Jeremiah

@hshah18 @linear @karrisaarinen You're describing @usehamster, the AI-native workspace for product teams, where context compounds, and your whole team refines and aligns. The age of the product wiki that nobody keeps up to date has passed. And Hamster two-way syncs with Linear (who we love).

@XanaIndustries @tom_doerr It's so good! A shame it hasn't had any updates in recent years.

@tom_doerr Fucking WHAT!???? I'm taking a look at whatever wizard created this thing.

Chromium browser in terminal with 0% CPU idle github.com/fathyb/carbonyl

@bazbazeso @GithubProjects Yeah, I was going to say. This funnels you into paying for an API key when there are projects that do the same thing 100% local for free.

@GithubProjects And you send your codebase in their servers 😴 Use grepai. Same DX, 100% local

This is wild: You can search your codebase like: “where do we handle auth?” And actually get answers. mgrep = semantic grep for code, docs, and more 🔗 osp.fyi/mgrep

@EyalToledano Funny how most of the chaos just goes away when you're clear about what you're building from the start!

every time you start a new claude code session you spend the first 10 minutes re-explaining your project "here's the stack. here's what we're building. here's what was decided last week. here's the file structure. DON'T TOUCH THIS PART WE JUST REBUILT IT" but it's not just your own context. your teammates shipped 3 new things since yesterday, two architectural decisions changed and a dependency got swapped out. you need to capture all of that too, or claude is building from a stale snapshot you won't remember everything. so claude compiles context from scratch, misses things, and pulls in a direction that might completely miss the point. now multiply that by every dev on your team, every session, all day literal coordinated drift what we do instead: the .hamster folder syncs decisions, plans, and context to the filesystem automatically. claude reads it and just knows. no re-explaining. no stale snapshots. everyone's always got a fresh .hamster folder which updates in real-time as the rest of the team (or you) ship decisions, tasks, briefs, methods, skills, etc try it. you'll love it → @usehamster

everyone on your team maintaining their own CLAUDE.md is a symptom, not a solution. the root cause is that shared context has nowhere to live and evolve as your team makes decisions. you can't fix it with naming conventions or a better folder structure. decisions need a home. not a static file someone remembers to update. a workspace that accumulates as the team works. when a decision changes, it changes once, and every agent on the team pulls from that. there's no need to keep the markdown files up to date or copy-paste anything anywhere. claude just knows. your PRDs, your tasks, your skill files, your CLAUDE.md are all projections of the same underlying decisions. if the decisions live somewhere real, everything else stays aligned. if they stay up to date automatically, the rate of progress can explode because the synchronization overhead disappears. that's what we've been building into hamster. decisions get a home. blueprint holds your product's current state. methods encode how agents should work. the projections stay aligned because the source of truth is real. dm if you want to try it GA reeealllly soon!

@sawyerhood @ptsi Fantastic - I should have looked harder! 🙌

@harveyfullstack @ptsi i do in fact have support for it!

tired: assigning tasks to agents wired: agents assigning tasks to you

@sawyerhood @ptsi Any plans to integrate with Claude's Agent SDK so we can use our existing Claude Code subscription to run middleman? 👀

@ptsi yeah i'm playing with this in middleman.tools

@thorstenball @_dhamidi These are the fundamentals to what made me pursue a career as a web developer all the way back in 2012.

The coding agent is dead, the editor is dead, and software is dead, of course, but you know what's still alive? That's right: the browser. (Spotted on @_dhamidi's phone.)

@MatthewBerman @LinusEkenstam Plot twist: he joins Anthropic 🦞

@LinusEkenstam Lol they don’t need me

I've spent 2.54 BILLION tokens perfecting OpenClaw. The use cases I discovered have changed the way I live and work. ...and now I'm sharing them with the world. Here are 21 use cases I use daily: 0:00 Intro 0:50 What is OpenClaw? 1:35 MD Files 2:14 Memory System 3:55 CRM System 7:19 Fathom Pipeline 9:18 Meeting to Action Items 10:46 Knowledge Base System 13:51 X Ingestion Pipeline 14:31 Business Advisory Council 16:13 Security Council 18:21 Social Media Tracking 19:18 Video Idea Pipeline 21:40 Daily Briefing Flow 22:23 Three Councils 22:57 Automation Schedule 24:15 Security Layers 26:09 Databases and Backups 28:00 Video/Image Gen 29:14 Self Updates 29:56 Usage & Cost Tracking 30:15 Prompt Engineering 31:15 Developer Infrastructure 32:06 Food Journal

@sanketsahu Dude, you're cooking!

Now run git, npm, ffmpeg in the browser with lifo.sh — the fast Linux-like sandbox for browsers and now for Node environment! Built for Agents & Humans, no VM, no cloud, just a sandbox that runs anywhere, fast! ⚡️

@SumitM_X "modern" frontend developer. Times were simpler back in the day...

As a Frontend Developer, Please slap yourself if you cannot clearly explain at least 10 of the following : Hydration Partial hydration Islands architecture Streaming SSR Concurrent rendering Time slicing Reconciliation algorithm Fiber architecture Virtual DOM diffing complexity Structural sharing Immutable data patterns Referential equality Memoization pitfalls Stale closure problem Event loop (macro vs microtasks) Task starvation Layout thrashing Critical rendering path Render blocking resources Tree shaking internals Code splitting strategies Dynamic import chunking Module federation Shadow DOM Custom Elements lifecycle Web Components interoperability Web Workers vs Service Workers SharedArrayBuffer Transferable objects OffscreenCanvas WebAssembly integration Browser compositing layers Paint vs composite vs layout GPU acceleration in CSS CSS containment Subpixel rendering IntersectionObserver internals ResizeObserver loop limits MutationObserver cost IndexedDB Service Worker lifecycle traps Cache invalidation strategies Stale-while-revalidate ETag vs Cache-Control HTTP/3 and QUIC Priority hints Preload vs Prefetch vs Preconnect CORS preflight SameSite cookie modes CSRF vs XSS mitigation Content Security Policy (CSP) Trusted Types DOM clobbering Prototype pollution Race conditions in UI state Tearing in concurrent UI Scheduler priorities Render waterfalls Suspense boundaries Selective hydration Server components Edge rendering Micro-frontend orchestration Finite state modeling Event sourcing in frontend Optimistic UI rollback strategy Offline conflict resolution CRDT basics for collaboration WebRTC Backpressure in streams API AbortController Streaming fetch response handling Browser memory leak detection Detached DOM nodes Garbage collection timing PerformanceObserver API Long tasks API First Input Delay (FID) Interaction to Next Paint (INP) Cumulative Layout Shift (CLS) Largest Contentful Paint (LCP) Speculative prerendering Priority inversion in async code Deterministic rendering Idempotent UI actions Accessibility tree ARIA live regions internals Pointer events

@jonathanfishner @tom_doerr Awesome! Wasn't trying to criticize. I was just expressing how if it is quite literally multiple OpenClaws then it must be expensive. 😆

@harveyfullstack @tom_doerr Hi! Tnx for the feedback We actually did it very efficiently, it's running each agent as an isolated cron every 15m and continues from where it stopped. Still ongoing improvement currently. Will write more about it soon

Coordinates AI agents through shared files and a dashboard github.com/getclawe/clawe

@ghostshippr @rauchg Yeah as long as LLMs hallucinate, you will always need to fact-check or else get gaslit

@rauchg the future is your coffee getting cold while you debug the agent's insights

Every Monday I get a deep AI analysis of our metrics across every product area to enjoy with my coffee. Anomalies, growth, trends, recommendations. AI spots patterns human analysts easily miss. I can @ the agent for further questions. AI will soon be running every company.

@sawyerhood I applaud you for open-sourcing this. Amazing.

if you are a large org building one of these yourself, i highly recommend giving the terragon codebase a look. both the ui and the architecture is pretty well thought out and you can vibe code it to adapt to your own infra github.com/terragon-labs/…

@ryancarson I don't understand what you propose the solution is that cannot be solved in a TUI?

The new agent team feature in Claude Code has super confusing UX. All the model and agent labs need to move out of the TUI as soon as possible. Coding agents on the CLI made sense when we just interacted with one agent. Now all of us are trying to orchestrate teams of agents and the TUI makes zero sense (the IDE is even more hilariously out of date). I’ve built my own solution for orchestrating agents on top of openclaw (just bought antfarm.cool and might open source it) but surely we’ll see all the model and agent labs ship brand new UI for this soon. Orchestrating teams of agents is clearly where we’re going. Then orchestrating teams of teams of agents.

@Khaliqgant @ryancarson @mattshumer_ Feel free to take from it as you will! Just run `agent-relay up --tui` from this fork: github.com/harveyfullstac…

@harveyfullstack @ryancarson @mattshumer_ Amazing!

One thing that's so clear with GPT-5.3-Codex and Opus 4.6: Multi-agent systems are now real + extremely powerful. While I was testing 5.3, I had over a dozen agents working together using @agent_relay. It was a dramatic capability improvement over just one agent.

@ryancarson @mattshumer_ @Khaliqgant I was so intrigued by it I had to throw it into a TUI! Was surprised at how smooth it came out.

@mattshumer_ I'm currently trying this out and have a meeting booked with @Khaliqgant :)