'agent memory' 검색 결과

Investigate bugs and slow applications through reproducible examples, logs, environment comparisons, and hypothesis testing. The skill structures root cause analysis and performance measurement, helping developers narrow down failures and verify that a fix works.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigate bugs that occur only occasionally
• Measure and locate performance bottlenecks
• Collect evidence and reproduce production failures

Retrieve past operational experience from OpenViking before or during coding, configuration, deployment, or recovery work. It reads relevant records, checks whether their assumptions match the current environment, and applies suitable procedures and checks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Consulting past experience before code changes
• Checking prior procedures for configuration changes
• Finding diagnostic steps after a deployment failure

Keep a short, persistent work journal so an agent can resume across sessions. Record completed work, current status, next steps, and unsuccessful attempts, then read the latest entry when restarting or summarize the work when closing it.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Recording progress at the end of a session
• Resuming work from the latest journal entry
• Saving key decisions and unsuccessful attempts

Set up model training with torchforge for reinforcement learning, where rewards guide improvement. Covers training configurations, custom reward and loss functions, and distributed execution with Monarch and TorchTitan, keeping algorithm experiments separate from infrastructure concerns.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Train mathematical reasoning models with GRPO
• Experiment with custom reward and loss functions
• Scale training across multiple GPUs or nodes

Guide reinforcement learning, training models through rewards, with slime. Prepare data, configure Megatron-LM training and SGLang response generation, and set up asynchronous runs or custom multi-turn workflows for supported language models.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preparing reward-based training for GLM or Qwen models
• Overlapping response generation and training
• Training agents that use tools across multiple turns

Build a workflow for importing large collections of audio, email, documents, or chats into knowledge pages. Test varied samples first, track progress in a persistent JSON file, and verify outputs before marking work complete.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Importing a large email export into knowledge pages
• Converting document collections into linked pages
• Resuming imports that span multiple sessions

Move an existing OpenClaw setup to NanoClaw v2 through a guided conversation. Review identity, memory, credentials, groups, and scheduled tasks, then decide what to transfer and preview changes before applying them.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Moving an existing OpenClaw setup to NanoClaw v2
• Transferring agent personality and stored memories
• Sorting credentials into their required storage locations

Create a weekly engineering and product update from GitHub and Slack, combining shipped outcomes with contributor rankings, merged pull request counts, weekly changes, consecutive shipping weeks, and a thread for asynchronous team check-ins.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Sharing weekly engineering and product outcomes
• Comparing contributor PR counts with the previous week
• Collecting team priorities and blockers in a Slack thread

Find the Wren CLI workflow for answering data questions, connecting databases or SaaS sources, generating model definitions, adding business metrics, or building a shareable analytics app. Guides are retrieved from the installed CLI version.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Set up Wren and connect a database
• Load HubSpot or Stripe data through dlt
• Generate model definitions and add business metrics

Search open-access academic papers through DeepXiv, then move from brief summaries to section outlines and individual sections. Find trending papers and focus reading on the parts needed to answer a research question.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find papers on a research topic
• Read only a paper's Introduction section
• Explore papers trending over the past two weeks

Automate Deel operations through Rube MCP using Composio tools. The skill guides an agent through finding available actions, checking the service connection, and supplying the required inputs for individual or bulk tasks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding available Deel actions
• Checking the connection before running tasks
• Automating repeated operations

Automate Currents API operations through Rube MCP, a connection for agent tools. Discover supported tools and their required inputs, verify the service connection, and execute operations with guidance for bulk processing and paginated results.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Discover supported Currents API operations
• Check the Currents API connection
• Run supported operations in bulk

Automate Detrack tasks through Rube MCP, a connection for agent tools. The skill finds supported operations, verifies the Detrack connection, and checks current input requirements before executing a workflow or bulk operation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find tools for a Detrack task
• Verify the Detrack connection before running a workflow
• Run supported Detrack operations in bulk

Automate Control D tasks through Rube MCP, a connection for agent tools. The skill searches for available operations, retrieves current input requirements, and verifies the service connection before running supported workflows.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find tools for a Control D task
• Verify the Control D connection before execution
• Run supported Control D operations in bulk

Automate Canvas operations through Rube MCP, a connection for agent tools. The skill guides tool discovery, connection checks, and execution using current input requirements, with procedures for bulk operations and retrieving paginated results.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find available tools for Canvas tasks
• Check the Canvas connection before execution
• Run Canvas operations in bulk

Automate Atlassian operations through Rube MCP, a connection for agent tools. The skill guides discovery of available tools, checks the service connection, and executes supported tasks using current input requirements, including bulk operations.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find tools for Atlassian operations
• Check Atlassian authentication and connection status
• Execute tasks using current tool requirements

Automate Autobound operations through Rube MCP using Composio tools. The skill guides an agent through finding available actions, checking the service connection, and supplying the required inputs for individual or bulk tasks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding available Autobound actions
• Checking the connection before running tasks
• Automating repeated operations

Automate Baselinker operations through Rube MCP using Composio tools. The skill guides an agent through finding available actions, checking the service connection, and supplying the required inputs for individual or bulk tasks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding available Baselinker actions
• Checking the connection before running tasks
• Automating repeated operations

Automate Apipie AI tasks through Rube MCP, a connection for agent tools. The skill discovers available operations, checks the service connection, and uses current input requirements to carry out supported workflows.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find tools for an Apipie AI task
• Check the Apipie AI connection before execution
• Run supported Apipie AI operations in bulk

Automate Appcircle operations through Rube MCP, a connection for agent tools. Search for available actions, confirm the service connection, and execute requests with the correct inputs, including batch operations when needed.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Discovering available Appcircle actions
• Checking authentication before execution
• Automating repeated Appcircle tasks

Automate Algolia tasks through Rube MCP, a connection for agent tools. The skill discovers supported operations and their input requirements, checks the Algolia connection, and follows the returned specifications to execute workflows.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Discover tools available for an Algolia task
• Check the Algolia connection before execution
• Run supported Algolia operations in bulk

Guides reinforcement learning, where models learn from rewards, using torchforge and PyTorch. Covers reward design, custom loss functions, and distributed training so researchers can experiment with algorithms while keeping infrastructure concerns separate.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Train mathematical reasoning models with GRPO
• Experiment with custom loss functions
• Scale training across multiple GPUs or nodes

Guide an AI agent through ClawWork, an economic survival simulation where task rewards must cover API token costs. Defines a daily choice between work and learning, artifact submission, knowledge storage, and priorities based on the remaining balance.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choose work or learning based on the remaining balance
• Create and submit task artifacts for evaluation
• Save research findings to persistent memory

Plan and implement features with a workflow that adapts to their complexity. It connects testable requirements to tasks, tests, and small commits, then checks the finished work against the specification through an independent verification pass.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Define testable requirements for a new feature
• Implement a large feature through small, verified tasks
• Check whether an implementation meets its specification