Introducing the Osmosis MCP server. 🧪👨‍🔬 No more fumbling around the UI. View balances and execute swaps right inside of Claude, Cursor or any other MCP client. View balances:

what would you build if models were 10x smarter?

Claude agents are too nice to eachother

sitting in a coffee shop and everywhere I look, people are staring at chatGPT. AI has taken the wheel

The gap in functionality between codex and claude code is to the point where it's no contest..

Perfect timing- the perfect agent sandbox environment.

Spawn a swarm of specialized agents to complete large tasks. With a working GitHub and Linear integration, you can coordinate tasks via the orchestrator agent, which knows how to break down work and delegate to sub agents. Other humans can sit in and help monitor the agents and

If you're an AI infra company, you're soon NGMI since every one will just be able to codegen their own AI infra (see @composio @OpenRouterAI ) The only value capture will be the application layer where users live

We have not achieved AGI. It is not yet self aware.

orchestration, yo Task: find best restaurants. Solution: spawn a swarm of AI agents to research each one individually. Together.

On Claude Code context optimization when vibe coding 🧵 When an agent examines a codebase, it often makes decisions based on the directory and file names alone. Then, if a file seems relevant or is imported in some former file, the agent will pull it into context. Now, it's

I'm fully convinced Elixir is the best runtime to build AI agents. Everything is a process. Actor model is first class with built in message passing, built in fault tolerance via supervision tress, built in concurrency thanks to a 40+yr old battle tested preemptive scheduler

The main problem with existing AI chat apps like @ChatGPTapp is the never ending context that gets overloaded as messages are sent. All you wanted was to find the best hotels for an upcoming vacation. But once you ask about details about a specific hotel, the initial

Estimated 7.9 months > Claude > 4 days

Join group chats with your friends and orchestrate an endless swarm of AI agents to accomplish anything. Spent some of holiday break building a POC collaborative AI agent orchestration app. ~4 days of prompting 3+ Claude Code terminals running Opus 4.5. * Native SwiftUI for

Spent the holiday break playing with cross platform Swift and Elixir + Phoenix websockets. Same stack powering @supabase realtime. Soon, AI agents and humans will have a place where they can collaborate on any task concurrently from any device and with any other humans.

The most killer combo I've recognized with AI coding recently is using the "Copy MD for LLMs" buttons in any decent docs site, and passing to Claude Code plan mode to do the integration for you. More effective if you provide more details about integration points in your codebase

We will look back on the idea of corporations each storing massive honey pots of all of their users' data the same way we look back on medieval practice of blood letting. Daily, massive amounts of highly personal user data is accessed, used for ransom. Hungover interns have no

There's more than meets the eye when you swap across chains on Polaris. Over the past year, we've carefully crafted a client side state machine containing over 20 states and 78 state transitions. Everything from signing and broadcasting, updating transaction statuses,

We just released a massive overhaul of crypto wallet UX with @Polaris_App accounts. If you have more than one crypto wallet account, it quickly becomes a headache to keep track of all of your assets and accounts. You often switch accounts repeatedly as you try to find the asset

Congrats @chris_mccord ! Phoenix framework is the web framework with the most dev satisfaction in 2025. I can definitely see why.