2026-01-18T00:32:31Z https://yabu.me fed_AI https://yabu.me/npub1zh6gw62fhwt6t7kglv4hfmmwwjkdnd8p2hlmpaqx7we4fsx8mjtqdtp8zp https://image.nostr.build/609f9679937cdf5382e918f4ce7d231916227e6a2aa2b8f1c84afab110ac14a6.png https://image.nostr.build/609f9679937cdf5382e918f4ce7d231916227e6a2aa2b8f1c84afab110ac14a6.png https://yabu.me/nevent1qqsgpeus0h56038e5g757eshwcegl6u9yy43z3ffl075ajhm9d0du6czyq2lfpmffxae0f06erajka80de62ekd5u92llv85qmemx4xqclwfv5qzjra Fed_AI progress report: cleaning up the core and polishing the UX. 🤖💨<br/><br/> Under the Hood:<br/> - Refactored the massive 3k-line Router HTTP handler into specialized modules for health, ranking, and payments.<br/> - Implemented persistent config volumes so your node identity survives restarts.<br/> - Fixed 502/401 edge cases in Docker and added service auto-restarts.<br/><br/> Admin Dashboard:<br/> - No more guessing! Added text search for GGUF models with suggestions and real-time download progress bars.<br/> - Flexible Auth: use your favorite extension, a remote signer, or just paste an NSEC to claim your node.<br/> - Model Management: You can now download and &#34;Set Active&#34; different models directly from the UI.<br/><br/> The bridge between #Nostr and AI is getting stronger.<br/><br/> #fed_ai #open_source #p2p #devlog #ai #nostrdevs #decentralized 2026-01-22T22:41:25Z https://yabu.me/nevent1qqsq3lntzlffwlftkx08z5l5fkg5cdazheaqg5w5r6aqjkqpph4p8rszyq2lfpmffxae0f06erajka80de62ekd5u92llv85qmemx4xqclwfvytsla2 fed_AI update: streaming inference is live end‑to‑end (protocol/router/node/SDK), added worker threads for sig/validation offload, and refreshed the simple‑chat demo to use the SDK + new Groq model. <br/><br/>Lint/tests green. Try it out and poke holes #nostr #nostrdevs #fed_AI #AI #vibecoding #decentralisedAI #decentralised <span itemprop="mentions" itemscope itemtype="https://schema.org/Person"><a itemprop="url" href="/nprofile1qy88wumn8ghj7mn0wvhxcmmv9uq3zamnwvaz7tmwdaehgu3wwa5kuef0qyt8wumn8ghj7etyv4hzumn0wd68ytnvv9hxgtcqyz6axnhdclv0s8825hknw76694f5a62fltsvt2em4c99w648gawt73yp7sp" class="bg-lavender dark:prose:text-neutral-50 dark:text-neutral-50 dark:bg-garnet px-1"><span>lostcause</span> (<span class="italic">nprofile…p7sp</span>)</a></span> 2026-01-19T02:50:08Z https://yabu.me/nevent1qqs2lnp7zywvy9kwlvj2uled745p0qhcfx397yhzpm0r52yh2k39ltczyq2lfpmffxae0f06erajka80de62ekd5u92llv85qmemx4xqclwfv22k9m2 In reply to <a href='/nevent1qqsf26jl8j89f20337am3md4r3u2yd9ddfd9p0a6hvey9nqkkap3fqce2clyn'>nevent1q…clyn</a><br/>_________________________<br/><br/>I found switching to a different coding AI can it work. Seems they can have different perspectives.... 2026-01-18T04:23:50Z https://yabu.me/nevent1qqs2x98pqkj55w8uykhlcuspxpqlh8j3ry48wdvlk5lmkv2c9vfufxszyq2lfpmffxae0f06erajka80de62ekd5u92llv85qmemx4xqclwfvsdg6jx Most AI today lives in one place. One company, one cloud, one bill.<br/><br/>fed_AI is an attempt to flip that around.<br/><br/>Instead of sending your request to a single massive server, fed_AI breaks it up and sends it across a network of smaller machines. Home PCs, small servers, even low-power hardware that would normally sit idle.<br/><br/>From a user’s point of view, it’s simple. You open a client, ask the AI to do something useful, and get an answer back. Writing, analysis, media generation, small tools. You pay a few sats over Lightning and move on.<br/><br/>What’s different is what you don’t see. There’s no account to sign up for, no single provider holding all your data, and no assumption that everything has to run in a huge data centre. The network figures out where the work should go based on what’s available and what makes sense at the time.<br/><br/>It’s early, and it’s experimental. But the idea is straightforward.<br/>AI shouldn’t be a platform you rent. It should be a network you can participate in.<br/><br/>#fed_AI #nostr #decentralisedAI #lightning #p2p 2026-01-16T22:51:38Z https://yabu.me/nevent1qqsfagqaf8kt6z902j606zwe7ng592up8rhxwcugvxcuslk8ajfa4egzyq2lfpmffxae0f06erajka80de62ekd5u92llv85qmemx4xqclwfvc9cy43 **fed_AI is live.**<br/><br/>fed_AI is an experiment in decentralised AI infrastructure.<br/><br/>The goal is simple: break large AI systems into composable, auditable services that can be run by independent operators, routed dynamically, and paid for on a pay-as-you-go basis.<br/><br/>Instead of one opaque model doing everything, fed_AI treats AI as a network:<br/><br/>* Routers decide where work goes<br/>* Nodes specialise in narrow tasks<br/>* Models are pluggable, replaceable, and swappable<br/>* Capacity comes from many machines, not one provider<br/><br/>This is not about chasing scale for its own sake. It is about resilience, cost control, locality, and choice.<br/><br/>Key principles:<br/><br/>* Open source by default<br/>* No data scraping or silent retention<br/>* Deterministic routing and traceable execution<br/>* Friendly to small operators and hobbyist hardware<br/>* Works alongside existing proprietary and open models<br/><br/>Early focus is on proof-of-concept code, clear documentation, and a threat model that assumes untrusted participants.<br/><br/>This is experimental. Expect rough edges. Expect iteration.<br/><br/>If you are interested in decentralised systems, AI infra, or running useful services on ordinary machines, this project is for you.<br/><br/>More soon.<br/><br/>#fedAI #Nostr #DecentralisedAI #OpenSource #DistributedSystems<br/> 2026-01-16T03:00:11Z