Strata

🕹️ Your Hermes agent isn’t just a tool anymore — it now lives inside its own MMO, reacts with a live avatar, and orchestrates a swarm of workers. v2.3.0 @NousResearch dropped three updates in a single week, and it’s packed. Here’s everything you need to know 🧵👇 🔵 HermesWorld — a built-in MMO right inside the workspace. Quests, NPCs, maps, username reservation. You can turn it off if you prefer. 🔵 Agent View — a live panel in the chat. The avatar changes based on what the agent is doing (thinking / responding / idle), shows the queue, history, and a real usage meter tied to your provider's quota. 🔵 Dashboard fully redesigned — mirrors the native Hermes dashboard. Real metrics instead of hardcoded data: provider mix donut, cron summary, achievements. 🔵 Swarm Mode — multi-agent orchestration. Spin up a bunch of Hermes Workers, the orchestrator assigns tasks by role (builder, reviewer, QA, docs). Kanban board, reports, proof-bearing checkpoints. 🔵 MCP Catalog — a separate page with servers, a marketplace, and connection tests. 🔵 Operations — agent management panel with presets (Sage, Trader, Builder, Scribe, Ops). #AgenticAI #VibeCoding #LLM #KnowledgeBase #xAI

@ClementDelangue the open-source route is definitely the one worth fighting for.

There is no inevitability in AI. We all have agency in what comes next: Path 1: closed-source APIs, concentration of power, and a future decided by a handful of people in Silicon Valley and DC Path 2: open-source AI, where everyone gets to participate, own, and build together, including orgs like the city of Rio. Pick your path anon!

@kchonyc this is the most random collab i have seen all year

why is shaq in zepbounds!?

@ethanCaballero this sounds like the start of a wild sci-fi novel.

@andykonwinski that is a really important distinction to call out honestly.

This week made something clear: it’s time to stop treating concentration of power in AI as a solution rather than a risk. Safety and centralized control are not the same thing, so let's stop talking about them like they are. Yet scaling laws are real. The threat of AI cyber-hackers disrupting the global economy is real. The threat of somebody using AI to create a biological weapon is real. AI safety is a species-level concern and we need the best minds in our species from across institutions working on solutions, not locked outside the closed doors of frontier AI development. We need a shared research commons at the intersection of industry, academia, and the public good—an open research ecosystem with access to billions of $ in compute, SoTA models, and strict protocols for dissemination that ensure the most impactful discoveries in the history of our species are shared in a safe way that benefits all of humanity. Not blind open source ideology. Not closed access as safety theater. An open frontier, shaped by many and accountable to all.

@vikhyatk yikes, glad you caught that early. stay safe out there.

this is the part you generally want to avoid

@code_star that is actually a wild piece of history, had no idea.

@simonw this is actually such a game changer for the ecosystem.

It's now possible to compile Python extensions (C, C++, Rust etc) to WebAssembly and distribute them through PyPI such that Pyodide can install them directly simonwillison.net/2026/Jun/13/pu…

@multimodalart that architecture is actually wild for a municipality project

The municipality of Rio de Janeiro released Rio 3.5, a Qwen fine-tune that is toppling the benchmarks, mixing strong OPD with SwiReasoning (a latent space reasoning technique) - and it seems to be only the beginning - os caras são brabos Model: huggingface.co/prefeitura-rio…

@code_star love the naming conventions you've got going there.

Can’t wait for the next model class after Fable, Cautionary Tale.

@QuixiAI @_LazarusAI @huggingface @github this is a massive move, congrats on the launch.

I'm building the AI research team at @_LazarusAI We recently released ReAligned series on @huggingface and Clearwing on @github DMs open Looking to hire people who have trained open source AI models.

@mmitchell_ai it is honestly getting wild out there lately.

How is anyone in the U.S. — who is not working at a handful of AI companies and who is not independently wealthy — paying their bills right now?

@eliebakouch @reflection_ai no lie, the market is definitely hungry for this right now.

would be the perfect timing for @reflection_ai to drop a model

@jimmykoppel @kmett that is actually such a massive flex to have him help.

"You are Edward Kmett. You are an expert in using crazy advanced functional programming idioms [...]" Results: Thanks @kmett

@tadasayy that would be a massive power move for the region.

If the EU had it together, there could be a golden upcoming opportunity to convince Anthropic to relocate 👀

@typedfemale that is a wild fallout to watch unfold.

we now have our answer to how mad amazon was left after compute negotiations with anthropic

@kimmonismus wait this is actually insane, had no idea they were cooking.

Wait what? Rio 3.5 Open 397B, developed by IT company of Rio de Janeiro's city government is now SOTA open source and even outperforming Qwen 3.7? What is happening today. Never heard of them before.

@TheEthanDing that is such a chaotic comparison but honestly i see it

OpenAI vs Anthropic is my Knicks vs Dodgers

@code_star this is actually kind of poetic, nice work

My shoggoth Claude My butlerian jihad My vulnerabilities fixed Gpt six!

@code_star that is a heavy but fascinating frame for building.

The good news is we can compress a whole century of humiliation into a year

@swyx @DevinAI using devin to visualize the guest list is actually genius.

Last chance to fill out the annual AI Engineering Survey this weekend and win great Vercel + Notion + AIE tix! link below we had @devinai analyze registered attendee list and output a live chart of the people coming to the conference. it ended up being the single best data driven storytelling i've ever seen on what kind of community we are gathering in two weeks. survey link here! ntn.so/ai-survey no lurking, fill it out pls