Changelog
Follow up on the latest improvements and updates.
RSS
new
improved
fixed
1.3.0
- Added gpt-4omodel. The latest & greatest from OpenAI ticks all the boxes for Wingman AI, so we are making it the new default model for... everything. We've even removed thegpt-3.5-turboandgpt-4-turbooptions because we're sure we won't need them anymore. General responses should already be significantly faster, and it will get much faster once OpenAI unlocks audio input/output to the API. The model also seems to work well with our new contexts and capabilities. Please let us know (with examples) if we are wrong!
- StarHead is now a Skill, meaning you can attach it to any Wingman.
- Added new Control Windows Skillto launch applications, minimise/maximise Windows etc. For example, tell it to “Open Spotify”. Note that the skill currently only looks for applications in your Start Menu directory (%APPDATA%/Roaming/Microsoft/Windows/Start Menu/Programs), so if it tells you that it cannot find an application, create a shortcut in that directory.
- Added new Spotify Skillto play songs or playlists, "like” songs, control the playback device and more. The skill is very intelligent and honestly takes Spotify to another level because you can ask it things like: “Play the theme song from Bad Boys”. Try it out, it’s really good! You will need to create a developer account for your Spotify Premium account and then connect Wingman to it. The Spotify client has to be running on any one of your clients and must be playing a song. Otherwise, the Spotify Web API won't find any active device for your account. You can find more information and instructions on our Discord server.
- Added Groq and OpenRouter(in favour of the old "Llama") as AI providers. You can select any of their models from a list in the UI, but only Mistral and Llama3 have been tested with AI function calls. However, you can use other models for roleplaying etc. and experiment with them. Our demo contexts may need to be tweaked to work properly with other models.
- Added "Local LLM" as an AI provider**. This makes it easier for you to connect to different models from different providers. Use "Local LLM" instead of the old "OpenAI > Advanced > base_path" setting to connect to Ollama, LMStudio etc. You can now enter your own custom model name and are no longer limited to the drop down choices in the client.-
- Updated default commands for Star Citizen 3.23. There have been a lot of changes in the last SC patch and our commands are by no means a complete mapping for everything. Feel free to improve these bindings and post your updates in Discord. We can collect your changes and then release them for everyone to use.
- Added a handler and websocket allowing you to connect esp32devices to Wingman AI. This is what we used in our Walkie Talkie for Wingman AI short video. We’ll publish a blog post about this but until then, contact @Timo if you’re interested in connecting external devices to Wingman AI usingOpenInterpreteretc.
- Added Debug Modetoggle to global settings. Enable this for more verbose system messages and additional benchmarks-
- @JayMatthew’s beloved UEXCorpWingman has already been converted to be a skill, too. Unfortunately, the UEXCorp API was changed completely yesterday, so he will fix the skill as soon as possible and you can then install it (without another Wingman AI update) when it’s done. You can even use it together with StarHead now! You may need to give special commands to determine which skill you want to prefer when asking for a good trading route. We are experimenting with this, but we need more data and experience from you, so please let us know how it goes.
- fixed crashes when AI function calling with llama3 models
SlickGPT Pro (For Wingman Ultra users):
- added gpt-4omodel for both SlickGPT Free and Pro users
- Free users can now use llama3(for free via Groq) andmistral-largewith their own API keys. We are waiting for a fix in Azure to serve these two options in our SlickGPT Pro backend.
- various UI improvements on desktop & mobile viewports
new
1.2.1
- We updated the StarHead Wingmanto support better trading data and added a new function to get detailed ship data. You can ask for ship details or even compare different ships or ship systems. Try something like "What is the difference between a Constellation Taurus and a Constellation Andromeda", for example.
- We worked around the super slow performance of GPT-4-Turbo, so you can now use it again. It's still slower than GPT-3.5-Tubo.
- Remove emotesfrom Audio Playback, if they are in the text result. Sometimes the AI want's to express emotions like this, but it was very annoying in the audio output.
new
improved
1.2.0
- Mistral AIhas been added as a top class provider. You can use your own API key to access all their cloud models or use the most powerful one (mistral-large) with Wingman Pro. Please note that if you use Mistral, you will need to adapt your contexts, as it does not seem to handle our examples written for GPT very well. Mistral supports function calls, so start with "You are a helpful assistant", which should work with AI commands, and iterate from there.
- We have also added experimental support for Llama3. It's all ready in Wingman AI, but not yet in Azure, so if you try to use it with Wingman Pro, your requests will time out. We are waiting for Microsoft to fix this and will let you know when it works (hopefully with no additional client update). Until then, you can use 3rd party providers like Groq (super fast!) or host it locally and play around with it. Function calls won't work yet because we need to write some more code to parse them, but you can already chat with it and run instant commands as usual.
- Reworked command UI. You can now add mouse and write (text) actions. You can also delete individual actions from a command's action list and reorder them using drag and drop.
- Improved Windows audio device settings. Wingman AI should now handle disconnected devices or changed hardware configurations much better.
- Improved function call parsing to be more robust when using local LLMs.
- Added a UI option to make OpenAI the default provider for all Wingmen settings. This makes it easier to use Wingman AI without a subscription. Note that you can still manually change your default provider in the config defaults.yaml in your config directory.
Unfortunately we have to change our payment provider for tax reasons.
We are switching from Stripe to Paddle.
We have already changed the whole process for new users/subscribers. If you have a subscription with Stripe, you can still manage it using the client and our website. We are currently trying to determine if we need to cancel and migrate current Stripe subscriptions. If you would like to help with the transition, please cancel in Stripe and then re-subscribe with Paddle if your subscription has expired. You don't need to do anything at the moment, but if this changes we'll let you know!
Roadmap
Aside from potential hotfixes, we will now focus on Wingman AI 2.0, which will include an exciting new system:
Wingman Skills
!Skills are similar to custom wingmen, but easier to implement. They can be selected from a list (think "Alexa") and shared between Wingmen easily. Huge for developers: you can define your own Python dependencies, so you don't have to fork the whole Wingman repository if you want to use a library that's not already available. We have already converted our StarHead and UEXCorp community Wingmen to skills, so you'll be able to use both at the same time in the future.
We are also experimenting with non-gaming skills such as an "app launcher" on Windows. We think this expansion will open up Wingman AI to other use cases. So "Spotify Wingman" and "Get data from this website Wingman" are now within reach. Give us some more time to polish the API and write some nice example skills.
So long, stay hydrated!
fixed
1.1.1 (Hotfix)
- fixed error when switching config
- text input is now disabled if the focused Wingman is disabled
new
improved
fixed
1.1.0
- You can now send text messagesto your Wingmen! To do so:
- Select a Wingman in the bar on the left to open a filtered "Focus view" which only shows the conversation history with this particular Wingman. If you talk to another Wingman while in this mode, the view will automatically switch to the activated Wingman. Select "View all" to see the shared "Terminal" with messages of all your Wingmen (as usual).
- fixed handling of "extended" keys and added a default "hold time" of 0.1s which should greatly improve keypress command executions. If you had "Wingman doesn't press the key" issues before, please try again with this version!
- added "extended macro" recordings, meaning that key down/up events will be recorded separately. This gives you more flexibility to record complex and staggered macros
- The client now has a button to reset the conversation history(in both Focus and Terminal view)
- reworked "energy threshold" controls for Voice Activation in the client. It's no longer a slider but a numeric input with presets (low/standard/custom) and better hint texts to explain what meaningful values are.
- fixed Microsoft password policy to be less restrictive
- fixed Conversation/Summarize model not being saved properly when using the client
- changed/moved various API endpoint URLs
new
improved
fixed
1.0.0
- added user authentication (to the client)
- added Wingman Pro as new default provider with several choices for you: STT: Azure Speech or OpenAI Whisper (via Azure);TTS: Azure TTS or OpenAI TTS (via Azure);AI Conversation & Summarization:gpt-3.5-turboorgpt-4-turbo(via Azure);Voice Activation: A special implementation of Azure Speech STT;Regions: Europe or USA - pick the nearest for best latency!
- ElevenLabs: output streaming can now be disabled; lowered default latencyOptimization(from 3 to 2) to prevent choppy audio
- added OpenAI base_urlandorganizationparams to the UI, allowing you to plug in a local LLM as stand-in replacement (or a proxy) easily
- added a lot of hint texts to the UI & updated docs
- migrated to new elevenlabslibversion and updated all important packages
- stop current playback if a new one starts, preventing "overlapping" audio
- Voice Activation now prefilters all recordings and checks if they contain frequency bands resembling human voice
- print version number and update notification on start
- fixed some keybinding issues with "special” keys like Alt and Alt Gr
- fixed Star Citizen "SelfDestruct" command not being executed due to moderation policies
- fixed a crash occurring on command execution
- fixed Azure speech languages not being passed correctly
- fixed a performance problem with Voice Activation
- fixed Wingman initialization errors not showing up in the UI
- fixed a problem causing slowdowns if whispercppwas configured but not running
- fixed a bug preventing to change the AI model to gpt-4-turbowhen using Azure
- fixed StarHead not setting gpt-4-turboas default model correctly
Known issues:
- gpt-4-turbovia Azure/Wingman Pro is VERY slow at the moment. Microsoft is informed and (hopefully) working on it.
- Voice Activation sends way too many blank messages to the STT provider. We found a cool solution that we will test until the final release but it’s not in the RC yet.
- If you only see a blank white screen after starting the client: Close Wingman AI. Delete this directory: %APPDATA%/Local/com.wingman.dev. Restart Wingman AI.
Happy Easter holidays and have fun!
new
improved
fixed
2.1.0b2
- Elevenlabs and Azure Speechnow support real output audio streaming, meaning that they’ll start playbacksignificantly fasterthan before. Edge and local XVASynth are fast enough to not require it and OpenAI still has an open issue that we're observing and waiting for an official fix before we implement it.
- You’re now auto-muted during playback so that Wingmen will no longer talk to themself endlessly (when using external speakers or over-sensitive mics)
- playback can now be stopped (with a button in the client, not with voice because you’re muted during playback)
- client now shows playback state in the Wingman Card (similar to the “recording dot”) fixed key recording with modifiers and some special keys like numpad keys
- added Feedback view where you can post and votefor feature requests and see what we’re currently working on. This is also available at https://wingman-ai.canny.io/.
- added a changelog widget to “Core version” in the Settings view. It’s now a button that turns orange when the Core version is outdated (temporary solution). Note that the oudated state will not work during the pre-test phase - beta2 will always be "green" until we go public.
- add option to force commands to be triggered by instant activation. This fixes AI calling the ResetHistoryCommandfor no apparent reason
- Voice activation now allows to to have no “Default Wingman” configured and you can “undefault” a Wingman in the client
- added new OpenAI 0125 models. You can use them already with your own OpenAI API key but Azure does not support them yet. We’ll add them as soon as they’re available.
- ResetHistoryCommandis now a “system command” that cannot be edited in the client
- moved Light/Dark mode toggle to Settings view
- updated documentation and added Linux Setup HowTo (community-based, not officially supported)
- fixed a bug that would break the config when changing the Mute key in the client
- fixed a validation bug that would prevent you from changing Elevenlabs “slider” settings
- fixed a bug that unmuted Voice activation when a push-to-talk key was activated
- fixed Custom Wingman property hints not showing
- changing config or deleting a Wingman now clears the Terminal in the client
- fixed several labels & translations
- fixed minor layout issues in the client
new
improved
fixed
2.0.0b2
- The open source "Wingman AI" is now called Wingman AI Core.It has been completely rewritten usingFastAPIandPydanticand is now basically a type-safe API that our (closed source) client uses. This is also great news for you: You can now basically do and trigger everything "from the outside" if you need to. Interface with your game, build your own client, embed it on a toaster... the possibilities are really endless. Once the core is up and running, check outhttp://127.0.0.1:8000/docs- it's an interactive OpenAPI (ex: Swagger) spec!
- Our package now includes the Wingman AI Core (backend) and our Wingman UI (client). The client will start the core silently in the background. If you don't want to use our client (or want to modify the Core), you can start it manually with WingmanAiCore.exe. Bonus: The client will detect an already running instance of the core, so you can hook it to a modified version, e.g. one running from source.
- Config files are now stored in your OS-specific %APP_DATA%directory. On Windows this is something likeC:\user\AppData\Roaming\ShipBit\Wingman AI\2_0_0_b2and has a few advantages:
- Configs are now versioned. If you install a newer version of Wingman AI Core later, your old configs will still be there.
- Finally, you don't need admin privileges anymore. Really.
- Windows automatically synchronizes the roaming directory across devices
- The config structure has changed quite a bit. The most important change is that Wingmen configs now reside in their own files and are merged with a new defaults.yamlat runtime. If you are a Core-only user, you can still easily override what should be changed in a specific wingman. When you save a config with our client, the wingman config will contain everything, including a copy of the defaults. We always use the default config to create new wingmen, but you can't currently edit them in the UI. So if you always want to use 11Labs for all your new wingmen, change it indefaults.yamland new wingmen will pick it up. If you ever mess up your config, just delete everything exceptsecrets.yamlin your config directory, then restart Wingman AI. It will rebuild the default configs from our templates.
- Voice Activation:You asked for it and we listened. You can now talk to your wingmen without having to press PTT. If you enable this feature in the (global) settings, you should define a "Default Wingman". You can always just talk to him without saying his name. To talk to the other wingmen in your active config, say their names anywhere in your sentence. This is not perfect, and if the name is misspelled, it won't work. So choose names that are easy to say. You can also press your wingmen's activation keys to force them to talk to you, even if voice activation is turned on. Voice activation is currently Azure Speech only. We'd like to add whispercpp as well, but it's not supported well enough for us yet. On our list though.
- Command Key Recording: Use our new interface to actually "record" hotkeys (with our without modifiers) or more complex macros. Our preconfigured commands were recorded on a German Windows keyboard and may not work for other layouts. If you find a hotkey does not work, try rebinding it in the client.
- New providers:
- XVASynth: XVASynth is a local TTS provider installed through Steam that supports downloadable voices cloned from various games. Only available on Windows.
- whispercpp: whispercpp is a local STT (transcription) provider and it's really, really fast. @teddybear082 has provided both adapter implementations for Wingman AI, and you can configure them using our client. Running and configuring them is up to you though, as we cannot bundle them.
- Audio Device Settings: Finally, set your input (microphone) and output device using our client.
- Lots of bug fixes, most importantly:
- remember_messagesno longer raises atool_callserror and preserves your history correctly. Thanks to @jaymatthew.
- Command execution should be much more robust now.
- various 11Labs and Azure fixes
Our client has a ton of other new features that we'll leave you to explore. Some of the coolest are avatars for your wingmen, multiple configurations, live previews of voice & audio effects, and many, many more.
One last thing: Patreons are now getting the "full version" to try out. This will be "Wingman Pro" at some point in the future. There will also be a free basic version, but it might not have all the features. So please don't be disappointed if the day comes when we launch Pro and you don't have access to everything anymore. We know it feels bad to "take away" features, but we consider you our testers and of course we have to test everything.
Have fun and let us know what you think. Feedback is greatly appreciated!
Known issues:
- Azure's speech recognizer sometimes crashes on mute/unmute. Please be gentle with the mute toggle and if it crashes, just restart Wingman.
- You currently cannot record Alt Gr, Esc, F5, and CTRL+F5. If you need to bind these, you can do so directly in your config file.
- You currently cannot record mouse or "write" (=type) macros with the client. They do work, so you can add them to your config manually.
TODOs
- Produce a "HowTo setup & showcase" video
- A lot of UI hints (the small "info") icons and texts are still missing.
new
1.1.3b1
- Added Azure Speech integration to support speech-to-text
fixed
1.1.2b1
- Fixed a sneaky bug that would cause Wingman to create temporary files in your system32directory instead of in its extraction directory during certain moon phases. This could potentially lead to a false-positive Antivirus alert.
- StarHead
- now connects to their stable API endpoint instead of their test instance
- deactivates itself gracefully if the remote API is unreachable
Load More
→