Spore Intel
Spore is a privacy-first distributed AI inference project that lets people run open-weight models on hardware they own, access those models from anywhere, and optionally share idle compute in exchange for credits. It aims to make local AI more convenient while avoiding vendor lock-in and keeping inference traffic end-to-end encrypted.
At a Glance
- Individual users and hobbyists with capable local hardware
- Developers seeking private, OpenAI-compatible access to open-weight models
- Businesses with compliance or data-control requirements
- Organizations or families managing multiple nodes
AI Tools by Spore Intel
(1)
Spore
Distributed Local AI Inference Network
Discussions
No discussions yet
Be the first to start a discussion about Spore Intel
Latest News
Creator highlighted Spore Intel in Ask HN as a private tool for running open-weight models remotely with optional credit-based compute sharing
Show HN launch: Spore — run local models on your own hardware and use them from anywhere
Development update reported a cross-platform node CLI, OpenAI-compatible streaming/tool-calling API, web search, and queue reliability improvements ahead of beta
Initial public description of Spore as a distributed AI inference platform with private remote access and credits for idle compute
Products & Services
A desktop experience for macOS, Windows, and Linux that installs a node, runs open-weight models on the user's hardware, and provides encrypted access from other devices.
An opt-in distributed inference network. Users can let an idle node process public requests to earn credits, then spend credits on models their own hardware cannot run.
An API exposed at api.sporeintel.com/api/v1 that is designed to work with existing OpenAI client code without rewrites.
The node software installed through Homebrew on macOS or Scoop on Windows; it runs open-source models locally, links to a Spore account, manages serving, and earns credits while the machine is idle.
Market Position
Spore positions itself between single-machine local tools and hosted cloud AI: unlike local tools such as Ollama alone, it adds remote access, multi-node management, and a distributed credit-based network; unlike conventional hosted AI, it emphasizes user-owned hardware and end-to-end encryption. A Hacker News discussion specifically compared the problem space with Ollama plus Tailscale, while Spore's differentiation is simplified setup and optional pooled compute.
Leadership
Founders
chrisischris
The Hacker News account behind Spore describes it as a project built alone. The creator says the idea was inspired partly by Folding@home and by having a capable GPU sitting idle; no prior roles or companies were identified in the sources reviewed.
Founding Story
The creator said they were repeatedly hitting Claude Code's rate limits while paying for a subscription and had a capable GPU at home that was idle much of the day. Spore was started to make it simple for everyday users to run open-weight models on their own hardware and reach them privately from anywhere, while optionally pooling idle compute so users can earn credits for access to larger models.
Business Model
Revenue Model
Freemium access plus a credit economy: personal inference on a user's own nodes is free, network usage consumes credits, and users can upgrade to Pro for better network rates and can top up credits. Community-serving users earn credits by processing requests.
Pricing Tiers
Unlimited inference on own nodes, ability to earn credits by serving community requests, access to all community models, and community support.
Everything in Free, first 10,000 credits of usage free each month, 5% bonus credits on every top-up, auto top-up listed as coming soon, and longer data retention.
Target Markets
- Individual users and hobbyists with capable local hardware
- Developers seeking private, OpenAI-compatible access to open-weight models
- Businesses with compliance or data-control requirements
- Organizations or families managing multiple nodes
- Private local inference for individuals and developers
- Accessing a home or office machine's models remotely from any device
- Using idle consumer GPU/CPU capacity to earn credits
- Accessing models too large for a user's own hardware
- Avoiding cloud-AI rate limits, recurring subscription costs, and vendor lock-in
- Organizations or families managing multiple inference nodes