Hanseatic Alliance for Networked Sovereign Architecture
Make tokens cheap again. The easiest way to run an LLM on your own hardware — a private, OpenAI-compatible endpoint, fully offline. No accounts, no API keys, no usage bills. When you choose to, share spare capacity with the community swarm and route your own requests across the network, geo-scoped to your rules.
The same software serves radically different needs — because self-sovereignty, research freedom, and regulatory compliance are not in conflict.
Install H.A.N.S.A. on a gaming PC or Apple Silicon machine. You get a private, OpenAI-compatible endpoint — no API keys, no usage bills, no data leaving your device. Opt into the community swarm when you want more capacity.
The long-term thesis: combining smaller models can outperform single large ones. Mixture of Agents, self-consistency, speculative ensembling — this research exists but lacks a real-world substrate. H.A.N.S.A. aims to provide it.
Data residency is designed to be enforced by the routing layer, not left to a policy checkbox. The coordinator filters peer discovery so a node's candidates are already restricted to its configured boundary — and is designed so the coordinator itself never sees inference data.
Built on proven open-source primitives. The novel parts are the policy engine, the batch splitter, and the routing layer.
The installer detects your GPU (CUDA / Metal / ROCm) and suggests the right model tier. One command. Works offline. No accounts required.
LiteLLM Proxy exposes a standard OpenAI endpoint on your machine. Any app that calls OpenAI works with H.A.N.S.A. — no code changes.
Enable sharing. Set your geo scope. The coordinator matches you with compatible peers — applying your policy before any peer sees your node.
The batch splitter detects parallel agentic calls and fans them across peers when the local node is loaded. The same primitive enables multi-model ensemble research.
H.A.N.S.A. builds on Ollama for local inference, LiteLLM Proxy for OpenAI compatibility, and Iroh for encrypted peer transport with NAT traversal. The coordinator handles discovery and geo-policy — and is designed to stay completely off the inference data path.
The novel layer is what we build on top: geo-policy enforcement, latency-aware peer ranking, the agentic batch splitter, signed update distribution, and a public network dashboard.
We publish a full threat model and we don't overclaim. Here's the short version of what each side can and cannot see.
| Claim | Status |
|---|---|
| Running locally is exactly as private as your own machine — it is your own machine. | ✓ True today |
| Your traffic never leaves the geographic boundary you choose. | ✓ Enforced by geo-scoped matching |
| The coordinator is designed never to see your inference content. | ✓ Off the data path by design |
| Every update is signed; nodes reject tampered software. | ✓ Implemented |
| The serving node never learns who sent a request — prompts travel via relay, anonymized. | 🛠 Rolling out through the alpha |
| Names, passwords, and IDs are stripped on your own machine before a prompt leaves it (PII firewall); prompts flagged sensitive stay home by default, visibly. | 🛠 Rolling out through the alpha |
| A malicious operator could still read what their node processes. | ⚠ True — but once the privacy layer lands, that means an anonymous prompt stripped of names, credentials, and IDs, unlinkable to you. Until then, send only non-sensitive workloads. Node validation & confidential execution come next on the funded roadmap. |
Rule of thumb: the swarm gets an anonymized, PII-stripped version of your prompt — truly confidential material stays on your own node, by default and by design. Read the full threat model at the institute.
MVP demo in weeks. Community alpha by Q3. Research program by Q4.
One command and about a minute to a private, OpenAI-compatible LLM on your own hardware.
curl -fsSL https://hansa.institute/get/install.sh | bash
irm https://hansa.institute/get/install.ps1 | iex
Windows / Linux / macOS · Python 3.11 · 8 GB+ RAM · NVIDIA / Apple Silicon GPU recommended
Fully private by default. Joining the network is a separate, optional step and needs an invite.
Join the builders and researchers shaping a community-run AI network.
No spam. Demo invites and major milestones only.
By joining you agree to our privacy policy.