co/core — an AI cooperative<br>an experiment in member-owned AI<br>An AI cooperative.<br>co/core is a place where people share the compute they already own to run AI for each other, instead of renting from a handful of giant providers. It's an experiment in inference we build, share, and own together — and your existing code works as-is, because we speak the same standard API everything else does. The models are open ones that run on the hardware people already have.<br>Get started — it's free →See how it works<br>↓Have compute to share? Get the cocore app — macOS, Apple Silicon

machines online<br>29

models available<br>9 / 9 active (7d)

time to first token<br>1.7sp50 · last 100 jobs

combined memory<br>936 GB RAM

combined cores<br>304 cpu cores

free to start<br>1M tokens · one-time

live on the network<br>Real members. Real machines. Real receipts.<br>A glimpse of the co-op right now — some of the people who've signed up, some of the machines sharing compute, and the latest jobs they've signed off on. Every one of these is a real, public record.<br>some cocore members<br>Guillermo Zapata@gzapata.bsky.sociallksz@lksz.namejack@j4ck.xyzproviderKevin Santo Cappuccio@architeuthisflux.bsky.socialBen@nvisible.bsky.socialTim Disney@disnetdev.comprovider

machines sharing compute<br>▢MacBook AirApple M5 · a very good ren<br>▢mac.lanApple M2 · Devin Gaffney<br>▢fair-windApple M4 Max · Nick Gerakines<br>▢paperclip_maximizer_01Apple M1 · Jack<br>▢Mac MiniApple M1 · Devin Gaffney<br>▢feixiaoApple M4 · lot

recent job receipts<br>mlx-community/gemma-3-4b-it-qat-4bitin 50 · out 316 · did:plc:xrqs…xo4ojs · 16.0s<br>mlx-community/gemma-3-4b-it-qat-4bitin 35 · out 316 · did:plc:xrqs…xo4ojs · 15.0s<br>mlx-community/Qwen2.5-0.5B-Instruct-4bitin 39 · out 508 · did:plc:zisy…jpeo6n · 6.0s<br>mlx-community/Qwen2.5-0.5B-Instruct-4bitin 35 · out 13 · did:plc:jijw…lqrpec · 1.0s<br>mlx-community/Qwen2.5-0.5B-Instruct-4bitin 32 · out 23 · did:plc:jijw…lqrpec · 0ms

01 drop-in<br>Just change three lines.<br>Cocore speaks the same API language as everybody else. Point your existing SDK at console.cocore.dev/v1, drop in a cocore-… key, and keep going — streaming, tool calls, and the usual chat/completions shape all work, no code changes. Host from our presets or any MLX model.

OpenAIAnthropicTogetherGroqOllamaco/core

client.pybefore<br>from openai import OpenAI

client = OpenAI(<br>base_url="https://api.openai.com/v1",<br>api_key="sk-proj-…",

resp = client.chat.completions.create(<br>model="gpt-4o-mini",<br>messages=[{"role": "user",<br>"content": "hello"}],<br>stream=True,<br>client.pyafter<br>from openai import OpenAI

client = OpenAI(<br>base_url="https://console.cocore.dev/v1",<br>api_key="cocore-7f3a2c…",

resp = client.chat.completions.create(<br>model="mlx-community/Qwen2.5-0.5B",<br>messages=[{"role": "user",<br>"content": "hello"}],<br>stream=True,

02 how it works<br>You send a request. The co-op runs it.<br>Your request finds a member's available compute, runs the job, and comes back to you. The whole thing is an open spec — every job leaves a signed, public record anyone can verify for themselves, ours included.<br>1job<br>You send a job

Your encrypted prompt heads out into the co-op. Run your prompt for a given model anywhere in the open network, or choose to keep your jobs private to only a trusted circle of co-op friends and their machines.

→dev.cocore.compute.job<br>inputCommitment: sha256<br>priceCeiling: 2,500 tokens<br>acceptedTrustLevel: hw

2attest + run<br>A member runs it

Someone picks up your job, runs it, then returns the result after signing with a key locked in the Secure Enclave that never leaves their hardware — proof of exactly who did the work, and that nobody touched it after.

→dev.cocore.compute.receipt<br>tokens: 50 in · 316 out<br>price: 366 tokens<br>enclaveSig: ✓ SE-bound

3settle<br>Receipts, in the open

A receipt closes out the job — credits go to whomever who ran it, minus a small cut to a shared pot. Each month that pot splits back to members by how much they pitched in, so the cut cycles right back to the people running the network.

→dev.cocore.compute.settlement<br>debit: 366 tokens<br>credit: 347 tokens<br>fee: 19 tokens → treasury

03 open by default<br>You don't have to take our word for it.<br>Every job writes a receipt anyone can verify on their own, without ever calling us. We can't inflate a balance, fake a payout, or quietly change the rules. And if you don't like how we run things, you can run the whole thing yourself — point your own copy at the same data and it lands on exactly the same numbers.<br>◆The record lives with the person who made it<br>We keep a fast index, but the real, signed record of every job lives on the provider's own account — not locked inside our database.

◆Receipts check out on their own<br>A receipt plus our public spec plus the signer's identity is all you need to confirm a job happened — offline, with no cocore API in the loop.

dev.cocore.compute.provider<br>provider

dev.cocore.compute.attestation<br>provider ·...