The Manifest.
More posts from The Manifest, paginated so the main blog stays lighter and faster to load.
How to Fix LangGraph RecursionLimit Error (Solved)
Is your LangGraph agent crashing with a 'RecursionLimit' error? Learn how to fix infinite agent loops and properly increase recursion limits in 2026.
MCP vs Function Calling: What's the Actual Difference?
MCP and function calling both let AI models use tools. But they work very differently. Here's the comparison.
Spotting Deepfake Video in Real-Time: A 2026 Guide for Remote Workers
Scammers are using real-time AI to impersonate IT staff and managers on Zoom and Teams. Learn how to use AI verification overlays and simple behavioral 'glitch tests' to detect a digital mask.
Real-Time AI Phishing Detection: Stop Clicking Bad Links in 2026
Phishing is no longer about bad grammar. Scammers now use AI to clone entire websites. Learn how to use AI security agents to detect 'Intent Divergence' and block malicious links instantly.
AI-Driven Financial Security: Stop Scammers from Emptying Your Wallet
Banks are too slow to stop modern scams. Learn how to use AI-driven transaction monitoring agents to detect fraudulent merchants and high-risk wallets in real-time before you hit 'Send'.
Stopping AI DM Scams on LinkedIn, Twitter, and WhatsApp
Social media is a minefield of AI-driven scams. Learn how to use sentiment-analysis AI to pre-screen your DMs and detect 'Scam Vibes' from fake recruiters and crypto bots in 2026.
The 2026 Guide to Killing Voice-Clones and Deepfake Calls
Scammers can clone your voice with just 30 seconds of audio. Learn how to use AI call screening and challenge-response protocols to protect your family from voice-cloning scams.
LangGraph vs. Semantic Kernel: The 2026 Enterprise Showdown
A deep dive comparing LangChain's LangGraph and Microsoft's Semantic Kernel. Find out which framework is best for your enterprise AI architecture.
The Burner Email Survival Guide for 2026: 12+ Tools to Kill Spam and Protect Your Privacy
Your main inbox is a data goldmine for AI trackers. Learn how to use 10-minute inboxes, alias services, and anonymous forwarding to vanish from the 2026 spam cycle.
The Gmail Secret: How to Generate Unlimited Email Addresses from One Account
You don't have one Gmail address; you have infinite. Learn how to use Plus and Dot addressing to track data leaks, loop free trials, and kill spam in 2026.
An Intro to HTML <address> Tag
The semantic <strong>HTML <code><address></code> element</strong> indicates that the enclosed HTML provides contact information for a person or people or an organization of a document or an article representing document or an article.
How to Use Gmail SMTP Server for Sending Email
Gmail SMTP settings, ports, and App Password setup — configure any app, script, or email client to send mail through Gmail in 2026.
Agent Skills with Google Gemini: Function Calling Guide
Complete guide to Gemini function calling — define tools, handle function_call responses, return results, and compare syntax with Claude and OpenAI. Node.js.
Vercel AI SDK Tools: One API for Claude and OpenAI Skills
Vercel AI SDK's unified tool interface works with Claude, OpenAI, and Gemini. Write your skill once and switch AI providers without rewriting the agent loop.
Reduce Disk Writes on Debian and Ubuntu Desktop
Five tweaks that cut unnecessary disk writes on Debian and Ubuntu — noatime, volatile journald, tmpfs, swappiness, and zram. Safe on SSDs and HDDs.
Build a GitHub Issue Creator Skill for Your AI Agent
Create a production-ready agent skill that creates GitHub issues from natural language, with label assignment, duplicate detection, and dry-run mode.
Chaining Agent Skills: Research, Summarize, and Save
Build a skill chain where an agent searches the web, summarizes findings, and saves results to a file — all from a single prompt. Full Node.js walkthrough.
File System Skills: Let Your Agent Read and Write Files
Build safe file system skills that let an agent read, write, and list files — with path sandboxing, size limits, and guardrails to prevent runaway writes.
Agent Skills with Memory: Persisting State Between Chats
Teach your agent to remember across conversations. Build read/write memory skills backed by a JSON file, then upgrade to SQLite — full Node.js code.
Testing and Debugging Agent Skills Before You Deploy
Skills that work alone fail differently inside an agent loop. Unit test your tools, mock AI calls, and debug the full tool_use cycle in Node.js.
Domain Expertise
Browse by topic.
Get new posts without checking the archive.
Stay close to the latest deep-dives, references, and practical engineering notes from MeshWorld without having to scan the archive manually.
More posts, still searchable and still useful, without forcing the main blog page to carry the full post list at once.
Faster main archive, lighter page weight, and a cleaner path into older tutorials, installs, and references.