo context Local only Never sent Never sent
Inference prompt Assembled here Plaintext (v1) Plaintext (v1)
User identity Known Token only Anonymous
Conversation history Full context Per-request only Per-request only

The roadmap: end-to-end encryption

Phase 4 introduces direct peer connections with end-to-end encryption. Until then, treat the network like any cloud API: don't send secrets you wouldn't send to a hosted LLM provider.

Quickstart

Up and running in 2 minutes

1

Install Ollama + dollama

curl -fsSL https://ollama.com/install.sh | sh
curl -fsSL https://dollama.net/install.sh | sh
2

Launch Claude Code

dollama launch claude
3

Start coding

You're running on community compute. Claude Code is configured automatically.

Get started

Install in one command

🦙
Ollama
Required runtime
💾
8GB+ RAM
Recommended
💻
macOS / Linux / Win
Cross-platform
🧠
llama3.1:8b
Network model
Terminal 
curl -fsSL https://dollama.net/install.sh | sh

Requires Ollama installed with llama3.1:8b pulled if you plan to contribute.

PowerShell 
irm https://dollama.net/install.ps1 | iex

Requires Ollama installed with llama3.1:8b pulled if you plan to contribute.

What the installer does: downloads the latest dollama binary for your platform, verifies the checksum, and moves it to /usr/local/bin. That's it — no services, no daemons, no config changes. Read the script source.

Direct binary download

macOS (Apple Silicon) macOS (Intel) Linux (x86_64) Linux (ARM64) Windows (x86_64)

Verify checksums

curl -fsSL https://dollama.net/dl/latest/checksums.txt
sha256sum -c checksums.txt

Build from source

git clone https://github.com/notangrywaffle/dollama.net.git
cd dollama.net/cli && make build
Configure

Use with Claude Code

1

Launch with one command

Run dollama launch claude — it starts the local proxy, configures the environment, and opens Claude Code automatically. That's it.

tip

Want to contribute too?

Run dollama both first, then dollama launch claude in another terminal — you'll use the network and share your idle compute.

Launch Claude Code 
dollama launch claude
Or configure manually in ~/.claude/settings.json 
{
  "env": {
    "ANTHROPIC_BASE_URL": "http://localhost:11435",
    "ANTHROPIC_API_KEY": "dollama-proxy"
  },
  "model": "network:llama3.1:8b"
}
Pull the model (contributors) 
ollama pull llama3.1:8b
Live network

The herd at a glance

loading
Nodes online
Active contributors right now
loading
Tokens processed
Total inference served
loading
Requests completed
Successful inferences

Works with

Claude Code Continue Aider Any Anthropic-compatible tool

Open source

Full source code on GitHub. Coordinator, CLI, installer, and this website — all public.

Built on

Ollama Llama 3.1 8B Cloudflare Workers
FAQ

Common questions

Yes — in v1, contributor nodes see the raw inference prompt in order to generate a response. They don't see your files, identity, or conversation history. Nodes are stateless and process one request at a time. Your files and repo context never leave your machine.
Not yet. In v1, prompts travel through the coordinator in plaintext. Don't send credentials, secrets, or proprietary code you wouldn't share with a cloud API. Use it for open-source projects, learning, and non-sensitive coding tasks. End-to-end encryption is coming in Phase 4.
The coordinator relays all traffic in v1, so it can see inference prompts in plaintext. We don't log prompt content, and no data is sold or shared with third parties. This is a known tradeoff for simplicity — see the Privacy section for details.
Phase 4 introduces direct peer connections (WebRTC/QUIC) with end-to-end encryption between your machine and the contributor node. The coordinator would handle routing only — it would no longer see prompt content. The entire codebase is open source.
It hits the sweet spot: fast enough to run on consumer hardware, capable enough for agentic coding tasks. A single model keeps routing simple. More models may come in future phases.
Ollama installed with llama3.1:8b pulled. Then run dollama serve. The CLI handles registration, heartbeats, and routing automatically. Any machine that can run Ollama can contribute.
Yes. The local proxy exposes an Anthropic Messages API endpoint at localhost:11435. Any tool that supports a custom base URL can use it — Continue, Aider, or your own scripts.
We like llamas — Ollama is the backbone of this project. But a doe felt right for what we're building: gentle, graceful, and part of a herd. Plus, dollama → doe. It was right there the whole time.
Feedback

Report a bug or request a feature