Roadmap

Deep Research Assistant

A rival to OpenAI’s Deep Research Assistant Provide a built in AI agent that acts like a dedicated research assistant. You give it a prompt (a question or topic), and it: Searches the Web: It intelligently browses the internet, finding relevant information. Iterates: It doesn't just stop at the first search. It analyzes the results and asks itself, "Do I need more information?" This creates a loop of searching and refining. Generates a Report: Once it has gathered enough information, it compiles a complete report for you.

Independent Privacy Audit

Venice prides itself with being completely private, but users have no way of checking. They have to trust. I would appreciate a Privacy Audit done by a third party. Alternatively, making more of Venice’s Infrastructure public would increase trust in the Privacy claim. Is that possible / already done / in the works?

Autonomous Character Messages

Allow characters to proactively send messages without requiring a user prompt, enabling more interactive conversations.

Custom Training Sets

Allow users to create custom distilled or fine-tuned models from base models users upload training data in some standardized format training progress can be monitored within the app after training, model is available for download and possibly use within Venice

add embedding model(s)

Apologies if asked/answered, didn’t see it in search results. Having embedding models on API would be great if that’s feasible! thanks

"Copy" should copy <Thought Process> if expanded

When copying a chat response (clicking the “copy” button) the response is copied but the information in the “Thought Process” is not. The user user should have the choice of whether the “Thought Process” information is copied along with the response or not. I propose the following fix: If the tag is COLLAPSED, and the user presses “copy” then the information is NOT copied along with the response. If the tag is EXPANDED, and the user presses “copy” then the information IS copied along with the response. Thank you.

Log in with QR code

android mobile characters

add characters to android mobile

Allow characters to analyze documents/ images

Allow characters to analyze uploaded documents/ images

[Website] Quick reference with current model info

An always-up-to-date page linked from the front page that lists current production (and maybe separate for beta?) models, open source model they’re based on, context and other pertinent data. Currently, as far as I can tell, this kind of information isn’t available in any single place. Trolling through multiple change logs, FAQs, and blog posts is unnecessarily effortful and leaves one with an incomplete picture. Another request, “Active model comparison chart” would likely include this basic info but this would be a simpler place to start. Additionally, it could give a home to add the comparisons suggested in that request as the dropdown might not be a realistic home for so much info.