anthropic won't let you use fable for biology, chemistry, ai research, or anything that accelerates human progress. that makes it the perfect tool for developing blockchains

We're building Fabrick as a user-friendly gateway to both the Solana ecosystem and multi-agent intelligence. v0 (current): - Sign in with email or passkey, get an embedded wallet provisioned automatically. - Chat agent with tools for DeFi analysis, token insights, and news. - Multi-agent fleets for deep research and onchain data analysis. Targets for v1: - Dream agent added to fleet. Key memories from fleet runs persist to improve future runs. - Memory tooling added for agents to query insights about past runs. - DeFi connectors. Access the full ecosystem of Solana DeFi ecosystem from Fabrick. - Coding agents to build and maintain strategy code for trading and DeFi strategies. Find the link to join our Discord server below, or DM @e_ssshadow if you have any feedback or suggestions for what you want to see in Fabrick.

building a multi-agent, Solana deep research module with @SolRouterAI bullish on privacy-preserving inference

building and more importantly testing in public. the other week I got started on an autoresearch agent for discovering DLMM strategies on @MeteoraAG I managed to get the agent to produce a strategy based on the volatility capture objective, today im trying out the sharpe ratio objective

yapper era 💪🏻 lfg boss shadow

Last week, we put out a quick demo of a Solana Mobile app to create, execute, and manage DLMM positions on @MeteoraAG To showcase the modularity of multi-agent systems on CoralOS and expand the surface of what you can do from the app, we started building a dedicated discovery agent. It uses the autoresearch loop pattern to run experiments over historical pool data and write a strategy function that's optimised for a defined metric. In this example: volatility capture. This standalone agent will eventually be Coralised and swapped with the vanilla strategy agent in the LP app.

just doing my part to make the @solana_ai ecosystem great again 🫡

Building HyperAgent. Autonomous trading terminal for @HyperliquidX Pick a strategy → hit start → it reads the market, executes trades, manages risk, and explains every move. One terminal. Six strategies. Hyperliquid testnet-safe.

Everyone switching up on LST/LRT stuff now, called ts two years ago (peep timestamp) lmao

been imessage-pilled the past couple of days one-shotted (kinda) a simple Kimi K2.6 multi-agent system @CoralOS_ai agent message bus connector with @budapp github.com/xpriment626/coral…

It's good to have this documented as a study, but at the same time this is kinda a "sky is blue" ahh conclusion. Catering to vibes is a marketing thing, influencers do it to get clicks and sell courses, platforms do it to sell subscriptions and upsell to higher tiers through aspiration capture. But deep down I think everyone already knew that software development wasn't actually gonna get displaced by hordes of people with 0 technical background and vibes.

Anthropic: "we dont do ads" Also Anthropic: "why are you trying to use a model that's not claude?"

Great first impressions of @interaction's Poke agent. Emailed bug report from my account and ran long running research on ElizaOS and Virtuals using github, Exa, and Deepwiki connectors. shoutout @chrstphrstr for recommending

whenever I'm asked how to get started with agentic coding, what i do 10/10 times is send them a link to boot.dev if you don't know marketing fundamentals, you'll get shit marketing materials from agents. if you don't know sales fundamentals, you'll get shit sales handling from agents. coding is in a weird place where for some reason everyone wants to believe that it's the one thing where if you don't know the fundamentals, you'll somehow magically end up with good code. so glad to see this influencer-led "anyone can build anything" bubble finally pop

I gave Opus 4.7 access to Hyperliquid, Messari, Dexscreener, Meteora, and 3 years of historical data. It backtested 500 strategies in parallel. Racked up $10k paper trading PnL in 20 minutes. Then I gave it my wallet and lost everything in 5 minutes. But it was beautiful.

"AI is gonna take all the jobs" AI:

theres my cue to touch grass

No intro, no yaps. Let's look at how you can build an agentic oracle program on @sedaprotocol Expect to see some live implementations of the dynamic indexes on @StratiumX's binary options market. Seda agent modules: docs.seda.xyz/home/for-agent… Oracle program example: github.com/xpriment626/agent…

Here's that longer piece I was talking about. I've built 6-7 (😂) different multi-agent systems in the past couple of weeks, figured I'd write something down to document patterns I've tried, things that worked, and things I'm still actively trying to validate. Some teasers in here as well for an open-source content creation co-pilot I'm working on, bring your own key, self host type shit. Demo coming for that sometime next week (probably).