“persistent”的搜索结果

在NanoClaw交互环境中管理以Markdown保存的会话，支持恢复、分支、跨会话搜索、历史压缩和导出，并协助切换模型及加载技能。

• 恢复已保存的会话
• 在高风险更改前创建分支
• 跨会话搜索并压缩历史记录

按项目保存Claude Code中的工作进度、决策和后续步骤，在其他会话中读取摘要，接着上次中断的位置继续工作，也可在会话开始时自动加载。

• 结束会话前保存进度和后续步骤
• 接着上次会话继续工作
• 查看多个项目的状态

指导您在Lambda Labs启动GPU服务器，进行机器学习训练与推理，并介绍SSH连接、持久化存储、Python API操作及多GPU分布式训练。

• 为长时间训练准备专用GPU环境
• 使用多个GPU微调大语言模型
• 保留数据集与训练检查点

使用云端GPU运行机器学习训练、推理和数据处理，并将模型发布为API。通过Python定义运行环境，还可配置自动扩缩容、存储、并行处理和定时任务。

• 无需管理GPU服务器即可训练模型
• 将模型发布为自动扩缩容的API
• 并行处理大量数据

分析 Git 变更历史中的开发成果、工作时段、测试代码比例和频繁变更的文件，汇总个人与团队的改进方向，保存指标并比较不同时期的趋势。

• 汇总每周开发成果
• 回顾个人贡献与改进方向
• 查看测试比例和频繁变更的文件

Search persistent Claude-Mem records on cmem.ai for context from earlier sessions across agents. Narrow keyword searches to relevant observations, then explain past work, decisions, and dates in plain language.

中文简介正在准备中。当前显示英语简介。

• Recalling what happened in the previous session
• Finding the reasoning behind a project decision
• Retrieving past records about a file or error

Work on advanced RuView sensing with signals from multiple WiFi nodes. Explore position estimation, three-dimensional occupancy reconstruction, changes in movement patterns over time, and defenses against suspicious signals, with guidance on implementation modules and validation.

中文简介正在准备中。当前显示英语简介。

• Combining WiFi observations from multiple nodes
• Reconstructing occupied space with RF tomography
• Studying long-term changes in movement patterns

Schedule workers to run checks at fixed times while a Claude Code session stays open. Set up recurring security scans, test coverage analysis, or documentation tasks, and find or cancel scheduled jobs.

中文简介正在准备中。当前显示英语简介。

• Scheduling security scans every 15 minutes
• Checking test coverage at regular intervals
• Running API documentation tasks every two hours

Build agents that record task outcomes and use past experience to choose future approaches. Implement pattern matching, strategy comparisons, persistent learning records, and metrics for checking how recommendations and results change over time.

中文简介正在准备中。当前显示英语简介。

• Build an agent that learns from task outcomes
• Compare approaches to code review or bug fixing
• Find learned patterns relevant to the current situation

Build AI agents with Cline SDK using guidance on choosing APIs, adding custom tools, saving sessions, and handling live events. References also cover model providers, scheduled runs, multi-agent coordination, and production deployment.

中文简介正在准备中。当前显示英语简介。

• Build an AI agent with custom tools
• Choose an API for persistent sessions
• Configure model providers and live event handling

Automate website navigation, form filling, screenshots, data extraction, and web app testing while keeping page state between scripts. Works with a fresh Chromium session or an existing Chrome session through an extension.

中文简介正在准备中。当前显示英语简介。

• Automating navigation and form entry
• Saving screenshots of web pages
• Extracting website data

Guide browser work inside the Claude desktop app, including reading page text, opening tabs, and handling existing sign-ins. Covers site approvals, browser visibility, and connection problems when a cloud session uses the desktop browser.

中文简介正在准备中。当前显示英语简介。

• Read web page text in the Claude desktop app
• Open a page in an additional browser tab
• Guide a user through sign-in or verification

Inspect Muse Code’s saved settings and defaults, then make targeted changes when explicitly requested. Explain reasoning and display options while distinguishing persistent configuration from the settings currently active in a running session.

中文简介正在准备中。当前显示英语简介。

• Check saved settings and defaults
• Change the saved reasoning effort
• Adjust reasoning summaries and output detail

Build Python workloads on Modal for cloud execution, including GPU model training and inference, web APIs, scheduled jobs, and parallel batch processing. Configure container environments, persistent storage, and automatic scaling through the Modal SDK.

中文简介正在准备中。当前显示英语简介。

• Serving an AI model through a web API
• Running model training or fine-tuning on cloud GPUs
• Processing independent batch inputs in parallel

Guides agents in choosing Cherry Studio tools for research, document conversion, memory, notifications, and other tasks. It explains when to use app tools or local runtimes, with checks for availability, configuration, and approval.

中文简介正在准备中。当前显示英语简介。

• Choose the right Cherry Studio tool for a task
• Read or convert local Office and PDF files
• Set up scheduled tasks and notifications

Build Java applications that exchange live audio with AI assistants using Azure AI VoiceLive. The skill covers authentication, streaming sessions, speech detection, voice selection, transcription, and handling responses over WebSocket, a persistent two-way connection.

中文简介正在准备中。当前显示英语简介。

• Implementing a real-time voice assistant in Java
• Configuring speech detection and interruptions
• Adding transcription and noise reduction

Build and manage Linux containers on Apple silicon Macs with Apple's container CLI. Run each container in its own lightweight virtual machine, and get guidance on images, networking, storage, and translating familiar Docker workflows to this tool.

中文简介正在准备中。当前显示英语简介。

• Building container images from a Dockerfile
• Running Linux containers on an Apple silicon Mac
• Managing persistent volumes and container networks

Automate page interactions and screenshots with agent-browser running in AWS Bedrock AgentCore cloud browsers. Use standard browser commands, preserve login state across sessions with persistent profiles, and watch active sessions through an AWS Console link.

中文简介正在准备中。当前显示英语简介。

• Run browser automation on AWS
• Reuse login state across browser sessions
• Watch a cloud browser session live

Add browser automation to Vercel apps by running agent-browser and headless Chrome in temporary, isolated virtual machines. Capture screenshots, inspect page structure, and complete multi-step forms while preserving browser state between commands.

中文简介正在准备中。当前显示英语简介。

• Add website screenshot capture to a Vercel app
• Fill and submit forms across multiple browser commands
• Run recurring browser tasks with Vercel Cron Jobs

Move slow Python operations into background jobs so requests can return promptly. Use task queues and workers, the processes that execute queued work, with retry rules, duplicate handling, time limits, and persistent job status.

中文简介正在准备中。当前显示英语简介。

• Send emails and notifications in the background
• Generate reports and data exports asynchronously
• Process uploads and media conversions

Retrieve earlier decisions, preferences, and saved resources from OpenViking across sessions. Store durable information, import documents or repositories, and manage deletion, with guidance on how project memory is shared between directories and repository clones.

中文简介正在准备中。当前显示英语简介。

• Recall decisions from earlier sessions
• Save preferences and lasting decisions
• Import files, URLs, or Git repositories for later use

Build and modify Java plugins for Minecraft servers running Paper, Spigot, or Bukkit. The skill covers commands, event handling, minigames, and saved player progress, with checks for configuration, task cleanup, and server API compatibility.

中文简介正在准备中。当前显示英语简介。

• Add server commands and event listeners
• Implement team battles and arena minigames
• Build quests, perks, and saved player progression

Turn documents into a growing Markdown wiki and a knowledge graph, a map of entities and their relationships. Preserve source text, update linked pages as new material arrives, and answer questions with supporting evidence.

中文简介正在准备中。当前显示英语简介。

• Build a reusable knowledge base from documents
• Trace relationships between terms and topics
• Answer questions with source evidence

Build systems that use Pinecone to find documents for AI answers or retain agent memories across sessions. Guides index setup, data loading, meaning-based and keyword search, memory separation, and end-to-end checks.

中文简介正在准备中。当前显示英语简介。

• Build an AI assistant that answers from documents
• Keep agent facts and decisions across sessions
• Combine meaning-based search with exact terminology