AI агент в Telegram на ChatGPT — голос, файлы, код, картинки (Codex Claw в Telegram)
The speaker explains their Telegram-based AI bot system that uses existing subscriptions from services like Claude and ChatGPT. They emphasize cost efficiency and clarify that these aren't open-source bots but subscription-based services accessed through Telegram.
Summary
The speaker discusses their AI bot system called 'Codex' or 'Codex Claw' that operates within Telegram. The main advantage they highlight is the ability to leverage existing subscriptions from cloud services like Claude and ChatGPT, rather than paying separately for bot functionality. They explain that while deploying traditional bots might cost around $20, their system allows users to operate multiple bots for a month using minimal subscriptions from these AI services. The speaker mentions they personally use minimum subscriptions and find them more than adequate for running multiple bots simultaneously. Each bot runs on the user's server and can be delegated different tasks. The speaker expresses frustration at having to repeatedly clarify a common misconception - that people mistakenly think these are open-source bots when they are actually subscription-based services from Claude, Codex, or ChatGPT that are accessed through Telegram rather than through traditional terminals. They emphasize this Telegram-based interaction as the key differentiator from other bot implementations.
About this episode
AI агент в Telegram на ChatGPT — голос, файлы, код, картинки (Codex Claw в Telegram) Codex Claw в Telegram: исправляем «бот молчит», включаем typing и тестируем ответы В этой серии видео я покажу, как собирать полноценных AI агентов в Telegram без сложных платформ и дорогих API. Мы вместе строим реальных рабочих ботов на базе ChatGPT Codex и Claude, которые принимают голосовые, работают с файлами и выполняют задачи прямо в мессенджере. Всё что нужно — минимальная подписка и желание автоматизировать свою работу. #CodexClaw #CodexCLI #ClaudeClaw #OpenClaw #ClaudeCode
Key Insights
- The speaker argues that using existing AI service subscriptions through Telegram bots is more cost-effective than traditional bot deployment, requiring only minimal subscriptions versus $20+ deployment costs
- The speaker claims that many people misunderstand their system, incorrectly assuming the bots are open-source when they actually rely on official subscriptions from Claude, Codex, or ChatGPT
- The speaker asserts that the main differentiator of their system is enabling interaction with AI services through Telegram rather than through traditional terminal interfaces
Topics
Transcript
codex or codex claw as we call it here means what are their advantages of the same cloud claw bot what is the main advantage is that we can use subscriptions from services for example from the cloud service for working with the cloud claw and subscription chat gpt when working with the codex, that is, we use the same subscriptions for interaction with these bots that work with us telegram, for example, when building the same there is electric bill of a bot, you spend only there on hisigma deployment about $ 20 and here for a whole month you can use these bots for a minimum subscription, I am still sitting at minimum subscriptions from the cloud from…
Full transcript available for MurmurCast members
Sign Up to AccessMore from Игорь Зуевич
Сравнение Claude Code, Gemini и Codex — тесты на контент, анализ и изображения
The speaker is comparing AI coding assistants — Claude Code, Gemini, and Codex — by testing their ability to create image-generation agents. Each tool is being evaluated on how well it writes prompts and structures sub-agents for text-to-image and image-to-image tasks.
Экономия токенов и контекстного окна: настройка памяти нейросети – Compact сжатие контекстного окна
The transcript explains the 'Compact' command in AI agent sessions, which compresses the entire conversation history to reduce context window usage without switching sessions. It also covers related commands for full history clearing and automatic triggers for compact execution. The speaker recommends configuring automatic notifications or auto-execution when the context window reaches a certain threshold.
HR-агент на Claude Code: создаёт других сотрудников сам по запросу
The video demonstrates setting up a Telegram HR bot using Claude Code, walking through the process of creating a bot via BotFather, obtaining a Telegram user ID, and letting the code automatically generate the HR agent. The presenter shows how the system initializes itself by installing dependencies and launching the bot with minimal manual configuration.
Живые скиллы для Claude Code, Gemini и Codex | Как настроить super skills для ИИ агентов
The video explains how to create 'living' or 'super' skills for AI agents like Claude Code, Gemini, and Codex that self-update based on user feedback. The presenter demonstrates how these skills collect feedback after each task, store it in log files, and periodically incorporate that feedback into the skill's core instructions. This approach reduces token consumption and ensures skills continuously improve over time.
Планировщик для ИИ агента: 50 идей и готовые файлы для Claude, Codex и Gemini
The speaker describes their use of a scheduling/routing tool called Routins, which they compare to N8N, to automate daily delivery of curated YouTube videos on topics like Gemini and Claude. The system runs autonomously, collecting videos and generating concise summaries of their content without manual intervention.