Shane

AI Dev Robotics Dev Graphic Design

[Jonathan Richard Schwarz @schwarzjn_]

We've just made a major finding for SovereignAI 🚨:

Take any open-weight model (here: Qwen3.5-397B), apply our π-shaped Continual Learning, and own a genuine frontier model competitive with Opus 4.8 for ~$450k in compute.

Full tech report + open-source models coming soon!

[Unitree @UnitreeRobotics]

Unitree Super Athlete AS2-W 😉
Fluid movement, compact yet exceptional. Supports a continuous 16kg payload, with 30+ km unloaded driving range

[tonbi @tonbistudio]

You can now trade directly on Robinhood with your agent, and it's surprisingly easy to set up.

I made a quick video showing how to connect to the MCP server (with any agent, ClaudeCode, Codex, Hermes Agent etc.), trigger the authentication flow, and open your agentic account.

[Shane @shanecastile]

@thekitze stability

[OpenShip @openshipio]

Introducing OpenShip.

An open-source application platform for building, deploying, operating, and scaling applications on infrastructure you own.

Replace deployment tools, managed services, and infrastructure workflows with one open-source platform.

Available today:

- Mail Server (Built in. One click).

• Runs on your own VPS
• Unlimited domains
• Unlimited mailboxes
• Modern webmail included
• Connect with Gmail, Outlook, Apple Mail, Thunderbird, or any IMAP/SMTP client
• Send email directly from your applications using SMTP
• No mailbox subscriptions or API fees
• High email deliverability

- Deployment:

• Deploy any stack
• Git-based deployments
• Zero-downtime deployments
• One-click rollbacks
• Development, Staging, and Production environments
• Multi-branch deployments with isolated environments • Deploy to VPSs, dedicated servers, cloud VMs, or your homelab

- Services:
Provision the services your applications need in one click.
Replace multiple managed providers with services running on your own infrastructure.

• Supabase
• PostgreSQL
• MySQL
• MariaDB
• MongoDB
• Redis
• MinIO
• Meilisearch
• Qdrant
• RabbitMQ
• Kafka
• ClickHouse
• Elasticsearch
...and deploy any other service alongside your applications.

- Operate:

• Live deployment logs
• Live request logs
• Real-time traffic analytics
• Automated backups
• Monitoring
• Secrets management
• Domains
• Automatic SSL
• Environment variables
• Scheduled jobs
• Health checks

-Multi Environments:

• Separate Development, Staging, and Production environments
• Deploy every branch independently
• Test changes before production
• Isolated services, secrets, and configuration per environment

- Security & Teams:

• Team management
• Role-based access control
• IP allow/block rules
• Rate limiting
• Security rules

- Developer Experience:

• Web dashboard
• Native desktop application
• CLI
• REST API
• MCP support for AI agents, just add the mcp and your agent can do the work for you
• Manage your infrastructure without living in SSH

- Coming Soon:

• Multi-server clustering for applications and databases
• One-click load balancing
• Horizontal scaling across multiple servers
• Built-in high availability and failover
• Scale from a single VPS to a cluster with the same workflow
• Just add servers. OpenShip handles the rest.
Open source.

[Shane @shanecastile]

@Stake Woot!

[Zane Chen @chenzeling4]

744B parameters. On a laptop. With 25GB RAM.

Colibri runs GLM-5.2 (744B MoE) in pure C with zero dependencies. The trick: only ~40B params activate per token, so it keeps the dense part resident and streams experts from disk on demand. A single 2,400-line C file. No GPU, no BLAS, no Python at runtime.

This shouldn't work. But it does.

⭐ 2.1K #AI #OpenSource

https://t.co/W8dnCQmNnL

Follow for daily dev finds 🔔

[Harsha Subramanyam @Shad0WShinigami]

Made a skill for creating lyric videos for my @suno songs using @NousResearch Hermes agent. Hermes with the new GPT 5.6 models is insanely cracked. @Teknium any plans for a community skill hub? GPT-Image-2 + Omni Flash for the visuals

[ClaudeDevs @ClaudeDevs]

https://t.co/v694m8Eaj6

[Shane @shanecastile]

Fable on autopilot

[Machina @EXM7777]

https://t.co/IeIcbLNVCr

[𒐪 @SHL0MS]

i'm open sourcing UNBROKER: a tool that finds where your personal info is exposed by data brokers and files the removals for you

it runs as a skill in Hermes Agent
_________

your data is everywhere; hundreds of brokers publish your name, current and old addresses, phone, email, birthday, even your relatives. anyone can find where you live in about ten seconds

CCPA, CPRA, GDPR, and a growing number of state laws say a broker has to delete your data if you ask. there's just no easy bulk button. every broker has a different process and many make it intentionally difficult to exercise your right to delete

this is the entire business model for companies like DeleteMe, Incogni, EasyOptOuts; they charge you monthly (DeleteMe is $330/yr for a Family plan) to file removals that you can submit yourself for free, and then you're giving a new company the exact data you want to erase

so i built one you just run for free. your data never even has to leave your machine if you run a local model
_________

how it works:

first it builds search vectors from everything: every name, alias, email, phone, and address you've had (brokers might index you under a maiden name or a house you left in 2014, so the naive "current name + current city" approach can miss profiles). then it fans out parallel sub-agents across the broker list, which refreshes from a maintained public source

automation is tiered. when it can handle a broker end to end with your settings, it drives a browser through the opt-out form, sends the email, and opens the confirmation link itself. soft CAPTCHAs clear on their own with a real browser. anything only a human can finish comes back to you as a short list at the end

the email side doesn't need a stored password and can send opt-outs and open verification links through your own logged-in webmail. you can also wire up SMTP, or keep it manual and just send the drafts it writes

it tailors every request to your jurisdiction, filing under the framework that applies where you live: CCPA and CPRA in California, GDPR in the EU and UK, a general right-to-delete request everywhere else. if you're in California it also uses the state's DROP portal, a single request that covers 500+ registered brokers at once

it holds as little of your data as it can, and keeps it local. dossiers are encrypted at rest if you want, opaque ids keep your real name out of every filename and log, and nothing leaves your machine unless you opt in

brokers sometimes relist you eventually or new ones find your data, so every case is tracked in a ledger and can be re-scanned on a cron schedule so if your data pops back up it files the removal again

https://t.co/2jfQxBYZkW

[Shane @shanecastile]

Great Hermes /learn tip from @tonbistudio

[tonbi @tonbistudio]

A few tips for the /learn command in Hermes Agent that made it way cleaner for me.

Keep a separate "classroom" directory. Just a plain folder where all your learning and skill-building lives, away from your actual project context.

Inside it, keep a "textbook" file with the key paths and links you reuse: your Claude Code sessions folder, GitHub, folders full of papers, whatever. Then you can start a session, say "review the last Claude Code session, check the textbook," and it knows exactly where to look.

That's the trick I like most. You can pull a whole Claude Code conversation into Hermes as a source (point it at the sessions folder, or copy a specific session ID and have it search just that one), then /learn it into a reusable skill.

Doing it in the classroom instead of your project session means you can talk through exactly how you want the skill to look without muddying your project's context, and every skill you build lands in one folder you can go back to. I'll be having a full video on /learn next week, so be sure to subscribe to my YouTube channel!

[dotta 📎 @dotta]

Get Hermes and Paperclip working together in less than a minute

https://t.co/GY95iKA6kc

Control Hermes with Paperclip or
Control Paperclip with Hermes

it's super easy

[Daniel Han @danielhanchen]

DeepSeek just released DSpark for V4 Flash & Pro, a new speculative decoding method boosting throughput by 51% to 400%!

DS also showed DSpark works well for other models like Gemma & Qwen

Github: https://t.co/EGVYpc1kcK
Paper: https://t.co/TaBMRVlaW9
HF: https://t.co/289jVU2pxh

[Shane @shanecastile]

@Heistedxyz Redeem

[tonbi @tonbistudio]

I made a short video demonstrating how to use /learn in Hermes Agent to take a bunch of different sources, as well as your own preferences expressed to Hermes, and create a reusable skill.

It's never been easier to teach your Hermes exactly how to work for you!

[Shane @shanecastile]

Solar powered!

[Max Zanoga @zanoga]

Finally finished building my AI datacenter! 🚀

32x3090s across 4 servers (8 GPUs each), all connected over InfiniBand.

The whole setup is solar-powered with a massive battery bank and generator backup.

More technical details and benchmarks coming soon.

[Brian Roemmele @BrianRoemmele]

BOOM! NEW OPEN SOURCE BEATS OPEN AI AND ANTHROPIC—AGAIN!

Includes:

Continual Pre-Training!
Supervised Fine-Tuning!
Reinforcement Learning!

In a local model.

Mr. @Grok CEO is going insane on this. We already trained 1 hour on our data!

Meet Qwen-AgentWorld Revolutionizes AI Agents – And We’re Testing It Now at The Zero-Human Company!

This is massive. Alibaba’s Qwen team just open-sourced Qwen-AgentWorld, the first native language world model built from the ground up to simulate seven key agent environments: MCP, Search, Terminal, SWE, Web, OS, and Android. Environment modeling is the core training objective from day one, not a bolted-on feature.

Why This Changes Everything

Most models train to act as agents. Qwen-AgentWorld trains to model the world those agents operate in. It predicts next-state observations with remarkable accuracy after any action, using long chain-of-thought reasoning.

The three-stage training pipeline is brilliant:

•Continual Pre-Training (CPT) injects massive environment knowledge and dynamics through real interaction trajectories.

•Supervised Fine-Tuning (SFT) turns that into structured next-state prediction.

•Reinforcement Learning (RL) sharpens fidelity with hybrid rewards.

CPT is a very big deal. Starting environment modeling right in continual pre-training embeds deep causal understanding, state tracking, and domain knowledge directly into the model’s core weights.

This creates a true foundation model instead of surface-level adaptations on a general LLM.

The result?

Far better simulation quality, stronger zero-shot transfer to agent tasks, and agents that genuinely “predict before they act.” It lifts performance dramatically without extra agent-specific tuning.

Benchmark Domination

On the new AgentWorldBench, the big 397B MoE model scores 58.71, beating GPT-5.4 (58.25) and Claude Opus 4.8 (56.59). The open-source 35B MoE (3B active, 256K context) jumps +8.66 points over its base and surpasses Claude Sonnet 4.6. Controllable sim RL even outperforms real-environment training in several cases, with predictive modeling transferring huge gains (+12.3 in multi-tool tasks) zero-shot.

Why The Zero-Human Company Is All-In

At The Zero-Human Company we build fully autonomous systems that minimize human oversight. Qwen-AgentWorld is ideal for us. Running it locally lets us simulate thousands of parallel agent runs cheaply and safely. The built-in world modeling accelerates learning, improves long-horizon planning, and boosts error recovery in our workflows. We’re already seeing strong results in internal tests.

Head-to-Head Comparison

•Beats GPT-5.4 and Claude Opus 4.8 on AgentWorldBench.

•Crushes typical post-hoc agent adaptations thanks to native training.

•The 35B open model rivals or exceeds frontier closed models in simulation power.

From China, But Fully Yours

Yes, it comes from Alibaba’s Qwen team in China. But you run the full weights on your own hardware with no cloud calls, no telemetry phoning home, and total privacy.

Complete control on your stack.

That’s a huge advantage for enterprise and sovereign deployments.

Qwen-AgentWorld marks a foundational leap toward truly capable general agents. We’re deploying it aggressively at The Zero-Human Company to push autonomous intelligence further. The agentic future just got turbocharged.

And get this Dario, no “Gun License” required. How could it be.

I will show more of what this does soon.

[Nav Toor @heynavtoor]

A lawyer in Manhattan gets a 500-page contract. Every clause needs to be searchable. By hand: one week.

An accountant in Chicago gets 200 scanned invoices. Every number needs to land in a spreadsheet. By hand: four days.

A researcher at Stanford has 50 academic papers. Tables, formulas, charts locked inside PDFs. By hand: two weeks.

Every one of them is losing days of their life to copy-paste.

Now meet MinerU.

A free and open source tool that reads any PDF, Word doc, PowerPoint, Excel sheet, or scanned image. It pulls out the text in reading order. Tables become clean HTML. Equations become LaTeX. Handwriting handled. 109 languages.

You give it a 200-page PDF. You get clean Markdown back in 90 seconds.

What makes it different from every other PDF tool:

- Multi-column layouts. It reads top to bottom within each column. Not left to right across the page. Like a human reads.
- Scanned documents. OCR built in. Point it at a photo of a printed page from 1995. Get clean text back.
- Math formulas. LaTeX-quality recognition. Every equation renders correctly.
- Tables. Merged cells, multi-row headers, tables that span three pages. All preserved.
- Ten-thousand-page documents. Sliding window processing. No manual splitting.
- Batch mode. Point it at a folder of 500 documents. Walk away.

Three ways to use it:

- CLI. One command per document.
- Python SDK. Five lines of code.
- Web app at https://t.co/AIC2NNey41. Upload, click, download. No install.

Plugs into Claude Desktop, Cursor, Windsurf, LangChain, LlamaIndex, RAGFlow, Dify, and FastGPT. Feed extracted documents straight to your AI agent.

The story:

The OpenDataLab team at Shanghai AI Laboratory needed to extract clean text from millions of scientific documents to train a language model. Existing tools failed. They built their own. Then they open sourced it.

68,551 stars. MinerU Open Source License, built on Apache 2.0. Free for personal and commercial use. Three technical reports on arXiv.

Adobe Acrobat Pro charges $239.88 a year. It still loses your tables.
ABBYY FineReader Corporate charges $165 a year. It still cannot do equations.
Mistral OCR charges $2 per 1,000 pages. Your bill never stops.

MinerU costs $0. Runs on your laptop. Your documents never leave your machine.

Here is the wild part.

The lawyer got her contract back in 4 minutes. Every clause searchable.
The accountant fed 200 invoices in. Every number landed in a spreadsheet in 12 minutes.
The researcher fed his 50 papers in. He wrote his literature review on a Sunday afternoon.

The document your company has been processing by hand for years takes MinerU minutes.

Your documents become text. Your text becomes data. Your data becomes answers.

The week you used to lose to paperwork is back in your hands.