TOP 6 PODCAST BIAR CEPAT PINTER BAHASA INGGRIS BUAT PEMULA!‼️
1. BBC 6 MINUTE ENGLISH
2. COFFEE BREAK ENGLISH
3. ESPRESSO ENGLISH PODCAST
4. THE ENGLISH WE SPEAK
5. SPEAK ENGLISH NOW
6. ESL POD
@its__Arthur19 Kalo saya pertanyaannya bukan spt itu, tp pertanyaannya jd siapa yang mengira bhw mumi-mumi firaun pd akhirnya akan dimuseumkan shg sesuailah dg ayat Al Quran yg mengabarkan bahwa mayat firaun akan diselamatkan dan akan dijadikan pelajaran seperti yg ada di surat Yunus ayat 92
Your phone charges every night.
Your mind just keeps running.
20 minutes. Eyes closed. Light + sound.
No scrolling. No multitasking. No “I’ll rest later.”
This is Neurovisor Brain Reset.
Watch the video.
Then get yours here:
👉 https://t.co/4H8n3DjfgY
📢 UPDATE SAYEMBARA IJAZAH GIBRAN
⏳ 1 hari lagi!
💰 Total hadiah kini Rp10.279.573.557
📅 9 Agustus – 9 September 2026
📱 WA: +61 434 794 488
Mari kawal terus moralitas dan konstitusi bernegara kita.
Besok kamis kita ajukan Permohonan merebut kembali Marwah dan Wibawa Negara Hukum Republik Indonesia ke hadapan Sembilan Negarawan Hakim Konstitusi.
Semoga Allah SWT meridhoi perjuangan kita.
Terus Berjuang!
Salam Integritas!
Generate endless real-time AI music directly in your browser
No sign-up. Free unlimited generations. Runs locally in your browser with transformers js
Tiny model: ~13M params, ~50MB. Runs in real time on almost any consumer CPU, even mobile.
Try it out
AI agent’lar için açık kaynak Palantir yapmışlar:
Semantica.
Veriyi knowledge graph’e çeviriyor, agent kararlarını kaydediyor ve sonradan “bu kararı neden verdi?” sorusunun izini sürebiliyorsun.
Context Graph + Decision Intelligence + provenance + deterministic reasoning.
Self-hosted, MIT lisanslı.
https://t.co/w2IC2mt9yc
Yapay zeka hakkında güncel kalmak için
https://t.co/igLD9mmWgw
THIS CLAUDE + OBSIDIAN SECOND BRAIN VAULT WAS SOLD FOR $37,000
now it's open sourced
someone wired Claude straight into his Obsidian vault and built a second brain that runs the chaos in his head for him
every stray thought, voice note and half finished idea gets dumped into one place
Claude reads the entire vault and quietly links the notes that were always meant to sit together
it tags everything, draws the map and surfaces the idea you forgot you had at the exact moment you need it
you ask it a question and it answers from years of your own thinking, in your own words
the messy pile you keep promising to clean up becomes a brain that files itself while you sleep
the people building this now carry a memory that compounds every single day while everyone else opens a blank page and starts over
dropping a full pipeline in the next post as always
see u there
Si usas un agente de IA open source como Hermes, seguramente lo llevas gestionando desde terminal.
Chats, credenciales, modelos, memoria, skills, tareas programadas, todo mezclado en una consola de texto.
Funciona. Pero es un infierno de organizar cuando empiezas a escalarlo.
acaba de aparecer algo que soluciona justo eso
Se llama Hermes Web UI Desktop.
Es una app gratis y de código abierto que convierte tu agente Hermes, que corre solo por CLI, en un espacio de trabajo visual completo.
Qué te da:
Chat en tiempo real con streaming, como hablar con Claude o ChatGPT pero con tu propio agente corriendo en tu máquina.
Gestión de sesiones: crear, renombrar, buscar y cambiar entre conversaciones sin perder el hilo.
Un solo panel para modelos, credenciales, memoria, skills, logs y tareas programadas.
Conecta con 8 plataformas distintas (Telegram, Discord, Slack...) desde el mismo sitio.
Terminal web integrada por si necesitas bajar a bajo nivel.
lo más importante compadre
Todo corre en tu hardware. Nada sale de tu máquina salvo lo que tú decidas.
No dependes de una empresa que un día decide cerrar el grifo o subir el precio.
Instalación con un solo comando:
npm i -g hermes-web-ui && hermes-web-ui start
y ya lo tienes corriendo en local
si tienes un agente open source y sigues gestionándolo a pelo desde terminal, esto te va a ahorrar horas cada semana
guarda este post
China open-sourced a fully local memory system that gives any AI agent human-like long-term recall.
No cloud. No API bills. No flat vector piles.
- 61.38% fewer tokens per session
- 76% persona accuracy (up from 48%)
- 51.52% higher task success rate
- works with any agent
100% Open Source.
Kemarin sempet rame soal ILovePDF yang katanya gratis, tapi ngambil cuan dengan jual data penggunanya.
Bener gak sih? Aku penasaran dan akhirnya coba riset. Temuanku malah bikin lebih kaget lagi:
Di balik jasa yang semua orang kira cuma "gratisan", iLovePDF ternyata perusahaan dengan omzet PULUHAN JUTA EURO tiap tahun. Bahkan di 2024 aja tembus di atas €20 juta, dan itu tanpa investor, tanpa iklan gede.
Gimana bisa web gratis kayak gini untung segede itu? Dari nyolong data?
A thread 🧵 by Narasi Visual
Screen Studio charges $29/month. Someone cloned it and put it on GitHub for free.
It's called OpenScreen. 39,000 stars.
> Auto-zoom on clicks, motion blur, cursor animations, webcam overlay, timeline editing, export in any format
> A dev then forked it and built Recordly — full cursor animation pipeline, zoom-reactive webcam scaling, native recording on macOS and Windows
> Screen Studio is Mac-only. Both of these aren't.
Free. No watermark. No account. MIT license. Works on Windows, macOS, and Linux.
LOOM AND SCREEN STUDIO JUST GOT OPEN SOURCED INTO IRRELEVANCE.
Github: https://t.co/3LyIkcaJbX
You installed Claude Code and stopped there.
Here are 22 skills (actually) worth adding:
If you're just getting started, check out these guides:
Every one is a GitHub repo. Grouped by what they do:
BUILD
superpowers — plans and debugs before it writes
Install → https://t.co/DI0sN54NJp (259k★)
gstack — 23 skills in one setup
Install → https://t.co/xSn6Dq7uBs (124k★)
caveman — no-fluff answers, no padding
Install → https://t.co/abkH9Ixey6 (92k★)
ponytail — says nothing, writes one line
Install → https://t.co/9v5XTv9X2q (88k★)
codex — runs Codex inside Claude Code
Install → https://t.co/yTC67RXu2I (30k★)
i-have-adhd — stops it burying the answer
Install → https://t.co/AAgVmfgBT1 (9k★)
DESIGN
ui-ux-pro-max — palettes and fonts that work
Install → https://t.co/p0HdcjBls9 (109k★)
taste-skill — makes a page look expensive
Install → https://t.co/ZKrL39o58P (66k★)
impeccable — the polish pass on any front end
Install → https://t.co/ANBmLLj4EA (49k★)
hyperframes — turns a web page into a video
Install → https://t.co/YkKNc7A4jE (37k★)
emil — beautiful interface animations
Install → https://t.co/HlvmsPCGTr (20k★)
gsap — smooth web animations
Install → https://t.co/GQuHRTIDG4 (12k★)
RESEARCH
skill-creator — build your own skills
Install → https://t.co/WKUIBRJGNa (163k★)
graphify — turns notes into a map
Install → https://t.co/UfizweeU9c (94k★)
last30days — what the internet said this month
Install → https://t.co/iBjCBqwlWr (53k★)
agent-browser — lets Claude use any website
Install → https://t.co/395O5Z9Bxb (39k★)
find-skills — finds any skill for you
Install → https://t.co/6dojcpb06j (27k★)
claude-hud — shows what Claude is doing live
Install → https://t.co/V9M8I0LCri (27k★)
MARKETING
remotion — build full videos in React
Install → https://t.co/1SsttgHY0H (54k★)
marketingskills — 40 marketing skills in one pack
Install → https://t.co/BuH343McGO (41k★)
humanizer — strips the AI tells from your writing
Install → https://t.co/kllApuqKKd (31k★)
social-media-skills — my own content pack, free
Install → https://t.co/eSwCrzsTmD (mine)
Most install with npx skills add [repo].
I don't reach for all 22 daily.
superpowers, caveman and last30days get the most use.
Repost ♻️ to help someone in your network.
P.S. Which one are you installing first?
Here are 10 GitHub repos that quietly print money while you sleep.
1. Cal. com
Open-source Calendly. Fork it, white-label it, sell to dentists and lawyers for $200/month. The founders hit $5M ARR in 3 years doing exactly this.
Repo → https://t.co/Qqe8Schsgt
2. Plausible Analytics
Privacy-first Google Analytics. Self-host it, resell to agencies for $50/month per client. Two founders bootstrapped this to 7 figures.
Repo → https://t.co/HKpN07mUZ5
3. Ghost
Open-source Substack with 100% margin. 1,000 readers at $5/month equals $60,000 a year. Forever.
Repo → https://t.co/qMl2Ig2h03
4. n8n
Open-source Zapier. Sell automation services for $500-$2,000 per setup. n8n raised $14M because the agency model behind it works.
Repo → https://t.co/pmMLX1OLtH
5. Supabase
Free Firebase replacement. Build a SaaS in a weekend, charge $29-$99/month. They raised $116M for a reason.
Repo → https://t.co/7KwbFsR2Qo
6. Medusa
Open-source Shopify. Take 5% on every sale forever. Zero rev share to Shopify.
Repo → https://t.co/aiN386blug
7. AppFlowy
Open-source Notion. Sell self-hosted to enterprises worried about data privacy. They raised $30M because this market is massive.
Repo → https://t.co/qcl2tERBCL
8. Coolify
Open-source Vercel and Heroku. Charge developers $20/month to manage their deployments. Replace their $200 Vercel bill.
Repo → https://t.co/kFprAirARL
9. Listmonk
Open-source Mailchimp. Send unlimited emails for the cost of an AWS bill. Resell to agencies at 10x markup.
Repo → https://t.co/QgcYOiFwiX
10. Penpot
Open-source Figma. Sell self-hosted design tools to agencies who refuse to upload client files to the cloud.
Repo → https://t.co/HsOBYxuyFL
The difference between developers who build features and developers who build businesses is one decision.
Pick one of these. Fork it this weekend. Ship it next week.
The founders behind these repos already proved the model.
Save this. Share it with the developer in your life who deserves to break free.
100% free. 100% open source.
🚨 Hugging Face just open sourced a complete real-time voice AI pipeline.
Speak. It listens. It thinks. It talks back. End to end. Running on your GPU. Free.
No OpenAI Realtime API fees. No ElevenLabs per-character billing. No Google Cloud per-minute pricing. Just a GPU and an internet connection.
It's called speech-to-speech. Built and maintained by Hugging Face. And it does something no other open-source project has assembled cleanly until now.
Here's what makes real-time voice AI hard.
Every voice AI pipeline has four stages: speech recognition (you speak → text), language model (text → response text), text-to-speech (response text → audio), and audio output. Each stage adds latency. Chain them together naively and you get a system that feels slow — the pause between you finishing a sentence and the AI starting to respond breaks the conversational illusion.
speech-to-speech is built around minimizing that latency at every stage simultaneously.
Here's the full stack it ships with:
Speech Recognition (STR):
→ Whisper (local) — OpenAI's transcription model, runs fully offline
→ Faster-Whisper — 4x faster inference with same accuracy
→ Distil-Whisper — smallest and fastest, lowest latency
→ Paraformer — Chinese language specialist
Language Model (LLM):
→ Any Transformers-compatible model — Llama, Mistral, Qwen, anything
→ Any OpenAI-compatible API endpoint — swap in Claude, GPT, Gemini
→ MLX-optimized models for Apple Silicon — runs efficiently on Mac
Text-to-Speech (TTS):
→ Parler-TTS — controllable voice with description-based prompting
→ MeloTTS — multilingual, fast
→ ChatTTS — natural conversational prosody
→ HF Inference Endpoints — offload TTS to Hugging Face servers when needed
Mix and match. Any STR with any LLM with any TTS. Test combinations. Find the lowest latency stack for your hardware.
Here's the wildest part.
It ships with a Language Model Speech (LMS) mode — an experimental architecture where the LLM generates audio tokens directly instead of text tokens. No separate TTS stage. The model thinks in audio.
This is the architecture that makes GPT-4o Advanced Voice feel natural — the model is generating speech as a native output, not converting text to speech after the fact. HF's open-source version lets you experiment with this architecture on your own hardware.
And there's a VAD (Voice Activity Detection) system that detects when you stop speaking in real time — no fixed silence threshold, no manual push-to-talk. The pipeline responds the moment you finish a sentence.
Here's the cost comparison that makes this worth caring about.
OpenAI Realtime API: $0.06 per minute input, $0.24 per minute output. A one-hour conversation: $18. A developer building a voice AI application with 1,000 daily users: $18,000/day in API costs.
speech-to-speech on a single A100: $0. Your only cost is the GPU rental.
For production voice AI at any scale, the economics are not close.
One command to install.
9.6K GitHub stars. 944 forks. Apache 2.0 License.
100% Open Source. From Hugging Face.
GitHub link in the comments 👇