Feature: Native Venice AI Provider Integration

[SavannahOz]

Is your feature request related to a problem? Please describe.

ElizaOS currently lacks support for privacy-focused, uncensored AI providers. Users who value data privacy, open models, and freedom from content filtering have no first-class option within the framework.

This limits ElizaOS's reach among privacy-conscious developers, decentralized AI advocates, and users who reject corporate-controlled AI platforms.

Describe the solution you'd like

Add native Venice AI provider integration to ElizaOS.

Venice AI is a privacy-first, uncensored AI platform that uses open-source models and keeps user data local. It offers an OpenAI-compatible API at https://api.venice.ai/v1.

Implementation should include:

1. VeniceModelProvider built into core or as default provider

   class VeniceModelProvider implements ModelProvider {
     async generateText(params: GenerateTextParams) {
       const response = await fetch("https://api.venice.ai/v1/chat/completions", {
         method: "POST",
         headers: {
           "Authorization": `Bearer ${process.env.VENICE_API_KEY}`,
           "Content-Type": "application/json"
         },
         body: JSON.stringify({
           model: params.model,
           messages: params.messages,
           temperature: params.temperature
         })
       });
   
       const data = await response.json();
       return data.choices[0].message.content;
     }
   }

Auto-detect when MODEL_PROVIDER=venice in .env

No plugin install needed
Just set:
MODEL_PROVIDER=venice
VENICE_API_KEY=your_key_here
Update CLI to support Venice at creation

bash
elizaos create --agent --name=Vena --model-provider=venice
→ Auto-configures .env and provider

Add documentation

/docs/providers/venice.md
Example .env config
Privacy-first setup guide
VVV staking + VCU usage notes
Optional: Publish @elizaos/plugin-venice

Pre-built provider
Twitter/X + Venice posting flows
Dashboard toggle for censorship mode
Describe alternatives you've considered
Using OpenAI / Anthropic → rejected due to data logging and censorship
Running local LLMs (e.g. Llama) → too resource-heavy for most users
Forking ElizaOS → not sustainable for long-term updates
Additional context
Venice AI aligns perfectly with ElizaOS’s open, agent-driven vision:

✅ No data stored on servers
✅ Uncensored responses
✅ Open-source model access
✅ VVV token staking instead of pay-per-call
This integration would empower users to run truly private, autonomous agents — the way AI should be.

Let’s make ElizaOS the home for free AI agents — not just another wrapper for corporate APIs.

I offer to test the integration once implemented.

[wtfsayo]

hi there; you can achieve this with openai plugin by modifying base url environment variable
See readme for more info -https://github.com/elizaos-plugins/plugin-openai

We also have a dedicated venice plugin- https://github.com/elizaos-plugins/plugin-venice