Rz Codes 💻

🔥 20 AI Tools Every Researcher & Student Needs A power list for research, writing, and content creation — bookmark this. 🎙️ Speech & Audio 1.Otter.ai — Speech to text 2. PlayHT — AI voices 3. Podcastle.ai — Podcast editing 🔍 Research & Literature 4. Elicit.com — AI research 5. Consensus.app — Scientific evidence 6. Researchrabbit.ai — Literature mapping 7. Scite.ai — Citation analysis 8. Connectedpapers.com — Visual discovery 9. Perplexity.ai — Source-backed search 10. Scholarcy.com — Paper summarization 11. Zotero.org — Reference management ✍️ Writing & Docs 12. Writefull.com — Academic writing 13. Overleaf.com — LaTeX collaboration 🎨 Visual & Media 14. Gitmind.com — Mind mapping 15. Decktopus.com — AI slides 16. Picwish.com — Photo editing 17. Tableau.com — Data visualization 18. Lightpdf.com — PDF creation 🎬 Video 19. Reccloud.com — Video generation 20. Kapwing.com — Video editing Save this list — you’ll need it eventually. 👋 Follow me on for more: 🐦 Twitter/X 💻 GitHub 🔗LinkedIn 📺 YouTube ✍️ Dev.to 🌐 Blog

🍎 Run Multiple Agentic AI 100% Locally on Your Mac — No Cloud, No API Keys — Completely free Apple’s WWDC26 session just dropped the playbook for running full agentic coding workflows entirely on Apple Silicon with zero cost, and it’s wild how little is needed to get there. The 4-layer local stack: 🔹 MLX — Apple’s open-source array framework, handles Metal acceleration & memory 🔹 MLX-LM — loads, runs, quantizes & fine-tunes models from HuggingFace 🔹 MLX-LM Server — OpenAI-compatible HTTP server with structured tool calling 🔹 Your agent — Xcode, OpenCode, or any framework that speaks the chat completions protocol Why it matters: ✅ Zero cloud cost, zero API keys, code never leaves your machine ✅ M5’s Neural Accelerators make matrix multiplication 4x faster, directly speeding up prompt processing for agents chewing through tool output ✅ Continuous batching lets multiple subagents run concurrently without queueing ✅ Distributed inference over Thunderbolt RDMA spreads massive models (even 1.6T-parameter ones) across multiple Macs — up to 3x faster with 4 nodes 3 steps to get running: pip install mlx-lm mlx_lm.server --model <tool-calling-model> # point your agent's base URL at localhost The live demos were the real kicker — an agent built a SwiftUI iPad drawing app from a blank Xcode project in ~2 minutes, then fixed bugs directly inside Xcode’s new Intelligence tab, all powered by a local MLX server. 🔗 Watch the session: developer.apple.com/videos/play/wwdc2026/232 🔗 MLX: github.com/ml-explore/mlx 🔗 MLX-LM: github.com/ml-explore/mlx-lm 🔗 OpenCode: opencode.ai 🔗 Companion session (distributed inference): developer.apple.com/videos/play/wwdc2026/233 👨‍💻 Follow Rabra (rzcodes) for more dev content: 🌐 rz-codes.com 💻 GitHub: github.com/rabira-hierpa 🐦 Twitter/X: twitter.com/rzcodes 💼 LinkedIn: linkedin.com/in/rabira 📺 YouTube: youtube.com/@rzcodes ✍️ Dev.to: dev.to/rabra_hierpa 📝 Blog: blog.rz-codes.com

🧠 Claude Code: From Vibe Coding to Agentic Engineering Found a goldmine repo for anyone using Claude Code seriously — not toy prompts, but actual production workflows. What’s inside: 🔹 Subagents, Commands & Skills — the building blocks for custom Claude workflows, with real implementation examples 🔹 Orchestration patterns — Command → Agent → Skill architecture, demoed with a working weather-orchestrator 🔹 Hooks, MCP servers, Memory & Settings — properly documented, not just “trust me bro” tips 🔹 Dev workflow comparisons — Superpowers, Spec Kit, BMAD-METHOD, and more, all benchmarked side by side 🔹 Hot/beta features — Auto Mode, Ultraplan, Agent Teams, Git Worktrees, Voice Dictation The repo follows one core philosophy: Research → Plan → Execute → Review → Ship If you’re building anything beyond quick scripts with Claude Code, this is worth bookmarking. 🔗 https://github.com/shanraisshan/claude-code-best-practice 👋 Follow me for more GIS, web mapping & full-stack content: 🐦 Twitter/X 💻 GitHub 🔗 LinkedIn 📺 YouTube ✍️ Dev.to 🌐 Blog

https://github.com/gboeing/osmnx 🗺️ OSMnx: Street Networks Meet Python If you do anything with GIS, urban analysis, or routing — this Python package by Geoff Boeing is essential, not optional. What it does: 🔹 Download street networks (walking, driving, biking) from OpenStreetMap in one line of code 🔹 Model and analyze urban amenities, POIs, building footprints, and transit stops 🔹 Pull elevation data, street orientations, speed/travel times 🔹 Built directly on NetworkX for graph-based spatial analysis Why it matters for your stack: ✅ 5.7k+ stars, actively maintained, backed by peer-reviewed research (published in Geographical Analysis, 2025) ✅ Pairs perfectly with PostGIS/QGIS workflows for anyone doing transit accessibility or routing projects ✅ Killer for quick city-scale prototypes before you scale into ArcGIS or full PostGIS pipelines import osmnx as ox G = ox.graph_from_place("Addis Ababa, Ethiopia", network_type="drive") That’s it. That’s a full street network, ready to analyze. 🔗 github.com/gboeing/osmnx 📚 Docs: osmnx.readthedocs.io 👋 Follow me for more GIS, web mapping & full-stack content: 🐦 Twitter/X 💻 GitHub 🔗 LinkedIn 📺 YouTube ✍️ Dev.to 🌐 Blog

To Watch WC2026 Match Live: Step 1 connect to VPN with country Brazil (i.e. Proton VPN) Step 2 Search for Caze TV (https://www.youtube.com/@CazeTV) Youtube Channel Step 3 open the live match video from the channel or use this app https://sportzx.cc/download-sportzx-tv-d/ to watch on mobile app and cast it on TV

🚨 Just discovered something wild — axios on npm was just compromised. If you’re a JS/TS developer, stop what you’re doing and read this. 🔓 The lead axios maintainer’s npm account got hijacked. The attacker published two poisoned versions — axios@1.14.1 and axios@0.30.4 — both carrying a Remote Access Trojan (RAT) targeting macOS, Windows, and Linux. 📦 axios has ~100 million weekly downloads. This is one of the most impactful npm supply chain attacks ever recorded. 🪤 How it worked: The attacker slipped in a fake dependency called plain-crypto-js@4.2.1 via a postinstall hook. It phones home to a C2 server and drops a RAT on your machine — then self-destructs to hide the evidence. Checking your node_modules won’t help — you need to check your logs. ✅ Quick checks: # Check if you installed the bad versions npm list axios | grep -E "1\.14\.1|0\.30\.4" # Check for the dropper directory ls node_modules/plain-crypto-js 2>/dev/null && echo "POTENTIALLY AFFECTED" 🛠️ Fix immediately: npm install axios@1.14.0 # for 1.x npm install axios@0.30.3 # for 0.x 🔑 If affected — rotate everything: npm tokens, AWS keys, SSH keys, .env secrets, CI/CD secrets. All of it. 🌐 npm has already pulled the malicious versions, but if you installed them before the takedown — assume compromise. Stay safe out there 🙏 Source Akido Turn this news to something I discovered to post it as a telegram post use emojis #npm #security #javascript #typescript #supplychain #devops #infosec​​​​​​​​​​​​​​​​

🚀 Introducing Dataset.ET The future of AI should speak Ethiopian languages. Today we are launching Dataset.ET — an open community initiative to build the largest dataset for Ethiopian languages. Why this matters: Most AI systems today barely understand Amharic, Afaan Oromo, Tigrinya, Somali, and many other Ethiopian languages. Without datasets, AI will ignore our languages. Dataset.ET is changing that. What we are building: • Speech datasets • Text datasets • Community-validated language corpora • Open infrastructure for Ethiopian AI How you can help: 1️⃣ Record sentences using our Telegram bot 2️⃣ Validate recordings from other contributors 3️⃣ Help expand datasets for Ethiopian languages No technical skills needed — just your voice and your language. 🤖 Start contributing: https://t.me/dataset_et_bot 🌍 Learn more: https://dataset.et 💬 Join the community: https://t.me/dataset_et Together we can teach AI to understand Ethiopia. 📢 Community leaders & channel admins:

If you run a Telegram group or community and believe Ethiopian languages should be part of the future of AI, we would really appreciate it if you could share this post with your community. Your support can help thousands of people contribute their language and voice to this initiative. Thank you!

Try public APIs for free https://github.com/public-apis/public-apis

Prompt for ChatGPT

Creat a caricature of me and my job based on everything you know about me

What are your thoughts on this ?

GitHub Store Open source  Play Store for GitHub releases that lets you install apps directly from GitHub repositories • GitHub • F-Droid #Resource @HanixJourney