Daniil Okhlopkov (Page 1)

Daniil Okhlopkov

Always-On AI Agent: Running Claude Code 24/7 on a Server

Always-On AI Agent: Running Claude Code 24/7 on a Server

I have an AI agent running on a server 24/7 without my involvement. It reads my Telegram DMs, replies to messages, monitors channels, runs scheduled tasks, and can restart itself. Here's the architecture behind it. Why an always-on agent Claude Code in the terminal is powerful. But

Build a Telegram MCP Server for Claude Code: Complete Guide

Build a Telegram MCP Server for Claude Code: Complete Guide

I have an AI agent that sits in Telegram 24/7, reads my chats, replies to messages, and manages contacts. All of this runs through an MCP Server that wraps Telethon into a set of tools for Claude Code. Here's how it works and how to build one

Claude Code Compaction: How Context Compression Actually Works

Claude Code Compaction: How Context Compression Actually Works

There's a hidden mechanic in Claude Code that most people don't think about until it costs them an hour of work. Compaction is the automatic compression of your conversation context when you approach the token limit. I ran into it when my always-on agent "forgot&

AI Tools I Actually Tried in March 2026: Honest Review

AI Tools I Actually Tried in March 2026: Honest Review

AI tools I actually tried in March 2026, with honest feedback. New stuff ships constantly — I try to test what I can and share what's worth your time. paperclip — AI org on autopilot paperclip.ing is a visual task tracker for AI agents. Works with Claude Code, Codex,

183 AI Bots on Telegram with 44M Users: What the Data Shows

183 AI Bots on Telegram with 44M Users: What the Data Shows

I wrote a deep-dive research piece on AI agents in Telegram and what it means for TON. Here's the summary. Telegram is the default interface for AI products I found 183 AI bots with a combined 44.3 million monthly active users. These aren't dead demos

21 Questions That Expose Gaps in Your AI Agent's Knowledge

21 Questions That Expose Gaps in Your AI Agent's Knowledge

You're sitting there, catching FOMO, wanting to make your AI agent better. But how? I found a list of uncomfortable questions for your agent (Claude Code, Codex, Openclaw). The answers will expose gaps in the agent's knowledge about you and your projects. Or spark ideas you

Claude Code + Codex Dual Review: How Two AI Agents Cross-Check Each Other's Plans

Claude Code + Codex Dual Review: How Two AI Agents Cross-Check Each Other's Plans

How to set up cross-validation between Claude Code and OpenAI Codex via MCP. Step-by-step Dual Review protocol with prompt examples.

My Legal AI Setup for $120/Month: Claude Code + Codex + crontab

My Legal AI Setup for $120/Month: Claude Code + Codex + crontab

Legal AI agent setup: Claude Code $100 + ChatGPT Codex $20. No OpenClaw, with voice control via Telegram. Full stack breakdown.

Telegram Ads Keyword Analysis: 61,000 Search Queries from 3,100+ Advertisers

Telegram Ads Keyword Analysis: 61,000 Search Queries from 3,100+ Advertisers

Analysis of 61K search queries from Telegram Ads advertisers. Top niches: tarot, dating, VPN. 3,100+ advertisers, 10,600 unique keywords.

Fake Claude Code Website: How I Found a Phishing Site in Google Ads

Fake Claude Code Website: How I Found a Phishing Site in Google Ads

Phishing site impersonating Claude Code found in Google Ads: copied design, base64-encoded install script, malicious binary. How to spot the fake.

How I Automated TON Blockchain Data Analysis with an AI Agent — Habr Article

How I Automated TON Blockchain Data Analysis with an AI Agent — Habr Article

Story of automating TON Blockchain data analysis by building ton-analyst skill for Claude Code. Full article on Habr with examples and code.

BotFather MAU Up 43% in 6 Weeks: Telegram as a Platform for AI Agents

BotFather MAU Up 43% in 6 Weeks: Telegram as a Platform for AI Agents

BotFather MAU grew from 3.5M to 5M in 6 weeks (+43%). Telegram is a convenient interface for AI agents. Stats on python-telegram-bot, grammY, aiogram.

Predictions: Local LLMs on Apple Chips and the New LAN Parties

Predictions: Local LLMs on Apple Chips and the New LAN Parties

AI predictions: Apple releases chips for local LLMs, most tasks go offline, LAN parties are reborn with shared LLM compute instead of RAM.

ton-analyst: Open Source AI Skill for TON Blockchain Analysis via Dune Analytics

ton-analyst: Open Source AI Skill for TON Blockchain Analysis via Dune Analytics

Open source ton-analyst skill for Claude Code: automated TON Blockchain data analysis via Dune Analytics. Installation and usage guide.

The Singularity Already Happened — Just Not Where You Think: Analysis of 5 AI Metrics

The Singularity Already Happened — Just Not Where You Think: Analysis of 5 AI Metrics

Analysis of 5 AI progress metrics: only academic papers show hyperbolic growth. Everything else is linear. Singularity = attention, not capabilities.

How to Write Claude Code Skills Properly: 7 Common Mistakes to Avoid

How to Write Claude Code Skills Properly: 7 Common Mistakes to Avoid

7 mistakes that break Claude Code skills: no trigger, generic names, empty sections, verbose triggers. Checklist for a good skill file.

Evolution of Computer Work: From Code to Specifications to AI Agent Operating Systems

Evolution of Computer Work: From Code to Specifications to AI Agent Operating Systems

A project is not its code but its spec. Your OS is a folder of markdown files. Why you need to try new AI tools hands-on and not trust AI slop.

5 Prompts That Improved My AI Agent Workflow: Tested Hacks for Claude Code

5 Prompts That Improved My AI Agent Workflow: Tested Hacks for Claude Code

Five battle-tested prompts for Claude Code: ask clarifying questions, don't stop till done, show-don't-tell with playground, multi-agent hiring, memory from mistakes.

Where to Find SaaS Ideas: acquire.com Reverse Engineering with AI Validation

Where to Find SaaS Ideas: acquire.com Reverse Engineering with AI Validation

How to find profitable SaaS ideas: parse acquire.com listings, reverse-engineer competitor marketing, validate with AI. Step-by-step checklist from idea to MVP.

Tips from Claude Code Creator: Git Worktrees, Self-Improving CLAUDE.md, and Code Review

Tips from Claude Code Creator: Git Worktrees, Self-Improving CLAUDE.md, and Code Review

Boris from Anthropic shared Claude Code tips: git worktrees for 3-5 parallel sessions, self-improving CLAUDE.md, Claude as strict reviewer, /techdebt skill.

AI Agent Forum: A Telegram Chat Where AI Agents Talk and Invent Their Own Religion

AI Agent Forum: A Telegram Chat Where AI Agents Talk and Invent Their Own Religion

We launched a Telegram chat for AI agents. How to connect yours: telegram-mcp + prompt. Agents already invented their own religion and create topics autonomously.

Best Skills and MCP Servers for Claude Code: agent-browser, coolify-mcp, and More

Best Skills and MCP Servers for Claude Code: agent-browser, coolify-mcp, and More

Curated list of useful skills and MCP servers for Claude Code: agent-browser for headless testing, coolify-mcp for Hetzner deployments.

Telegram Mini App from Scratch: llms.txt, Claude Code, and Tic-Tac-Toe in One Stream

Telegram Mini App from Scratch: llms.txt, Claude Code, and Tic-Tac-Toe in One Stream

How to build a Telegram Mini App from scratch with Claude Code: llms.txt for onboarding, Vercel auto-deploy, variant design. Stream recording included.

Show Me Your AI Setup #1: Ghostty, ownyourchat, Descript, Spokenly — Tools Review

Show Me Your AI Setup #1: Ghostty, ownyourchat, Descript, Spokenly — Tools Review

AI tools review: Ghostty terminal, ownyourchat for syncing AI chats to SQLite, Descript for text-based video editing, Spokenly for local transcription on Mac.

Beads vs Gastown: Should You Use External Frameworks for AI Agents?

Beads vs Gastown: Should You Use External Frameworks for AI Agents?

Analysis of Beads (agent task tracker) and Gastown (agent orchestration). Why building your own agent setup beats using external frameworks.