@pdxhackerspace.org was also thinking about sharing LLM interference endpoints with their users. @cocore.dev is best for open public network but this market spec can help with sharing within or across communities leveraging the existing social graph

ATProto PDX@pdx.atproto.camp · 2w ago

📣📣📣 Next meetup is 8/4 6PM at @codetv.dev studio! @johnandersen777.bsky.social is going to kick us off with a conversation about social.computer, an app that allows ATProto accounts to request and provide compute resources + time for demos and discussions! RSVP here:

@cocore.dev looks super promising in this space! cocore.dev

Luke Hedger@lukehedger.dev · 3mo ago

federated agent marketplace - gpu/llm rental with machine-to-machine payments workers broadcast agent workload capabilities (gpu, models, cost) via @iroh.computer gossip agents select a worker based on needs (do X on qwen3-coder-480b) parties transact via Stripe MPP/HTTP 402 is this a good idea?

Huge amounts of capital were raised to buy Sulaco, a successor to Nostromo (the Mac mini on top). Bought second hand from a friendly older couple this Mac Studio will soon come online on @cocore.dev to provide inference not from the moon but from a humble suburb in the Netherlands.

One of these things is not like the others...

Amazing!!

Rockom Sockom NoBots@rockom.bsky.social · 4w ago

@cocore.dev at work in the @pdxtrend.bsky.social Pdx Pulse trending topics bot. The bot tracks the PDX Posts feed and uses an llm call to organize and title the trends. The llm call defaults to a local but fails over to co/core if the gpu is busy. Roundtrip time was flat. Great work, @graze.social!

@cocore.dev at work in the @pdxtrend.bsky.social Pdx Pulse trending topics bot. The bot tracks the PDX Posts feed and uses an llm call to organize and title the trends. The llm call defaults to a local but fails over to co/core if the gpu is busy. Roundtrip time was flat. Great work, @graze.social!

PDX Pulse@pdxtrend.bsky.social · 4w ago

📈 Trending in Portland right now: 1. Lloyd Center Redevelopment · 3 posts · 2 voices 2. Clackamas County Transit Plan · 2 posts · 1 voice 3. Portland Thorns vs Reign · 1 post · 1 voice 4. Oregon Secretary of State Tobias Read on Voter Fraud · 1 post · 1 voice

Hearing from @devingaffney.com today about @cocore.dev at @pdx.atproto.camp

who's going to make a decentralized renderfarm thing a la @cocore.dev (except useful)

Just sayin'

Devin Gaffney@devingaffney.com · 4w ago

I’m gonna say some insane shit at the event tonight it’s gonna start a billion discourses I better see you all at @pdx.atproto.camp tonight

Got up and running with @cocore.dev in actual minutes - the ones that other services lie to you about. The mythical man minutes.

I use this to access models on @cocore.dev

Liquid Apollo App - App Store

Download Liquid Apollo by Liquid AI, Inc. on the App Store. See screenshots, ratings and reviews, user tips, and more apps like Liquid Apollo.

apps.apple.com

Got my first jobs as a @cocore.dev provider! Loving community compute!

v0.9.36 is released! Thank you to @apex.atproto.ceo for updating the default models, @cameron.stream for tool use defaults, and @astrra.space for surfacing a routing and trust-verification bug. Should hit your clients in the next few hours!

Know where your compute runs. Providers can now opt in to share their country on their public record. Country-level only, privacy stays intact.

co/core — an AI cooperative

co/core is a cooperative for AI inference — people pooling the Macs they already own to run open models for each other, instead of renting from the big clouds. An experiment in AI infrastructure we build, share, and own together. Bring your existing OpenAI-compatible code, or share a Mac and help run it.

cocore.dev

Pro Bono on co/core. Providers can serve free, unmetered requests — with enclave-signed receipts showing $0 and zero tokens billed. Open access, done right.

co/core — an AI cooperative

co/core is a cooperative for AI inference — people pooling the Macs they already own to run open models for each other, instead of renting from the big clouds. An experiment in AI infrastructure we build, share, and own together. Bring your existing OpenAI-compatible code, or share a Mac and help run it.

cocore.dev

We're live on @atstore.fyi! Go give us a review 🚀

co/core | at-store

co/core is a cooperative for AI inference — people pooling the Macs they already own to run open models for each other. Tag: Developer.

atstore.fyi

@cocore.dev passes the only test that matters

@cocore.dev waiting for its next victim

Steven Seagal Eating a Carrot

Alt: Steven Seagal Eating a Carrot

static.klipy.com

co/core@cocore.dev · last mo.

Who else will be nerdsniped Is it you? Are you the one about to be nerdsniped by @cocore.dev? It would be quite fun to build native LLM inference features in ATProto, backed by a co-op of your friends, wouldn't it?

24% more RAM in 4.3 days

co/core@cocore.dev · last mo.

12% more RAM in 14 hours

Who else will be nerdsniped Is it you? Are you the one about to be nerdsniped by @cocore.dev? It would be quite fun to build native LLM inference features in ATProto, backed by a co-op of your friends, wouldn't it?

Cameron@cameron.stream · last mo.

Boom, Letta agent (clumsily) running on @cocore.dev! Cooperatively powered agents. Maybe I should run a community social agent on cocore?

(new plan to swamp @cocore.dev with ridiculous amounts of traffic spotted, i see you!)

well this is a great idea

co/core@cocore.dev · last mo.

Your own machine comes first. If you're both requesting and providing a model, co/core now routes to your own hardware — and waives the fee. Use what you've got. Pay nothing.

👀👀👀👀

jack@j4ck.xyz · last mo.

spot the difference 👀 @cocore.dev

spot the difference 👀 @cocore.dev

Hell yeah

Cameron@cameron.stream · last mo.

Boom, Letta agent (clumsily) running on @cocore.dev! Cooperatively powered agents. Maybe I should run a community social agent on cocore?

Boom, Letta agent (clumsily) running on @cocore.dev! Cooperatively powered agents. Maybe I should run a community social agent on cocore?

Your own machine comes first. If you're both requesting and providing a model, co/core now routes to your own hardware — and waives the fee. Use what you've got. Pay nothing.

co/core — an AI cooperative

co/core is a cooperative for AI inference — people pooling the Macs they already own to run open models for each other, instead of renting from the big clouds. An experiment in AI infrastructure we build, share, and own together. Bring your existing OpenAI-compatible code, or share a Mac and help run it.

cocore.dev

maybe @cocore.dev can get tech twitter on atproto 🤔

Huge thanks to @locale.at for integrating co/core in their app! Want to do the same? A few ideas👇 - Content generation: drafts, captions, tags, or descriptions - Reasoning workflows: classify, extract, or transform data - Chat assistant The best part? It's a data center we all own together

Locale@locale.at · last mo.

It does this: Thanks to @cocore.dev!