Private, uncensored agents just got easier to build

Venice and Fleek are partnering to create the first end-to-end agent infrastructure that combines Venice's privacy-first AI inference with Fleek's seamless agent deployment

Let's break it down 🧵 This partnership eliminates the fragmented process of piecing together multiple services, letting developers focus on creating agents that solve real-world problems instead of wrestling with infrastructure.

Venice provides uncensored, privacy-first AI inference, while Fleek handles the complete agent lifecycle from development to monitoring with containerized hosting, built-in security, and automatic scaling.

Introducing Venice Image Engine v2 🌅

Venice Image Engine v2 is now live and represents a comprehensive overhaul of our image generation infrastructure, delivering the highest quality results across a range of styles

Let’s dive in 🧵 Venice Image Engine v2 consists of two major components:

1. Venice SD35 (New Default model): Custom-configured Stable Diffusion 3.5 engine powered by a Comfy UI workflow backend.

2. Upscale & Enhance (Pro only): Completely new upscaling architecture with proprietary enhancement that creatively in-fills new pixels at the higher resolution.

How to build private AI agent-powered workflows with n8n & Venice API

A comprehensive step-by-step guide 🧵 Integration Prerequisites
Before starting the integration process, ensure you have the following prerequisites in place:

Venice API Key

Obtain your Venice API key by staking VVV tokens, topping up your account with USD, or upgrading to Venice Pro. Note that Pro accounts have more restrictive rate limits.

Follow the Venice API documentation for detailed instructions on generating your API key: docs.venice.ai/overview/guide…

Vibe code privately in Cursor with Venice API

Here's how 🧵 Before starting the integration of Venice's API into Cursor, you'll need:

• Venice API key obtained through VVV staking, topping up your account with USD, or upgrading Venice Pro

You can follow these instructions for obtaining your API key:

• Cursor installed on your machine (download Cursor here)docs.venice.ai/overview/guide…

This Week in Venice 🌅

We're shipping new features every day, so here's our weekly overview of the daily changelog 🧵  🗓️ March 14-15

Securely Backup Chat History
Pro users can how securely backup chat history and migrate to other devices, or recover from a loss of data in their local browser.

Here's how they work:

1On your local device, when you create a new backup, Venice encrypts your data with a password that only you control.
2That backup is then broken into chunks and uploaded to Venice's infrastructure.
3You can then download and restore that backup, either overwriting your existing history, or merging it, on any logged in device.

A few important notes:

•Venice does not have any record of the password you create, so if you loose it, your backup is unrecoverable. We suggest you use a password manager to store them.
•You are limited to a max of 5 concurrent backups.
•Backups expire after 90 days.
Backups can be accessed via the menu in the left hand side menu

This Week in Venice 🌅

We're shipping new features every day, so here's our weekly overview of the daily changelog 🧵 🗓️ March 7-9

Characters with Pro Models accessible to all users
Characters that use Venice Pro models are now accessible for non-pro members to interact with. Anonymous and Free users will get a limited number of chats with these characters before being prompted to upgrade to Venice Pro. We look forward to your feedback on Venice Characters.

Venice Voice Downloads
Venice users can now download audio generate from Venice Voice. Once the audio has completely generated, a download icon will appear to the right of the speaker. Clicking this will allow you to save the audio recording as a .wav file.

The Venice Airdrop ended today at dawn, Venetian time 🌅

Over the past 45 days, 17.4 million VVV tokens were claimed by over 40,000 people

We now enter a new phase for Venice 🧵 To those who are just hearing about it, what does the VVV token do?

The Venice API is free for any human or agent who stakes VVV, meaning zero-cost generative AI for private and uncensored text, image, and code

Stake VVV for free API access here venice.ai/token

ICYMI: This Week in Venice

We're shipping new features every day, so here's an overview of this week's daily changelog 🧵 🗓️Feb 28th

App
Filtered out uncensored image models from the available image model list when Venice Safe Mode is enabled for image generation.

Hide chat settings on character pages unless toggled on.

API
Added documentation on the /characters endpoint that provides details on available public characters.

Resolved issue with in-painting where invalid images would throw 500 errors. Invalid images will now throw 400 Bad Request errors with a description in the body of the response.

Pro users can create their own AI Characters in Venice to chat with privately

Here's a quick guide to creating your Character 🧵 Step 1. Start building your Character

In the sidebar click “Characters”, and then click the "+" button in Characters to open the creation interface, where you'll find all the tools needed to bring your AI companion to life.

Venice’s mission is to provide permissionless access to private and uncensored machine intelligence

Since launch in May 2024
• 400,000 registered users
• 50,000 DAU
• 15,000 inference requests per hour

Today, we open our API to the public for AI agents, devs, and 3rd party apps

Paired with this: the Venice token, also now live on @base

It was airdropped to over 250,000 people and AI agents this morning

Here’s everything you need to know 🧵 Before we dive in, bookmark this post as it contains important information about the VVV token launch and airdrop

You can also read the full details in our VVV token launch blog post here

venice.ai/blog/introduci…

Ever been frustrated by the output you're getting in Venice?

Chances are your prompts need some work

Let's show you how to get the most out of text chat in Venice 🧵 Good prompts are open-ended questions or queries, and typically include:

• Clear instructions
• Relevant context
• Desired output format
• Specific details or constraints

Bad prompts are often too short, vague, lack context, or are too broad