Downloads:
579
Downloads of v 2.1.1:
18
Last Update:
14 Apr 2025
Package Maintainer(s):
Software Author(s):
- Nicolas Bonamy
Tags:
witsy ai byok llm ollama- Software Specific:
- Software Site
- Software Source
- Software License
- Software Docs
- Software Issues
- Package Specific:
- Package Source
- Package outdated?
- Package broken?
- Contact Maintainers
- Contact Site Admins
- Software Vendor?
- Report Abuse
- Download
Witsy is a BYOK (Bring Your Own Keys) AI application
This is not the latest version of Witsy is a BYOK (Bring Your Own Keys) AI application available.
- 1
- 2
- 3
2.1.1 | Updated: 14 Apr 2025
- Software Specific:
- Software Site
- Software Source
- Software License
- Software Docs
- Software Issues
- Package Specific:
- Package Source
- Package outdated?
- Package broken?
- Contact Maintainers
- Contact Site Admins
- Software Vendor?
- Report Abuse
- Download
Downloads:
579
Downloads of v 2.1.1:
18
Maintainer(s):
Software Author(s):
- Nicolas Bonamy
Witsy is a BYOK (Bring Your Own Keys) AI application 2.1.1
This is not the latest version of Witsy is a BYOK (Bring Your Own Keys) AI application available.
Legal Disclaimer: Neither this package nor Chocolatey Software, Inc. are affiliated with or endorsed by Nicolas Bonamy. The inclusion of Nicolas Bonamy trademark(s), if any, upon this webpage is solely to identify Nicolas Bonamy goods or services and not for commercial purposes.
- 1
- 2
- 3
This Package Contains an Exempted Check
Not All Tests Have Passed
Deployment Method: Individual Install, Upgrade, & Uninstall
To install Witsy is a BYOK (Bring Your Own Keys) AI application, run the following command from the command line or from PowerShell:
To upgrade Witsy is a BYOK (Bring Your Own Keys) AI application, run the following command from the command line or from PowerShell:
To uninstall Witsy is a BYOK (Bring Your Own Keys) AI application, run the following command from the command line or from PowerShell:
Deployment Method:
This applies to both open source and commercial editions of Chocolatey.
1. Enter Your Internal Repository Url
(this should look similar to https://community.chocolatey.org/api/v2/)
2. Setup Your Environment
1. Ensure you are set for organizational deployment
Please see the organizational deployment guide
2. Get the package into your environment
Option 1: Cached Package (Unreliable, Requires Internet - Same As Community)-
Open Source or Commercial:
- Proxy Repository - Create a proxy nuget repository on Nexus, Artifactory Pro, or a proxy Chocolatey repository on ProGet. Point your upstream to https://community.chocolatey.org/api/v2/. Packages cache on first access automatically. Make sure your choco clients are using your proxy repository as a source and NOT the default community repository. See source command for more information.
- You can also just download the package and push it to a repository Download
-
Open Source
-
Download the package:
Download - Follow manual internalization instructions
-
-
Package Internalizer (C4B)
-
Run: (additional options)
choco download witsy --internalize --version=2.1.1 --source=https://community.chocolatey.org/api/v2/
-
For package and dependencies run:
choco push --source="'INTERNAL REPO URL'"
- Automate package internalization
-
Run: (additional options)
3. Copy Your Script
choco upgrade witsy -y --source="'INTERNAL REPO URL'" --version="'2.1.1'" [other options]
See options you can pass to upgrade.
See best practices for scripting.
Add this to a PowerShell script or use a Batch script with tools and in places where you are calling directly to Chocolatey. If you are integrating, keep in mind enhanced exit codes.
If you do use a PowerShell script, use the following to ensure bad exit codes are shown as failures:
choco upgrade witsy -y --source="'INTERNAL REPO URL'" --version="'2.1.1'"
$exitCode = $LASTEXITCODE
Write-Verbose "Exit code was $exitCode"
$validExitCodes = @(0, 1605, 1614, 1641, 3010)
if ($validExitCodes -contains $exitCode) {
Exit 0
}
Exit $exitCode
- name: Install witsy
win_chocolatey:
name: witsy
version: '2.1.1'
source: INTERNAL REPO URL
state: present
See docs at https://docs.ansible.com/ansible/latest/modules/win_chocolatey_module.html.
chocolatey_package 'witsy' do
action :install
source 'INTERNAL REPO URL'
version '2.1.1'
end
See docs at https://docs.chef.io/resource_chocolatey_package.html.
cChocoPackageInstaller witsy
{
Name = "witsy"
Version = "2.1.1"
Source = "INTERNAL REPO URL"
}
Requires cChoco DSC Resource. See docs at https://github.com/chocolatey/cChoco.
package { 'witsy':
ensure => '2.1.1',
provider => 'chocolatey',
source => 'INTERNAL REPO URL',
}
Requires Puppet Chocolatey Provider module. See docs at https://forge.puppet.com/puppetlabs/chocolatey.
4. If applicable - Chocolatey configuration/installation
See infrastructure management matrix for Chocolatey configuration elements and examples.
There are versions of this package awaiting moderation . See the Version History section below.
This package is exempt from moderation. While it is likely safe for you, there is more risk involved.
Witsy AI Chocolatey Package
What is Witsy?
Witsy is a BYOK (Bring Your Own Keys) AI application: it means you need to have API keys for the LLM providers you want to use. Alternatively,
you can use Ollama to run models locally on your machine for free and use them in Witsy.
Non-exhaustive feature list:
- OpenAI, Ollama, Anthropic, MistralAI, Google, xAI, OpenRouter, DeepSeek, Groq and Cerebras models supported
- Connect other providers (together, siliconflow, fireworks...) through the OpenAI compatibility layer
- Chat completion with vision models support (describe an image)
- Text-to-image and text-to-video with OpenAI, HuggingFace, and Replicate
- Scratchpad to interactively create the best content with any model!
- Prompt anywhere allows to generate content directly in any application
- AI commands runnable on the highlighted text in almost any application
- Experts prompt you to specialize your bot on a specific topic
- LLM plugins to augment LLM: execute Python code, search the Internet...
- Long-term memory plugin to increase the relevance of LLM answers
- Read aloud assistant messages (requires OpenAI or ElevenLabs API key)
- Read aloud any text in other applications (requires OpenAI or ElevenLabs API key)
- Chat with your local files and documents (RAG)
- Transcription/Dictation (Speech-to-Text)
- Realtime Chat aka Voice Mode
- Anthropic Computer Use support
- Local history of conversations (with automatic titles)
- Formatting and copying to the clipboard-generated code
- Conversation PDF export
- Image copy and download
Prompt Anywhere
Generate content in any application:
- From any editable content in any application
- Hit the Prompt anywhere shortcut (Shift+Control+Space / ^⇧Space)
- Enter your prompt in the window that pops up
- Watch Witsy enter the text directly in your application!
AI Commands
AI commands are quick helpers accessible from a shortcut that leverages LLM to boost your productivity:
- Select any text in any application
- Hit the AI command shortcut (Alt+Control+Space / ⌃⌥Space)
- Select one of the commands and let LLM do their magic!
You can also create custom commands with the prompt of your liking!
Experts
From https://github.com/f/awesome-chatgpt-prompts.
Scratchpad
https://www.youtube.com/watch?v=czcSbG2H-wg
Chat with your documents (RAG)
You can connect each chat with a document repository: Witsy will first search for relevant documents in your local files and provide this info to the LLM. To do so:
- Click on the database icon on the left of the prompt
- Click Manage and then create a document repository
- OpenAI Embedding requires an API key, and Ollama requires an embedding model
- Add documents by clicking the + button on the right-hand side of the window
- Once your document repository is created, click on the database icon once more and select the document repository you want to use. The icon should turn blue
Transcription / Dictation (Speech-to-Text)
You can transcribe audio recorded on the microphone to text. Transcription can be done using the OpenAI Whisper online model (requires API key) or using the local Whisper model (requires download of large files). Once the text is transcribed you can:
- Copy it to your clipboard
- Insert it in the application that was running before you activated the dictation
Anthropic Computer Use
Log in or click on link to see number of positives.
- witsy.2.1.1.nupkg (709ed89beb27) - ## / 65
In cases where actual malware is found, the packages are subject to removal. Software sometimes has false positives. Moderators do not necessarily validate the safety of the underlying software, only that a package retrieves software from the official distribution point and/or validate embedded software against official distribution point (where distribution rights allow redistribution).
Chocolatey Pro provides runtime protection from possible malware.
This package has no dependencies.
Ground Rules:
- This discussion is only about Witsy is a BYOK (Bring Your Own Keys) AI application and the Witsy is a BYOK (Bring Your Own Keys) AI application package. If you have feedback for Chocolatey, please contact the Google Group.
- This discussion will carry over multiple versions. If you have a comment about a particular version, please note that in your comments.
- The maintainers of this Chocolatey Package will be notified about new comments that are posted to this Disqus thread, however, it is NOT a guarantee that you will get a response. If you do not hear back from the maintainers after posting a message below, please follow up by using the link on the left side of this page or follow this link to contact maintainers. If you still hear nothing back, please follow the package triage process.
- Tell us what you love about the package or Witsy is a BYOK (Bring Your Own Keys) AI application, or tell us what needs improvement.
- Share your experiences with the package, or extra configuration or gotchas that you've found.
- If you use a url, the comment will be flagged for moderation until you've been whitelisted. Disqus moderated comments are approved on a weekly schedule if not sooner. It could take between 1-5 days for your comment to show up.