Настройка Gemini CLI: агент с многоуровневой памятью и планировщиком задач
The video covers setting up a Gemini CLI agent with multilevel memory and a task scheduler, specifically demonstrating the integration of Telegram with Gemini. The presenter walks through configuring a Telegram bridge by providing API tokens and bot credentials to the agent interactively.
Summary
The transcript captures a practical demonstration of configuring a Gemini CLI agent to interface with Telegram. The presenter describes a workflow where configuration files are shared with the agent, which then reads them and requests necessary credentials. The setup involves a 'Telegram Bridge MD' file that contains instructions for how the bot should be configured.
The presenter explains two approaches for providing API tokens to the agent: either embedding them directly in the prompt, or allowing the agent to ask for them interactively when needed. The second approach is preferred, as it avoids exposing sensitive API tokens in the chat or prompt history.
A key detail discussed is that the Gemini API key is not needed in this setup because the agent is running on a subscription basis rather than via a direct API call. The presenter clarifies this to the agent and proceeds to send only the Telegram Bot Token and Chat ID. The segment ends mid-process, suggesting the configuration is ongoing.
Key Insights
- The presenter describes two methods for supplying API tokens to the agent: embedding them directly in the prompt or letting the agent request them interactively, with the latter preferred to avoid exposing sensitive credentials.
- The presenter notes that the initial setup of folders and configuration took the agent approximately seven minutes before the Telegram bridge file was introduced.
- The agent initially failed to locate the Telegram Bridge MD file on its own and had to be guided, highlighting a limitation in autonomous file discovery.
- The presenter clarifies to the agent that the Gemini API key is unnecessary in this context because the agent is operating under a subscription model rather than a direct API integration.
- The Telegram Bridge MD file serves as the primary instruction document, specifying that the agent must request the Telegram Bot Token, Chat ID, and Gemini API credentials from the user.
Topics
Transcript
[0:00] Fine. So, he set everything up, turned everything on. We saw, yes, with you several folders, it took him about seven minutes. So, I throw him the next file in the same way. Or you can not send it to him, but just copy this entire file, and he himself, accordingly, will see it all. Here we are directly building a bridge between Telegram and Gemini. The only thing is, here, uh, there is all the information about how he should set up the bot. And here there is information that he should request from us the same [0:32] AP key and ID identifier. And there are several options here. First, we write to him directly in the prompt…
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.