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.
Summary
The video segment introduces the 'Compact' command as a tool for managing the context window within a single AI agent session. Rather than switching to a new session and risking data loss, users can run the Compact command to compress the entire previous conversation into a condensed form, effectively reducing token usage while remaining in the same session.
The speaker explains that Compact can be triggered manually by the user or configured to run automatically — for example, when the context window reaches 50-60% capacity. This automatic configuration can be set up through a bot (referred to as 'ibot'). Alternatively, users can copy and paste the Compact command directly into their agent interface.
In addition to Compact, the speaker mentions complementary commands: a complete history clearing or a 'New + checkpoint' command that starts a completely fresh session with a full reset to zero tokens. These are presented as more drastic alternatives when compression alone is insufficient.
Finally, the speaker recommends enabling automatic notifications so the agent can proactively alert the user when it's time to run the Compact command or move to a new chat session. To use the Compact command, the user simply sends the corresponding prompt to the agent.
Key Insights
- The speaker explains that the Compact command compresses the entire previous conversation into a single session summary, allowing users to reduce context window size without losing data by switching sessions.
- The speaker states that Compact can be configured to trigger automatically when the context window reaches 50-60% capacity, managed via a bot called 'ibot'.
- The speaker describes that alongside Compact, users can run a complete history clearing or a 'New + checkpoint' command, which performs a full reset to zero tokens by starting a new session.
- The speaker recommends setting up automatic notifications so the agent itself can alert the user when it is time to run the Compact command or transition to a new chat session.
- The speaker notes that to implement the Compact command, the user simply needs to send the corresponding prompt directly to the agent.
Topics
Transcript
[0:00] The fifth team is the Kopaact team. Compact allows us to reduce the context window by compressing the entire previous conversation into one session. That is, we execute the compact command within one session. For example, we don’t want to switch, or we’re afraid that when we switch to a new session, or the agent switches to a new session, we’ll lose some data. We want to stay within this session and interact with the agent. Therefore, we run the compact command or set it to run automatically, for example, when a [0:31] certain limit is reached. For example, the context window has grown to 50-60%, the compact command is automatically enabled. This is also configured by our ibot.…
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.
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.
Экономия токенов и контекстного окна: настройка памяти нейросети Newchat без потери данных
The transcript explains the Newchat command, which opens a new session while pulling data from previous sessions. It works in conjunction with the checkpoint command, which can be configured to trigger automatically when Newchat is launched. The speaker recommends implementing these commands through skills rather than MD slots for a more professional workflow.