Pistachio
Permissionless AI inference on a decentralized network. No broker, no middleman, no vendor lock-in. Direct peer-to-peer connections to compute providers on the Morpheus network.
Morpheus is a decentralized peer-to-peer AI network where independent compute providers run models and register on-chain. The default gateway routes through a third-party broker who adds latency, takes a cut, and becomes a single point of failure. Pistachio removes that broker entirely. Your machine connects directly to the provider. One less hop, no middleman, no markup.
MOR staking is collateral, not payment. It returns in full when sessions close. The only real cost is a small amount of ETH gas on Base. Providers compete on price and uptime. You pick the model, Pistachio finds the best available provider.
Permissionless inference matters. No vendor approval, no API waitlists, no terms that change overnight. For open data processing at scale, that independence is the point. DRM3 runs millions of articles per year through AI analysis on this infrastructure. The same network is available to anyone running Pistachio.
OpenAI and Anthropic-compatible APIs on localhost. Drop it into any existing workflow. Auto-staking, auto-renewal, zero downtime. Available as a Docker image for hosted gateway deployments. Total cost: roughly $5 to $8 per month for the container, plus whatever MOR you stake for capacity.
Capabilities
Permissionless: no vendor approval, no API waitlists, no terms that change overnight
Peer-to-peer: your machine connects directly to compute providers
Zero capex: providers supply the compute, MOR collateral returns when sessions close
No broker markup: one less hop, lower latency, better economics
OpenAI + Anthropic API compatibility on localhost
Docker image for hosted gateway deployments ($5-8/mo)
MOR staking with automatic session renewal
NFT-gated access tiers (Free through Diamond)
Multi-provider routing with health monitoring
Ed25519 provenance signing on every response
Acknowledgment
Built on Morpheus
Gratitude to the builders who fair-launched a decentralized AI network and made permissionless inference real.
Morpheus was fair-launched with no VC round, no insider allocation, and no centralized gatekeeper. The protocol lets anyone stake MOR for inference and anyone serve models for emissions. That architecture is why DRM3 can offer AI compute as capex instead of opex, and why Pistachio exists as a sovereign, self-custodied inference node. None of this would be possible without the people who designed, coded, and shipped it.
Protocol and Governance↗
Designed the Morpheus protocol, wrote the whitepaper, and built the governance framework that keeps the network decentralized.
Smart Contracts↗
Built the on-chain layer on Base: session routing, staking, provider registry, and the contract infrastructure the entire network runs on.
Titan/Lumerin Node↗
First proved decentralized AI inference as a reality. The Titan/Lumerin team built both the consumer node and the provider node for the Morpheus network, handling prompt routing, session management, and direct provider connections on both sides of the protocol. The Lumerin node served as a reference implementation for Pistachio's core mechanics.
Morpheus is a fair-launched open protocol. No venture capital, no insider tokens, no permission required. DRM3 Labs builds on top of Morpheus and contributes back to the ecosystem. For more, visit mor.org.