Gemini CLI против Claude Code: почему я перехожу и как всё настроить самому
The video walks through setting up Gemini CLI, covering tool integrations like Google Workspace and Firecrawl, and explaining how to configure agents for automated task planning. The presenter compares Gemini CLI with Claude Code and explains their reasons for switching. Key advice focuses on customizing tool connections to individual needs rather than copying the presenter's setup.
Summary
The transcript covers a step-by-step walkthrough of configuring Gemini CLI, beginning at step eight which focuses on integrating external tools. The presenter discusses connecting tools such as Google Workspace, Firecrawl (referred to as 'Firecoll' or 'Firefox' in translation), and other utilities that allow the AI agent to interact with services like Google Drive and YouTube.
Step nine is introduced as a task planning configuration step, designed to allow the agent to autonomously wake up and perform tasks without the user needing to manually instruct it each time. The presenter emphasizes that this step is particularly powerful for automation workflows.
A recurring theme throughout the segment is the presenter's strong advice against blindly copying their tool configuration. Instead, viewers are encouraged to connect only the tools they personally use — for example, the presenter mentions using N8N and Firecrawl in their own agents, but stresses that other users will have different workflows and different tool needs. The presenter also mentions having separate dedicated videos on Firecrawl for those who want to learn more about that specific tool.
Key Insights
- The presenter argues that step nine — task planning configuration — is the most powerful step, as it allows the agent to autonomously wake up and execute tasks without manual prompting each time.
- The presenter explicitly warns viewers not to copy their tool configuration, stating that doing so leads to confusion, citing examples of people messaging them privately about how to connect Firecrawl after blindly copying the setup.
- The presenter recommends enabling Gemini CLI integration with Google Workspace so the agent can access Google Drive documents, YouTube, and other connected Google tools.
- The presenter states they personally use N8N and Firecrawl in their own agents, using these as examples of why tool selection should reflect individual workflow needs rather than a universal template.
- The presenter notes they have multiple separate dedicated videos specifically about Firecrawl, suggesting it is a significant tool in their workflow that warrants deeper standalone coverage.
Topics
Transcript
[0:00] The eighth step is more about working with tools, that is, so that it can work with Google Workspace Firewall search. For example, I love Firecoll, I have a lot of separate videos on Firec. So, here is information on how to work with additional tools accordingly. Since I will be deleting this and the agent, I do n’t need these tools now. Here you can add any additional tools you would like to use using the GPT chat. For [0:31] example, Google Workspace. Be sure to enable CL in Gemini so that it can work with Google Drive documents, YouTube, and all the tools available to it . I'll skip this step now and go straight to step…
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.