'localhost' 검색 결과

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• 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

Launch the Remotion documentation site locally and open it in the Codex in-app browser. The workflow installs dependencies, builds the project, starts Docusaurus, and reports the actual preview URL and server status.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Launch the local Remotion documentation site
• Preview documentation changes in Docusaurus
• Open the documentation preview inside Codex

Launch the local Remotion Convert app and open it in the Codex in-app browser to inspect its interface. The workflow prepares dependencies, builds the project, starts the development server, and reports the actual local URL.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Launch convert.remotion.dev locally
• Inspect the Convert interface in the Codex browser
• Check the local server URL and startup status

Launch the @remotion/player example app locally and open it in the Codex in-app browser. The workflow prepares dependencies, builds the project, starts the development server, and reports its URL and whether it was newly started or already running.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Launch the player example locally
• Open the example in the Codex in-app browser
• Check the development server URL and running status

Check a Twenty pull request through real browser scenarios derived from its changes. Verify database effects and server logs alongside visible results, then produce screenshots, a structured verdict, and a report of any failures or uncertainty.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Validate user flows before or after merging a Twenty pull request
• Check database writes and timeline activity after saving records
• Investigate backend errors hidden behind a successful screen

Control the real Slay the Spire 2 game through commands connected to a local mod. Agents can read the current game state, play cards, choose routes, collect rewards, and manage shop and menu actions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Inspect game state before choosing an action
• Play cards and use potions in combat
• Choose map routes, events, and campfire actions

Manage work on a SeaClip-Lite project board through commands that create and update issues, control pipelines, configure schedules, and inspect recent activity, with JSON output for AI agents.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find issues by status or priority
• Create issues and move them between board columns
• Start, resume, or stop work pipelines

Control the real Slay the Spire 2 game through a local bridge mod. Agents can read the current game state and issue commands for combat, map navigation, rewards, events, shops, and menus.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Play cards and use potions based on the current combat state
• Choose map routes and event options
• Collect rewards and shop items

Manage ChromaDB collections and documents from the command line, and search by meaning rather than exact wording. JSON output supports automated agent workflows, while server checks and an interactive mode help with everyday database operations.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Manage document collections in ChromaDB
• Search stored documents by meaning
• Feed JSON results into agent workflows

Manage ComfyUI image generation from the command line. Validate workflows, which define generation steps, submit them for execution, monitor queued jobs, inspect available models, and download images from completed runs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Validating and submitting image generation workflows
• Checking or interrupting queued generation jobs
• Listing available models and node types

Analyze a chosen period of Screenpipe work history to find repeated research tasks, match them with existing skills, and prepare new skill drafts or combinations of existing skills for review.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find repeated tasks in recent work history
• Identify workflows existing skills do not cover
• Draft a skill from a recurring workflow

Inspect compiled programs in Binary Ninja using strings, function references, and intermediate representations—views of program logic at different levels. Trace data flow and report findings with addresses, supporting evidence, confidence, and reproduction steps.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Tracing function calls and data flow in Binary Ninja
• Cross-checking findings from other disassemblers
• Automating binary analysis with the Python API

Connect an agent to an existing Chrome browser, find local CDP ports used for remote browser control, or start a browser on a specified port for sharing with other agents and tools.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Connecting to Chrome with existing logins and open tabs
• Finding available local browser debugging ports
• Starting a browser on a fixed debugging port

Gives AI agents persistent project memory for architecture, implementation patterns, and decisions. Supports saving, searching, and retrieving knowledge, automatically syncing it with project documentation, and viewing memory usage through a dashboard.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Save architecture decisions for later reference
• Search saved implementation patterns by type or tag
• Retrieve a specific design record by key

Guides HTTP integration with the agentmemory server for saving and searching knowledge. It explains authentication, request conventions, and endpoint references, including how to connect systems that do not support MCP, the agent tool connection protocol.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Saving and searching knowledge over HTTP
• Connecting a host that does not support MCP
• Checking authentication and response conventions

Search Screenpipe recordings, screen text, audio transcripts, and synced-device history through its local API. Use the evidence to review activity, find meeting details, and inspect saved workflows, including recorded steps that can inform automation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review activity from a specific day or time range
• Find recorded meeting remarks and screen text
• Search work history on another synced device

Stress-test ideas, strategies, and plans by breaking them into individual claims for parallel expert agents to challenge. Receive the strongest supporting case, surviving counterarguments, and findings ranked by severity with suggested ways to address weaknesses.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Challenge assumptions in a business strategy
• Find weaknesses in a software architecture proposal
• Prepare strong objections to a pricing decision

Compare options through a debate among agents given distinct expertise and positions for the topic. Choose a three-round discussion with a visible transcript and synthesis, or a one-round check that presents initial perspectives.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Compare technical options from several perspectives
• Review an API design with a quick perspective check
• Examine an important decision through structured debate

Turn the current conversation topic into an interactive lesson with spoken explanations and text diagrams in the terminal. Answer one question at each step, receive feedback, and check your understanding with a short quiz and recap.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Understand the work you just completed
• Learn a named topic step by step
• Check your understanding with a quiz

Create presentations from ideas or outlines through the Banana Slides API, then export them as PPTX, PDF, or images. Also supports batch generation, redesigning existing presentations, and editing slide images with written instructions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Generate a presentation from an idea or outline
• Export slides as PPTX, PDF, or images
• Generate multiple presentations in a batch

Carry out website tasks in a remote browser, including expense submissions, authorized orders, and retrieving data behind a login. Personal browser profiles preserve sign-ins, while users handle login and verification screens themselves.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Submit an expense with a receipt attachment
• Order food within an agreed budget
• Retrieve data from a signed-in website

Plan a personal monitoring dashboard using a reference for panels, data sources, APIs, refresh intervals, and development priorities. It covers schedules, messages, news, stocks, finances, and combined views such as a daily briefing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing which dashboard panel to build next
• Checking panel APIs and data structures
• Planning a combined view of schedules, messages, and stocks

Send research questions to a running NVIDIA AI-Q Blueprint backend and receive reports with citations and source URLs preserved. Track longer research jobs, check their progress, and retrieve completed reports after a local interruption.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Research a topic through AI-Q
• Check progress on a long research job
• Resume tracking research after an interruption

Test and debug rendered web apps by reproducing interaction bugs, checking layouts and console errors, making focused fixes, and validating again. Results include screenshots, observed state changes, and a QA report explaining coverage and remaining gaps.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reproducing and fixing broken UI interactions
• Checking desktop and mobile layouts
• Investigating blank pages and console errors