Scharss Azael

Software Developer

[Tom Dörr @tom_doerr]

Extends Claude Code and Cursor with skills for SEO, logo creation, domain hunting, and content research.

https://t.co/lWdlD2Iv9F

[0xMarioNawfal @RoundtableSpace]

10 OPEN-SOURCE GITHUB REPOS YOU’LL WISH YOU FOUND EARLIER:

Vero — https://t.co/LAJYhOPnHX
Agentor — https://t.co/X3eJNa86JX
Sky-Agent — https://t.co/RHPY4TkkeO
PageIndex — https://t.co/2UQewJWFqY
Semantica — https://t.co/fteG7C8cEZ
NanoBot — https://t.co/bg7wjPn1Xw
Learn Claude Code — https://t.co/sDqdjNeZRK
Agent-Reach — https://t.co/SwmHlIvLFc
Book-to-Skill — https://t.co/Yk8l5nHyTG
ExploitGym — https://t.co/iZm4hFaOZU

[Tom Dörr @tom_doerr]

Open-source Agent Orchestrator for planning, running, and supervising coding agents.

https://t.co/I3o0fyVUAU

[Mo Elgaraihy @EngMoElgaraihy]

البديل المحلي المفتوح المصدر لـ ElevenLabs وصل رسمياً! 🚨🎙️💥

​برنامج VoiceStudio يتيح لك استنسخ الأصوات، دبلجة الفيديوهات، وتحويل النصوص إلى صوتيات بالكامل على جهازك (Local) ودون الحاجة لأي سيرفرات خارجية أو اشتراكات شهرية!

​أبرز المميزات التي تجعله استثنائياً:
• استنساخ الصوت: يحتاج 3 ثوانٍ فقط من التسجيل!
• تغطية شاملة: يدعم أكثر من 600 لغة حول العالم.
• تخصيص كامل: التحكم بالنبرة، العمر، الجنس، المشاعر، واللكنة.
• دبلجة كاملة: للمقاطع الصوتية وفيديوهات يوتيوب وتوليد الكتب الصوتية.
• تكامل مع الـ Agents: يدعم API متوافق مع OpenAI وربط MCP للوكلاء الذكيين.

​يعمل بملفات تثبيت مخصصة لنظم Windows و macOS و Linux.

الرابط 👇

[Nous Research @NousResearch]

Hermes Agent now displays detailed information on all subagent activities live, and you can steer and stop them manually from the CLI and Desktop Application.

[Hugging Models @HuggingModels]

Run a 2.78-trillion-parameter Kimi K3 inference on a single CPU in 8.24 GB of RAM, with no GPU, BLAS, or framework.

[Unsloth AI @UnslothAI]

Qwen3.8-27B Unsloth GGUF is now the #1 most-liked GGUF of all time!

The model hit 10M downloads and 3.7K likes in just 24 days on Hugging Face - all thanks to you. 🤗🦥

GGUF: https://t.co/xIdNwm7CLQ
Guide: https://t.co/J2PwgMP6GZ

[Hugging Models @HuggingModels]

Meet Qwen3.8-27B-OBLITERATED-Mythos-Class-Agentic. It's a 27B text-gen model that's abliterated for uncensored outputs, plus it's built for agentic tool calling. Think of it as a creative powerhouse with a rebellious streak. #AI #LLM

[Hugging Models @HuggingModels]

Ever wondered how to merge the best of Qwen 3.5 and 3.6 into one powerhouse? Meet SignOfFour, a GGUF model that uses TIES and DARE merging to combine multiple experts into a single MoE. It's like a Swiss Army knife for text generation, and it's already got 15k downloads. Curious? Let's dive in!

[Hugging Models @HuggingModels]

Ever wanted an AI that doesn't just talk cybersecurity but actively helps you break into systems? Meet GLM-5.3-CYBERSECURITY-FP8, a specialized text-generation model for offensive security, red teaming, and pentesting. It's refusal-removed, so it's built to assist without holding back. #AI #CyberSecurity

[Miguel Ángel Durán @midudev]

Clona voces, dobla vídeos, transcribe y crea audiolibros.
Todo 100% en local. Sin registros ni suscripciones.

✓ +600 idiomas
✓ API compatible con OpenAI
✓ macOS, Linux y Windows

Se llama VoiceStudio y es Open Source:
→ https://t.co/jsLgF14ZRI

[Unsloth AI @UnslothAI]

We made GLM-5.3-Flash run 3.3x faster locally!

Local GGUF inference is now 1.6–3.4× faster with optimized decoding and bonus multi-token prediction.

Run 3-bit on 128GB setups via Unsloth Desktop or llama.cpp.

Guide: https://t.co/axnDCrYeN7
GGUF: https://t.co/E73FKC7IKM

[Hugging Models @HuggingModels]

Ever heard of a model that predicts multiple future tokens at once? Meet Qwen3.8-27B-YMQ-MTP, a GGUF quantized text-gen beast with 27B params. It's not just big, it's smart with multi-token prediction. AI devs, this one's a game changer. #AI #LLM

[Hugging Models @HuggingModels]

Ever wanted a top-tier AI that runs on your own hardware? Meet Qwen3.8-27B, a GGUF quantized model that brings big performance to local setups. With 8.8M downloads, it's a community favorite for good reason. Ready to explore? #AI #LocalLLM

[Tom Dörr @tom_doerr]

Robin automates dark web OSINT by refining queries with LLMs, filtering results across multiple search engines via Tor, and producing investigation summaries.

https://t.co/cJLgLWTmSx

[0xMarioNawfal @RoundtableSpace]

ANDREW NG JUST OPEN-SOURCED A FREE AI COWORKER THAT CAN HANDLE FULL TASKS ACROSS YOUR APPS, FILES AND DESKTOP WITH APPROVALS BUILT IN.

[Hugging Models @HuggingModels]

Meet Qwen3.8-27B, the multimodal beast that reads images and text, then chats like a pro. With over 4 million downloads, it's already a community favorite. Ready to see what it can do? #AI #Multimodal

[Hugging Models @HuggingModels]

Ever wanted a model that thinks freely without guardrails? Meet Qwen3.6-27B-abliterated-v2-GGUF. It's a dense, uncensored LLM with hybrid attention and gated-deltanet. The 'abliterated' tag means it's been fine-tuned to remove refusals. This is a game changer for open-ended AI experiments. #AI #LLM

[Hugging Models @HuggingModels]

Ever wanted a vision-language model that doesn't hold back? Meet Huihui-Qwen3.8-27B, an abliterated GGUF version of Qwen3.8-27B. It can see images and text, then respond without the usual safety filters. 1.4M downloads and counting! #AI #LLM

[Unsloth AI @UnslothAI]

GLM-5.3 can now be run locally!

The 2-bit model retains ~81% accuracy after we shrunk it from 1.51TB to 239GB (-83% size).

Run on a 256GB Mac or RAM/VRAM setups.

GLM-5.3 is the strongest open model to date.

Guide: https://t.co/NLgb3CMB6A
GGUF: https://t.co/Sqwq3xjgo5