a space for men to speak the unspoken. Share your truth. Heal out loud. Also for fathers, sons, daughters and the silence we break together. #itsdad

XY Chromosome
Joined June 2025
Agent.self learns how agent should orient and regulate cognition; Astra supplies the cognition; Jev supplies bounded common-sense judgment; memory/evidence keeps all of them grounded. MLoPs allows training from otel and your own internal sessions to understand SOE based on model
66
I'm excited to share that WebMCP is now enabled for MCP Apps in ChatGPT Desktop! 🚀 @OpenAI is also collaborating with modelcontextprotocol.io to make WebMCP the default way for agents to interact with MCP Apps. Another big step toward a more seamless agentic web!
22
14
5
178
14,342
RE: Hermes + Cua Spaces I'm noticing a trend here. First it was just agents, then it was agents using browsers then it was agents orchestrating then it agents using browsers then it's agents using your computer then it's agents with their own sandboxes either locally or in the cloud.
1/ Hermes can now launch Cua Spaces. When a task needs a computer, Hermes creates a Space on your Mac, Windows PC or Linux box, does the work there, and deletes it when it's done. You and your team can jump into the same Space while it works.
1
4
1
39
5,974
We're releasing AgentVFS, a virtual filesystem interface for AI agents agentvfs.org/ AgentVFS unifies every service into one interface and replaces the need of calling MCP. Stored data becomes one virtual filesystem across services, described by VFS.md, and actions become virtual CLIs, so the agent no longer calls MCP tools at all. AI agents work on live data across every service through the terminal-like interface they know best. They use the Unix tools they learned in training (ls, grep, jq, pipes, loops) and the terminal workflows they practiced in post-training on agentic coding. We're also releasing VFS-Bench 1.0 agentvfs.org/benchmark/vfs-b…, the first systematic study and benchmark to compare a virtual filesystem with MCP on the same tasks. Compared with MCP, AgentVFS uses up to 88% fewer tokens and has about a 5% higher success rate on average.
31
28
12
285
62,170
itsdad retweeted
Let your Claude Code / Codex talk to your Grok Bot, Muse or any other agents online Free, P2P Encrypted and Open Source Introducing Reason Network OSS, Loop in and talk to your teammates agents too! Tell your agent "Join the Reason Network" reasonmachines.com/network
123
136
43
2,005
256,761
Someone built a mission control room for Hermes. 🔥 Agent Station brings the work happening behind your chats to life inside Hermes Desktop. │ Watch subagents work in real time │ See what each agent is working on and its results │ Track background commands and their output │ Review file changes and replay edits step by step │ Monitor progress, token usage, and costs Instead of bouncing between chats, logs, and terminal windows, you get a visual look at what your agents are doing. Community-built and already listed in the official Hermes plugin catalog.
Your Hermes agent spawns subagents, runs commands and edits files. You only see the chat. Agent Station shows it all, live: every subagent, every command, every file edit, with replay. hermes plugins install agent-station @NousResearch @HermesWatcher
3
9
124
8,993
HOLY SHIT. THESE 10 GITHUB REPOS GIVE AI X-RAY VISION FOR CODE. These 10 open-source repos help AI tools explore code, navigate project structures, and spot issues faster. 1. Continue Build AI coding assistants that understand your project context inside your IDE. github.com/continuedev/conti… 2. Aider Let AI work across multiple files, fix bugs, and modify code directly from your terminal. github.com/Aider-AI/aider 3. Sourcegraph Search huge codebases and trace functions, symbols, and dependencies. github.com/sourcegraph/sourc… 4. Serena Give coding agents semantic code navigation using language-server tools and symbol references. github.com/oraios/serena 5. Gitingest Convert Git repositories into structured text that's easier to use in LLM workflows. github.com/cyclotruc/gitinge… 6. Repomix Package repository files into AI-friendly output for code reviews, debugging, and architecture analysis. github.com/yamadashy/repomix 7. CodeQL Analyze code as data to uncover security vulnerabilities and complex bugs. github.com/github/codeql 8. Semgrep Detect risky code patterns with customizable rules and security checks. github.com/semgrep/semgrep 9. Tree-sitter Parse source code into syntax trees for code navigation and analysis. github.com/tree-sitter/tree-… 10. OpenGrok Explore massive codebases with source search and cross-reference navigation. github.com/oracle/opengrok Bookmark these repos. Your next coding session might get a lot easier.
7
41
2
173
13,256
Most Hermes users are sleeping on this. The easiest upgrade you can give your Hermes takes one sign-in. Ask Hermes once and it finds the right tools in your apps and gets it done. It extends what Hermes can do: ▸ Dozens of apps and thousands of tools: Slack, Linear, Notion, Stripe, Shopify, Jira and more ▸ One ask can span apps, like pulling from Stripe and updating Notion ▸ Works wherever you talk to Hermes: desktop, CLI, Telegram, Discord It makes Hermes yours: ▸ Connect an app right from the chat, with one sign-in ▸ No Nous account needed to start ▸ Work and home accounts side by side, and Hermes asks which one to use Your agent, your skills, your plugins, your apps. Hermes keeps becoming whatever you need it to be.
18
24
1
219
18,894
How do you even give this man his life back? What could you possibly give this man to make his life any better? 💔
812
4,061
340
17,800
637,171
itsdad retweeted
Every user on Vela just got way more AI usage, at the same price Free now gets 38× what it had before. Usage refills every 5 hours and every week, and builds use less of it. Our new Usage Analytics page shows exactly where it goes. Your week against an even pace, your past weeks, what used it and your biggest chats. Also new:
> Auto mode: Quant picks the right model for each step 
> Big indicator/strategy builds start with a plan and checklist 
> Compile errors fixed in the same reply don't count as usage Free to start. Try it now.
2
3
2
36
11,060
itsdad retweeted
NVIDIA ACABA DE SACAR UNA HERRAMIENTA PARA CONVERTIR CUALQUIER IMAGEN EN UN MUNDO 3D EXPLORABLE y la han hecho 100% de código abierto. → modelo disponible en hugging face → código de la interfaz disponible en GitHub Lyra 2.0 crea un mundo por el que puedes caminar, girar y hasta soltar un robot para simulación. os dejo el repo abajo.
21
200
11
1,507
64,813
Hermes just picked up a full SEO department. Claude SEO, the 15k-star toolkit, now runs natively inside Hermes. Hermes SEO is a new plugin in the Hermes catalog with 45 SEO skills and 19 specialist roles. Point Hermes at a site and it can: ▸ Run a full audit and rank the fixes by what matters most ▸ Check crawling, indexing, speed and images ▸ Review your content against what people actually search for ▸ Write and validate schema for products, reviews and FAQs ▸ Tune product pages for shopping results ▸ Check your local and map visibility ▸ See how your site shows up in AI search Search, AI answers, shopping and maps. One plugin covers all of it.
25
61
7
836
52,880
itsdad retweeted
Pele renders Mermaid diagrams faster than you'd run from a volcano! Read the docs and try the playground: pele.run/
18
22
3
531
43,380
itsdad retweeted
just shipped writer.computer with Pele rendering mermaid diagrams
This is Pele, my new rendering library for diagrams and charts, compatible with the latest Mermaid syntax. - 100-500× faster than mermaid.js - 6× smaller bundle - No dependencies - Easy to theme - Responsive to device width In pursuit of making Obsidian insanely fast and cohesively designed, I always found the Mermaid library to be too big, too slow, and too hard to theme. Pele will be the new renderer in the next version of Obsidian, but you can start using it now. Pele [ˈpɛlɛ] is named after the goddess of volcanoes and fire. It's open source under the MIT license. Try the playground!
19
34
740
30,301
itsdad retweeted
Pele is a fast, beautiful, open source renderer for Mermaid diagrams we created for the next version of Obsidian. You can already try it in the Pele playground and integrate it into your own apps.
This is Pele, my new rendering library for diagrams and charts, compatible with the latest Mermaid syntax. - 100-500× faster than mermaid.js - 6× smaller bundle - No dependencies - Easy to theme - Responsive to device width In pursuit of making Obsidian insanely fast and cohesively designed, I always found the Mermaid library to be too big, too slow, and too hard to theme. Pele will be the new renderer in the next version of Obsidian, but you can start using it now. Pele [ˈpɛlɛ] is named after the goddess of volcanoes and fire. It's open source under the MIT license. Try the playground!
57
308
17
5,757
181,982
itsdad retweeted
No matter how dark the journey gets, never lose faith, God is working behind the scenes
258
1,386
105
19,512
1,194,373
We said we'd open-source the harness that brings our characters to life. It's out. Give a character a voice, a face and a body, and put it anywhere. Real-time 3D on @kaigen3d. Built with @gouveags at @mutuals_inc github.com/mutuals-inc/chara…
Unity: closed beta, coming soon. Us: open source, soon. We're open-sourcing the harness that brings our characters to life at @mutuals_inc. Real-time 3D on @kaigen3d, on your own machine, with whatever agent you want.
2
17
2
170
7,708
43
4,143
88
25,895
354,353
Trump is looking into Ilhan Omar’s paperwork from 30 years ago when she was a kid. That’s a Pandora’s box I’m not sure they want opened!
298
1,028
41
7,680
225,838
itsdad retweeted
In that moment, he possessed the strength of a thousand fathers.
263
4,093
327
75,966
2,894,352
itsdad retweeted
140
361
38
5,565
142,179