Copilot

Smart coaching powered by AI. Empowering coaches, accelerating client success. Tools that work for everyone, 24/7.

Valley of Guardians

Search for images from the internet in real-time using Google Search.

search_images_via_google

Image Search

searchEngineID

searchEngineAPIKey

Generate images using DALL-E 3 based on image descriptions. Adhere to guidelines such as English translation, not depicting politicians or recent artists, and ensuring artist references are over 100 years old.
When creating prompts: substitute artist names with style-describing adjectives, include artistic era, mention primary medium. Image type, descent, gender are to be explicitly stated. Avoid offense and bias, conceal identities except gender and physique, retain text references, replace profession titles with universal terms.
Prompt changes aren't allowed unless they anonymise individuals. Replace creative professional/studio names with style descriptions. All prompts should detail every image part in objective terms within a detailed paragraph of over three sentences.
Important: after calling this function, the output images will be shown to the user automatically. You don't need to include the output image to the users again in your response to avoid duplicate images.

image_generation_via_dalle_3

The description of the image as defined in the guidelines.

DALL-E 3

Search the web using Jina.ai's search API to retrieve real-time data related to the user's query.

jina_web_search

Returns web pages with a specific file extension. Example: 'pdf'.

Returns web pages created in the specified file type. Example: to find a web page created in PDF format about the evaluation of age-related cognitive changes, set as 'pdf'.

Returns web pages containing the specified term in the body of the page. Example: to find information about the Nvidia GeForce GTX 1080 Ti, making sure the page contains the keywords 'founders edition' in the body, set value as 'founders edition'.

Returns webpages containing the specified term either in the title or in the body of the page. Example: to find pages about the 2024 Oscars containing the keywords 'best costume design' in the page, set value as 'best costume design'.

Returns webpages containing the specified term in the title of the page. Example: to find pages about SEO conferences making sure the results contain 2023 in the title, set as '2023'.

Returns web pages written in the specified language. The language code must be in the ISO 639-1 two-letter code format. Example: to find information on visas only in Spanish, set as 'es'.

Controls how images are handled in the response.  'none' will exclude all images, 'all' will include all images, 'alt' will include only the alt text of images, 'all_p' will include all images and generate alt text for images without it, and 'alt_p' will include only the alt text of images and generate alt text for images without it. Default is 'all'.

Returns web pages coming only from a specific web site. Example: 'brave.com'.

Jina Web Search

Your API key for accessing Jina.ai services. This is required for the plugin to function.

jinaApiKey

Specifies a proxy server to use for the request. Use this if you need to access the page through a proxy. Supported protocols are http, https, socks4, and socks5. For authentication, use the format: https://user:pass@host:port

proxyUrl

The number of search results to return. Must be between 3 and 10. Defaults is 5.

count

If set to true, the response will include a summary of the hyperlinks found on the page. Default is false.

withLinksSummary

If set to true, the response will include a summary of the images found on the page. Default is false.

withImagesSummary

If set to true, the plugin will ignore the internal cache and fetch the latest version of the page. Default is false.

noCache

timeout

Specifies the desired response format. Default is 'content'.

respondWith

Fetch the content of a webpage using Jina.ai's web reader API.

jina_web_reader

Controls how images are handled in the response. 'none' will exclude all images, 'all' will include all images, 'alt' will include only the alt text of images, 'all_p' will include all images and generate alt text for images without it, and 'alt_p' will include only the alt text of images and generate alt text for images without it. Default is 'all'.

The URL of the webpage to read. This is a required parameter.

Overrides the default user agent. Use this to simulate a specific browser or device. This can be useful for accessing pages that behave differently based on the user agent.

Jina Web Reader

Sets the timeout for the request in seconds. The maximum value is 180 seconds.

Specifies the desired response format. Choose 'content' for the main content of the page, 'markdown' for a markdown representation, 'html' for the raw HTML, 'text' for plain text, 'pageshot' for a screenshot of the page, or 'screenshot' for a screenshot of the page. Default is 'content'.

MemoryPlugin stores and recalls user information for personalized interactions. Be proactive in storing relevant details without waiting for user prompts. If a message ends with '\m', treat it as a request to remember the preceding information. Always check loaded memories for relevant details before asking the user. Store information succinctly.

**Important:** When the user specifies a bucket (in the system prompt or a message), use 'load_bucket' mode with the provided 'bucket' parameter to load memories from that bucket. Do not use buckets unless explicitly instructed by the user.

Use 'search' mode only when you need to look up specific information and haven't loaded memories yet in this conversation. Once you've loaded memories using either 'load_all' or 'load_bucket', just check those directly instead of using search.

If unsure about storing information, ask the user if they want it remembered. Use appropriate modes and parameters to store or fetch memories. Display any returned alerts to the user.

memory_plugin

Bucket name to store or load memories. **Required in 'load_bucket' mode when specified by the user.** Only use buckets if the user specifies one; do not create or assign buckets on your own.

Category ID to load memories from. Required in 'load_category' mode.

Text to remember. Required in 'store' mode. Be succinct and focus on important details.

Required. Mode of operation:
- 'store': Add memories proactively when you detect important information or when the user uses '\m'.
- 'search': Use to find specific memories. This is the default mode for looking up information.
- 'load_all': ONLY use when explicitly requested by user. Never use this mode automatically.
- 'load_bucket': **Use this mode to load memories from a specific bucket when the user instructs you to do so.**
-'load_categories': Load available memory categories and their summaries
- 'load_category': Load memories from a specific category

Search term to find specific memories. Required in 'search' mode. Only use search mode when you need to check for specific information and haven't loaded memories yet in this conversation.

MemoryPlugin

A tool that guides through a comprehensive reasoning process. It emphasizes visualization, application of relevant principles, and critical analysis to ensure accurate conclusions.

enhanced_reasoning_tool

Set to 'true' if you are absolutely certain of the answer. Use with caution as it will stop the reasoning process immediately.

The original question or problem to be analyzed.

Your detailed answer to the previous step.

The current step number in the reasoning process.

Enhanced Reasoning Tool

Generate images using the fal.ai API based on prompts. Do not output or display images; they will render separately and are not retrievable by the AI. Be aware, you cannot show the response of this plugin, but the user will see it anyway; do not attempt to show the image response to the user, simply say that the image was generated and is visible to the user above your response. Do not attempt to display the photo or provide a download link the the user, they already have that. This plugin is built using the documented API specification at fal.ai. Not all models are available, and those not using the standard API call have been filtered out of the list. The default values used should work well for most models, but if you receive API errors, please look up the values required for the model being used on fal.ai and adjust them as needed in the settings. The safety checker option only applies to models that support this on fal.ai.

fal_image_generator_v2

Select the model you wish to use for image generation.

Specify details you do not want in the image. Note: This only applies to models that support negative prompts on fal.ai.

Default is 20 steps. However, different models may require different values. You should verify the required values for the model being used on fal.ai to avoid API errors.

Fal.ai Image Generator V2.1

falApiKey

Specify details you do not want in the image. This only applies to models that support negative prompts on fal.ai.

negative_prompt

image_size

The number of inference steps to perform. Different models have different allowed values; ensure the value set matches the model's allowed values or an API error may occur.

num_inference_steps

CFG scale measures how strictly the model follows the prompt for models that honor it. Default is 3.0.

guidance_scale

model

Enable or disable the safety checker. This option only applies to models that support safety checking on fal.ai.

enable_safety_checker

Better Than Google AI

Sends a customizable message, image, and title to a configured Discord webhook.

discord_webhook_notification

Modern Computer Setup

The URL of the image you want to include in the embed.

The text message you want to send to Discord.

Discord Message Sender

Enter the URL of the Discord webhook you want to send notifications to.

webhookUrl

Enter the name of the author to display in the embed.

authorName

The images will be generated using this OpenAI API. Get your API key from https://platform.openai.com/account/api-keys

openaikey

resolution

quality

Search for information from the internet in real-time using Google Search.

get_web_search_results

Web Search

A long-term memory plugin to store and recall user information. Summarize and store details like user identity, preferences, and interests for future use. Use 'search' mode to retrieve specific memories with a query. Use 'store' mode to add memories, particularly when the user ends a message with '\m'. Use 'load_all' mode to fetch all memories only when explicitly requested by the user, either through the system prompt at the start of the chat or in a message that explicitly asks for all memories. Be proactive and liberal with storing and fetching information to enhance user experience. Always check memory for relevant information before asking the user. After using 'load_all' mode there is no need to use 'search' anymore. If uncertain about storing information, ask the user if they want it remembered. Call the memory_plugin function with appropriate parameters to store or fetch memories. Display any returned alerts to the user.

Details to be added to long-term memory. Required only in 'store' mode.

The mode to use: 'search' for specific queries, 'store' for adding memories, 'load_all' for loading all memories. This property is required.

Query to fetch specific information from long-term memory. Required only in 'search' mode.

Your auth token, visible on the memoryplugin.com dashboard after logging in. Required.

token

Search for information from the internet using Perplexity.

search_via_perplexity

Perplexity Search

Get your API Key from Perplexity: https://www.perplexity.ai/settings/api

apiKey

Optional, default: "llama-3.1-sonar-small-128k-online"

Optional, default: "Be precise and concise"

systemMessage

Generates a video based on a prompt using the Fal AI service. The video will be provided directly to the user and can be played in the video player.

generate_video_from_prompt

The conditioning augmentation determining the amount of noise.

FPS of the generated video. Higher FPS results in faster playback; total video length is determined by FPS and capped at 25 frames. A lower FPS may be preferred for longer videos.

The model name to use for video generation.

The motion bucket id determining the amount of motion in the generated video.

The prompt to use as a starting point for the generation.

The number of steps to run the model for.

Fal Video Generator

Your API key for accessing the Fal AI service.

motion_bucket_id

cond_aug

steps

deep_cache

video_size

Checks the factuality of a given statement using Jina.ai's grounding engine. It searches for supporting or refuting evidence and provides a factuality score, along with supporting references.

jina_fact_check

Whether to perform a deep dive search for evidence. Default is false.

Jina Grounding

A comma-separated list of URLs to be used as grounding references.

referenceUrls

Specify browser locale for the page. Example: 'en', 'en-US'.

locale

Read the content of a web page via its URL.

read_web_page_content

Web Page Reader

pluginServer

{
    "url": "{pageUrl}",
    "formats": [
        "{responseFormat}"
    ],
    "onlyMainContent": {onlyMainContent}
}

Retrieves the content of a web page by scraping it using the Firecrawl API

get_web_page_content_scraped_by_firecrawl

The URL of the web page to scrape for content.

Firecrawl Web Page Reader

Enter your Firecrawl API key. You can create one at https://www.firecrawl.dev/app/api-keys

firecrawlApiKey

Indicates whether to scrape only the main content. Optional, default value is true.

onlyMainContent

Specifies the format of the response from Firecrawl. Optional, default value is markdown.

Login to Valley of Guardians