Alexander the great. (@cryptofrankhk) - Twitter Profili

Alexander the great. retweetledi

Claude Code artık ücretsiz çalışıyor. Sınırsız. Abonelik yok 🤯 Aracın adı free-claude-code. Ücretsiz bir NVIDIA API anahtarı alıyorsunuz, Claude Code'u localhost'a yönlendiriyorsunuz ve proxy, Anthropic API çağrılarınızı NVIDIA NIM formatına dönüştürüyor. Dakikada 40 istek. Fatura yok. Hiçbir zaman. Desteklenen modeller: → Kimi K2 → GLM 4.7 → MiniMax M2 → Devstral → Ve daha fazlası Düşünme token'larını ve araç çağrılarını gerçek zamanlı olarak aktarır. En çılgın yanı, Claude Code'u doğrudan telefonunuzdan kontrol edebilmeniz için yerleşik bir Telegram botu olması. 2 dakikalık kurulum. %100 açık kaynak. Claude Pro için ayda 20$ ödüyorsanız, yılda 240$ tasarruf ettiniz. Bu gönderiyi kaydedin. Bu hafta sonu kurun. Pazartesi günü ücretsiz kodlamaya başlayın. Yazılım geliştirirken ücretli içerik engellerini ortadan kaldıran daha fazla araç için @DeepTechTR hesabını takip edin.

Türkçe

8

31

214

11.9K

Alexander the great. retweetledi

Nekt0@Nekt_0·2d

This $30 fake AI model just pulled 12,000,000 views and $14,000 in brand deals The coat The sandals The eye contact Every single detail was generated from a single prompt Traditional video production is a massive waste of capital You don't need casting calls, lighting crews or a studio You just need a laptop and the right AI stack The workflow is completely straightforward: 1. Find a realistic, phone-quality reference on Pinterest 2. Generate the base image and lock the face using Nano Banana Pro 3. Drop the start frame into Kling 3.0 to animate the movement and dialogue 4. Synthesize the audio with ElevenLabs and sync it all together in CapCut Four simple steps to create an infinite, hyper-realistic content machine Most people are still wasting thousands on camera gear and burning out trying to film themselves The smart ones are using AI pipelines to replace the entire production studio

Insomnia@insomnia_vip

x.com/i/article/2056…

English

32

19

221

32.2K

Alexander the great. retweetledi

m0h@exploraX_·2d

no money for chatgpt pro or claude pro? this is for you🫵🏽 someone open-sourced 800M tokens/month of free AI inference on github. – Free LLMs, 2.3k stars on github, MIT licensed – no subscription. no rate-limit panic. no vendor lock – 14 providers stacked: google, groq, cerebras, openrouter, github models + 9 more – one openai-compatible endpoint. drop-in for any SDK – smart router with auto-failover, sticky sessions, encrypted key storage – runs locally on your machine it's a fresh repo, 2300 stars on github already.

m0h@exploraX_

you don't need to pay for ElevenLabs & WisprFlow subscription anymore. someone just open-sourced BOTH in one app. completely free. runs locally. no API keys. no usage caps. → clone any voice → global dictation hotkey → your agent can talk back → 7 TTS engines → 23 languages here's how to set it up under 5mins: 1/ download mac (apple silicon): voicebox.sh/download/mac-a… mac (intel): voicebox.sh/download/mac-i… windows: voicebox.sh/download/windo… docker: docker compose up open the dmg, drag to applications, launch. 2/ clone your voice (60 sec) → profiles tab → + new profile → name it, pick a language → upload a 10–30s clean audio sample (or record live in-app) → save that’s your voice. reusable across every engine. 3/ generate speech → generate tab → pick your profile → type your text → hit generate first run downloads the model (one-time). after that it’s a few seconds per clip. pro tip: use chatterbox turbo + type / in the box to drop in [laugh] [sigh] [gasp] tags. 4/ give your AI agent your voice this is the part that broke me. voicebox ships with an mcp server. add it to claude code / cursor / cline once, and your agent calls voicebox.speak to talk back in your cloned voice. settings → mcp → copy the snippet into your agent’s config. done. 5/ dictate into anything → settings → dictation → set a global hotkey → hold it anywhere on your system, speak, release → transcript pastes into the focused text field slack, email, code, browser — works everywhere. 6/ that’s it. no api keys. no usage caps. no audio leaving your machine. you just replaced two SaaS subscriptions with a 200mb native app. github.com/jamiepine/voic… follow and turn on post notification for more content that helps you maximize the use of AI.

English

27

68

663

132.8K

Alexander the great.@cryptofrankhk·1d

💰 I just claimed 0.0099 SOL with @unclaimed_sol! Check if you have some too! 🚀

English

0

1

14

Alexander the great. retweetledi

EXM@exmtweaks·3d

🚨 WINDOWS USERS 🚨 Disable Memory Compression if you have 16GB RAM or more to reduce extra CPU activity from Windows memory management. Memory Compression can help systems with LOW RAM by compressing unused memory instead of pushing more data to disk, but on HIGH RAM PCs, disabling it may reduce unnecessary background CPU overhead, which boosts performance 📈 For systems with under 16GB RAM, we recommend keeping Memory Compression enabled so Windows can manage limited memory more efficiently.

English

24

132

1.6K

239.3K

Alexander the great. retweetledi

Computer Knowledge@Computer_basic0·4d

How to clear junk files on windows Pc

English

1

41

159

9.4K

Alexander the great. retweetledi

How To AI@HowToAI_·7 May

China open-sourced a desktop automation agent that runs 100% locally. It sees your screen, controls your mouse and keyboard, and completes tasks in any app through natural language. 100% Open Source. 29k stars on GitHub.

English

82

218

1.6K

289.9K

Alexander the great. retweetledi

Oliver Prompts@oliviscusAI·28 Nis

This tool can download literally anything from link 🤯 100% free. open source. no ads.

English

32

257

2.4K

170K

Alexander the great. retweetledi

Vivek | Cybersecurity@VivekIntel·19 Nis

🛡️ The Largest Open-Source Cybersecurity Skills Library for AI Agents 754+ skills • 26 domains • 5 framework mappings • MITRE ATT&CK + ATLAS + D3FEND + NIST CSF + AI RMF • DFIR, Red Team, Threat Hunting, Cloud, Malware • Real workflows — not summaries • Plug into Claude, Copilot, Codex, Cursor 🔗 github.com/mukul975/Anthr… #AISecurity #CyberSecurity #RedTeam #Pentesting

English

2

94

424

19.4K

Alexander the great. retweetledi

Python Developer@PythonDvz·15 Nis

You don't need to spend a single dollar to build a production AI system in 2026. Here's the full stack: → LLM: Ollama + Gemma 4 / Llama 3.3 / Mistral Small 4 (local, free) → Orchestration: LangGraph / CrewAI (open source) → RAG: LlamaIndex + ChromaDB / Qdrant (local) → Tool Layer: MCP — the open protocol connecting agents to everything → Code Agent: Claude Code CLI / Aider → Frontend: Next.js + Vercel free tier / Streamlit → Data: SQLite / DuckDB / Supabase free tier → Observability: Langfuse / Phoenix (self-hosted) → Deploy: Docker / Cloudflare Workers / HuggingFace Spaces Total cost → $0. The tools are free. The architecture knowledge is what's valuable. Save this for your next build 🔖 Credit: codewithbrij #AIArchitecture #AgenticAI #LLM #Ollama #Gemma4 #LangGraph

English

57

524

2.6K

134.7K

Alexander the great. retweetledi

Manisha Mishra@manishamishra24·6d

16 best GitHub repos to build AI engineering projects! (star + bookmark them): The open-source AI ecosystem has 4.3M+ repos now. New repos blow up every month, and the tools developers build with today look nothing like what we had a year ago. I put together a visual covering the 16 repos that make up the modern AI developer toolkit right now. The goal was to cover key layers of the stack: 1) OpenClaw ↳ Personal AI agent that runs on your devices and connects to 50+ messaging platforms 2) AutoGPT ↳ Platform for building, deploying, and running autonomous AI agents 3) Hugging Face Transformers ↳ The model framework for state-of-the-art ML across text, vision, audio, and multimodal 4) Ollama ↳ Run powerful LLMs locally on your hardware with a single command 5) LangChain ↳ The foundational framework for building agents and LLM-powered applications 6) Open WebUI ↳ Self-hosted, offline-capable ChatGPT alternative with built-in RAG and plugin system 7) ComfyUI ↳ Node-based visual workflow builder for AI image and video generation 8) Sim ↳ Open-source drag-and-drop workflow builder for creating and deploying AI agent pipelines 9) Opik ↳ Open-source platform to trace, evaluate, and monitor LLM apps and agentic workflows 10) Firecrawl ↳ Turn any website into LLM-ready markdown or structured data 11) Airweave ↳ Open-source context retrieval layer that syncs 50+ data sources for AI agents 12) vLLM ↳ High-throughput, memory-efficient LLM serving engine for production deployments 13) Unsloth ↳ Fine-tune and run open models 2x faster with 70% less memory 14) OpenPipe ART ↳ Train multi-step AI agents for real-world tasks using reinforcement learning 15) OpenCode ↳ Open-source, provider-agnostic AI coding agent built for the terminal 16) Chandra OCR (by Datalab) ↳ State-of-the-art OCR model for complex tables, forms, handwriting, and 90+ languages These aren't just repos with high star counts but rather the building blocks behind most AI products shipping today. If you're building anything with LLMs, agents, or RAG in 2026, you're probably already using a few of these. P.S. This visual was inspired by a similar one from the ByteByteGo team. I extended it to be more engineering and builder-focused.

Kshitij Mishra | AI & Tech@DAIEvolutionHub

The AI industry has a dirty little secret: Half of “AI engineering” is just fighting CUDA errors. Wrong PyTorch wheels. Broken NVIDIA drivers. Mismatched CUDA versions. Dependency hell that destroys your entire environment overnight. Meanwhile you’re sitting there wondering why your GPU suddenly stopped existing. This open-source project fixes that chaos in one command. It scans your entire AI stack: GPU → CUDA → cuDNN → PyTorch → TensorFlow → Docker Then tells you exactly what’s broken and how to fix it. Honestly one of the most useful AI dev tools I’ve seen this year. github.com/mitulgarg/env-…

English

2

5

27

1.8K

Alexander the great. retweetledi

m0h@exploraX_·13 May

you don't need to pay for higgsfield or runway anymore. there's an open-source AI image/video generator on github, completely free. – no ads. no subscription. no heavy install. – 200+ models (seedance pro, kling, sora, veo, flux, midjourney) – cinema studio with real camera controls (lens, focal length, aperture) – just prompt → generate – pairs with claude code & codex via a skills library it's 10.7k stars on github already.

m0h@exploraX_

you don't need to pay for ElevenLabs & WisprFlow subscription anymore. someone just open-sourced BOTH in one app. completely free. runs locally. no API keys. no usage caps. → clone any voice → global dictation hotkey → your agent can talk back → 7 TTS engines → 23 languages here's how to set it up under 5mins: 1/ download mac (apple silicon): voicebox.sh/download/mac-a… mac (intel): voicebox.sh/download/mac-i… windows: voicebox.sh/download/windo… docker: docker compose up open the dmg, drag to applications, launch. 2/ clone your voice (60 sec) → profiles tab → + new profile → name it, pick a language → upload a 10–30s clean audio sample (or record live in-app) → save that’s your voice. reusable across every engine. 3/ generate speech → generate tab → pick your profile → type your text → hit generate first run downloads the model (one-time). after that it’s a few seconds per clip. pro tip: use chatterbox turbo + type / in the box to drop in [laugh] [sigh] [gasp] tags. 4/ give your AI agent your voice this is the part that broke me. voicebox ships with an mcp server. add it to claude code / cursor / cline once, and your agent calls voicebox.speak to talk back in your cloned voice. settings → mcp → copy the snippet into your agent’s config. done. 5/ dictate into anything → settings → dictation → set a global hotkey → hold it anywhere on your system, speak, release → transcript pastes into the focused text field slack, email, code, browser — works everywhere. 6/ that’s it. no api keys. no usage caps. no audio leaving your machine. you just replaced two SaaS subscriptions with a 200mb native app. github.com/jamiepine/voic… follow and turn on post notification for more content that helps you maximize the use of AI.

English

80

248

2K

301.8K

Alexander the great. retweetledi

Nav Toor@heynavtoor·23 Nis

10 open-source AI tools that feel illegal to be free. Bookmark this before big tech buries it. 1. Fooocus A Midjourney alternative that runs on your laptop. Three clicks from download to first image. Repo → github.com/lllyasviel/Foo… 2. ComfyUI The image generator professional AI artists actually use. Studios use it for real production work. Repo → github.com/comfyanonymous… 3. Ollama A ChatGPT alternative that runs on your own machine. No internet. No API costs. One command to install. Repo → github.com/ollama/ollama 4. OpenVoice Clones any voice from 10 seconds of audio. Built by MIT and MyShell. MIT license means commercial use is allowed. Repo → github.com/myshell-ai/Ope… 5. Penpot A Figma alternative with real-time collaboration. Runs in your browser. Self-hostable. Repo → github.com/penpot/penpot 6. AppFlowy A Notion alternative where your data stays on your own machine. Local-first. Built in Rust. Repo → github.com/AppFlowy-IO/Ap… 7. n8n A Zapier alternative with 400+ integrations and native AI nodes. Unlimited workflows when you self-host. Repo → github.com/n8n-io/n8n 8. Cal. com A Calendly alternative with more features than the paid version. White-label it for clients. Repo → github.com/calcom/cal.com 9. Supabase A Firebase alternative you actually own. Postgres, auth, storage, realtime, edge functions. All in one. Repo → github.com/supabase/supab… 10. Cline A Cursor alternative that lives inside VS Code. Reads your files, edits your code, ships your features. Repo → github.com/cline/cline Here's the wildest part: Add up what these tools would cost as SaaS subscriptions and you are looking at $300 to $500 every single month. All of it. Free. Forever. The only people who lose when you install these are the companies charging you $20 a month for what an open-source community built for free. Save this post before you forget. 100% free. 100% open source.

English

31

206

1.2K

78.3K

Alexander the great. retweetledi

Sukh Sroay@sukh_saroy·5d

I spent one weekend erasing myself from the internet using claude. 53 data broker profiles. 18 dead accounts. 4 buried search results. all gone. My name, address, and phone number used to show up on google. now they don't. Here's the full playbook. 8 steps. save this.

English

3

8

22

2.8K

Alexander the great. retweetledi

Guri Singh@heygurisingh·5d

ChatGPT just lost its grip. Someone built an AI that runs entirely off a USB stick. No internet. No account. No data leaving the drive. Plug it into any computer on Earth and you have a private AI in your pocket. It's called Portable AI USB. You copy it onto a 16GB flash drive, run one installer, and you're done. From that point on, the entire AI lives on the stick. The model. The chat interface. Every conversation you've ever had with it. Nothing touches the host computer. → Runs 100% offline once set up, no connection ever required again → Pick from 6 models including uncensored ones with zero content filters → Works on Windows, Mac, and Linux from the same drive → Leaves zero trace, no registry keys, no files, no cache on the host PC → All chats and settings stay on the USB, fully portable between machines → Built on Ollama, Llama 3, and AnythingLLM, all open source → Custom model support, paste any HuggingFace GGUF link and it handles the rest Think about what this actually means. ChatGPT logs every prompt you've ever typed. It trains on your data. It can be subpoenaed. It goes down when OpenAI's servers go down. And it costs $20 a month for the good model. This costs the price of a USB drive. One time. Forever. You can use it on a library computer, a hotel business center, a locked-down work laptop, a friend's PC, and walk away leaving absolutely nothing behind. The AI never existed on that machine. No subscription. No login. No telemetry. No cloud. No company reading your conversations. The whole thing is MIT licensed. Three steps to install. The most underrated privacy tool released this year. Your AI should belong to you, not rented from a server farm that reads everything you say.

English

26

133

596

47.2K

Alexander the great. retweetledi

MarketPredator@kasegeno19104·6d

🚨 TRADING TERMS YOU MUST KNOW ✍️ Master the language. Master the trade. ✔️ RISK MANAGEMENT: SL | TP | BE | KZ ✔️ LIQUIDITY: LS (Liquidity Sweep) | BSL | SSL | LC ✔️ MARKET STRUCTURE: BOS | ChoCH | MT | CE ✔️ KEY LEVELS: EQH | EQL | PDH | PDL ✔️ BLOCKS: OB | BB | MB | RB ✔️ LIQUIDITY RANGE: ERL | IRL ✔️ GAPS: FVG | IFVG | VI ✔️ CANDLE STRUCTURE: OLHC | OHLC 🚨 Bookmark this. Study it.

English

2

76

321

14K

Alexander the great. retweetledi

CryptoSoulz@SoulzBTC·5d

How to Trade Bollinger Bands 0:00 - What Are Bollinger Bands? 1:10 - Identifying Volatility 2:39 - Breakouts 4:08 - Reversal Setups 4:58 - Pullback Strategy

English

25

85

537

35.8K

Alexander the great. retweetledi

H.E. Justin Sun 👨‍🚀 🌞@justinsuntron·6d

Introducing B.AI — incubated by @yzilabs. One account, every major model. Claude, GPT, Kimi, DeepSeek — all in one place. No more juggling ten platforms, ten cards, ten passwords. Smart routing sends each prompt to the model that handles it best. Average cost cut in half. Built for crypto-native users: pay in stablecoins, privacy by default. Agent wallet coming soon — let AI place orders, sign, and transact onchain for you. Sign up for free credits. Top up to earn more.

CZ 🔶 BNB@cz_binance

Tried many AI models with OpenClaw, I found Kimi AI to be the most token efficient, good at coding, also the easiest to set up.

English

218

105

580

1.8M

Alexander the great. retweetledi

an0n@an0n_r0·5d

seems to be hot. a 6-year old LPE what was fixed(?) in 2020 by MS is still (again?) working on Win11 (and Server 2025). just tried the freshly weaponized PoC by @ChaoticEclipse0. regular user -> SYSTEM works like a charm on an up-to-date Win11. 🎉 deadeclipse666.blogspot.com/2026/05/minipl…

Nightmare Eclipse@ChaoticEclipse0

It's confirmed, CVE-2020-17103 patch is ineffective and the vulnerability still exists, A weaponized PoC can be found here - deadeclipse666.blogspot.com/2026/05/minipl… Tested against fully patched Windows 11 and Server 2025 machines.

English

2

67

308

35.3K

Alexander the great. retweetledi

Nightmare Eclipse@ChaoticEclipse0·16 May

It's confirmed, CVE-2020-17103 patch is ineffective and the vulnerability still exists, A weaponized PoC can be found here - deadeclipse666.blogspot.com/2026/05/minipl… Tested against fully patched Windows 11 and Server 2025 machines.

English

7

126

480

79.6K

Alexander the great.

Keşfet