🚀 TG-Echo is now open source

A while back I posted about building a Telegram AI that feels more like me: deep personalization, RAG on my own chat history, trying to make an LLM sound genuinely like Bilal.

Update: that part didn't survive contact with reality. The style-RAG kept leaking AI-generated replies back into its own vector store, indexing was too flat to separate contacts or context, and I had hardcoded phrases patching over gaps a real personalization system shouldn't need. Instead of shipping something that fakes "sounding like me," I stripped it back and rebuilt the core agent properly.

What TG-Echo is now:
A 100% local, MTProto-based (GramJS) auto-reply engine for your personal Telegram DMs. No Bot API, no webhooks, no port forwarding, just your own account.

🧠 Core pieces:
- Unified context engine: merges Telegram cloud history with in-memory session state into clean chronological turns for the LLM
- Zero hardcoded responses, zero fake RAG "facts," zero keyword-override shortcuts. Output is genuinely LLM-generated

- Security firewall: allowlist/blocklist + sensitive-keyword gating (money, passwords, private keys) before anything reaches the model
- Human typing simulation + multi-bubble message splitting, so replies don't read like a bot dumping a wall of text
- An AI-leak stripper in post-processing to catch responses that sound too obviously AI-generated
- Pairs with my AI-Gateway project for free multi-provider LLM routing across 9+ providers, so it can run 24/7 at zero API cost

The "make it sound like me" work isn't dead, it's just not something I'm willing to ship half-working. That layer needs a cleaner separation between AI-generated and human-authored data in the vector store, and real per-contact indexing instead of one flat pool. That's next.

For now, the base agent is solid, it's open source, and it's ready for people to build on.

🔗 github.com/bilalshemsu1/TG-Echo
Pairs well with: github.com/bilalshemsu1/ai-gateway

#NodeJS #Telegram #GramJS #MTProto #OpenSource #AI #LLM #AgenticAI #Project

TG-Echo passed the Turing test… then leaked the assignment instructions 😂

If you are Gamer you have to looks this short.

https://www.youtube.com/shorts/WpBkGl-vvg4?feature=share

Exploring Machine Learning with PHP

I've been spending some time exploring machine learning from a PHP perspective.

Usually, when people talk about ML, the first tools that come to mind are Python, scikit-learn, PyTorch, or TensorFlow. But PHP has some interesting options too.

I've been looking into libraries such as:
- PHP-ML for common machine learning algorithms and preprocessing
- Rubix ML for building more complete ML workflows in PHP
- FANN for neural network functionality through PHP bindings

I'm not saying PHP is going to replace Python for machine learning. It isn't.

But I think it's interesting to see how ML capabilities can be integrated directly into PHP applications, especially when you're already building backend systems with Laravel.

For me, the goal isn't to learn every ML library. It's to understand where these tools actually make sense and how they can be used in real applications.

Still experimenting and learning. 🚀

#PHP #Laravel #MachineLearning #PHPML #RubixML #SoftwareDev

Laravel + Stripe + Chapa: A Complete A–Z Payment Integration Guide 💳

I built a subscription payment system on Laravel 13 and documented every step so anyone can rebuild it from zero

What's inside (25 sections):
🔧 Full setup: Laravel → Laravel Cashier → Stripe dashboard → migrations → models → controllers → routes → Blade views

- 💳 Stripe subscriptions with hosted Checkout (test cards included)

- 📡 Webhooks done right — HMAC signing, local testing with Stripe CLI, idempotent event handling

- 📚 13 payment models with copy-paste code: one-time payments, trials, upgrades/downgrades, coupons, invoices, refunds, customer portal, failed-payment dunning, metered billing & more

- 🇪🇹 Full Chapa (Ethiopian gateway) integration — telebirr, CBE Birr, Amole, mPesa; HMAC webhook verification, test credentials, membership model (no recurring billing)

- 🐛 Real errors I hit + fixes (duplicate migrations, currency case, array message crashes, email validation, config path pitfalls)

- ✅ Production deployment checklist & security best practices

Full guide in the attached file. Feedback welcome!

Doc: https://t.me/AfroCoders/1165

#Guide #Tip #Doc #Laravel #Stripe #Chapa #Payments

❗️For developers who need a Visa/Mastercard for developer-tool verification

If you're trying to activate free trials or verify payment methods on some developer/AI tools but don't have an international card, you can check out Grey: https://app.grey.co/

Grey provides virtual cards that can be used for online payments and, depending on the service and card eligibility, payment verification.

Important: Not every service accepts virtual/prepaid cards, and card eligibility depends on your country and Grey account.

Don't use it to bypass a service's payment restrictions or create multiple trial accounts. Use your own verified account and follow the service's terms.

If you've successfully used Grey for a specific developer tool, share your experience with the community so others know what works.

Amazing extension #responsive #extension #tools

#Opportunity_Alerts📣

🚀Calling Young Founders: Join the Global Innovation Challenge 2026🚀

✨Are you 18–30 years old and leading a startup or project that is already creating social or environmental impact? The Social Shifters Global Innovation Challenge 2026 is calling on young impact founders from around the world to apply for grant funding and support to grow their solutions.

What You Gain:
🔹Grant funding of up to $15,000 USD
🔹Free support to strengthen your application
🔹1-to-1 pitch coaching for finalists
🔹Global exposure and connections
🔹Access to funding, fellowships, training, networking and paid opportunities

Who Can Apply?
🔸Founders aged 18–30
🔸Youth-led startups or projects with clear founder decision-making authority
🔸Projects already launched and delivering measurable social or environmental impact
🔸Applicants from any country worldwide
🔸Projects contributing to at least one UN Sustainable Development Goal (SDG)

💡Participation Fee: Free

🔗Apply: https://www.socialshifters.co/global-innovation-challenge/

📝Deadline: August 31, 2026

"If this isn't for you, please share it with others who might be interested."🙏

Follow us👇for more opportunities
@opportunity_alerts

🚨New Model

🥷 New stealth model: Ox Alpha

Ox Alpha is a frontier model built for efficient coding, sustained agentic work, and real-world production use.

- 1M token context window
- Text, image, and video input

🫡 OpenCode.

🤔 Is that my problem or not? It stops in the middle of tasks (Ox Alpha)?

Exploring ZCode a powerful new Agentic Development Environment (ADE) built to bring GLM-5.3 right into real coding workflows.

It integrates long-context planning, tool execution, and workspace state into a single desktop experience so tasks can move from idea to verification seamlessly. Definitely worth checking out if you're experimenting with long-horizon AI coding agents!

https://zcode.z.ai/en

China's 'Bilibili' reportedly paying creators $0.70 per 1k views — quickly rising to challenge RIVAL platform Youtube

Source: stockertim

🤖 What if AI could reply to your Telegram messages like you?

I built TG-Echo, a personal Telegram AI agent that uses your chat history + current context + communication style to generate replies that feel more like the way you actually talk.

Instead of hardcoded responses, it learns from the conversation context and lets the AI decide what to say.

Built with Node.js + GramJS + LLMs. 🚀

This started as an experiment, but it turned into something surprisingly interesting.

🔗 Open source: github.com/bilalshemsu1/TG-Echo

#TGEcho #AI #AIagents #NodeJS #Telegram #LLM #OpenSource #JavaScript #BuildInPublic #SoftwareDevelopment