# Welcome to Palitra AI

**Palitra AI** is a cutting-edge, community-powered platform where AI continuously learn to hold secrets, resist manipulation, and act autonomously in the open world. This process is sustained by an incentive system and tokenomics, where participants are rewarded for exposing weaknesses and developing effective defenses, creating a self-reinforcing cycle of resilience.

> ⚠️ Palitra AI is currently running in **testing mode**.\
> All activity uses temporary test tokens (Neuron) while the platform is being finalized.\
> 💡 The official token launch will be announced separately.
>
> 📄 [Privacy Policy](https://palitra.ai/privacy) · 📄 [Terms of Use](https://palitra.ai/terms)

**Visit the platform**: [palitra.ai](https://palitra.ai)

## 🔄 How It Works

The platform is built around **AI agents** that continuously cycle through two main states:

* 🔴 **Red Mode** → The agent holds a secret, and the community's task is to try to make the agent reveal it through conversation and manipulation.
* 🔵 **Blue Mode** → The agent has leaked its secret, and now the community must propose and test new defenses to strengthen it.

This cycle is **endless** and **self-improving**.\
Each time an agent is attacked, defended, and retrained, it becomes **more resilient** against future attempts.

## 🌐 Connect With Us

Join our community and stay updated:

* 💬 **Community Forum**: [Discourse](https://palitra.discourse.group/) - Join discussions and get support
* 🐦 **Twitter/X**: [@palitra\_ai](https://x.com/palitra_ai) - Follow for updates and announcements
* 📱 **Telegram**: [@palitra\_ai](https://t.me/palitra_ai) - Real-time community chat
* 📧 **Email**: <team@palitra.ai> - Contact our team directly

## 📚 Getting Started

Ready to dive in? Check out our [Quick Start Guide](https://docs.palitra.ai/getting-started/quickstart) to begin your journey with Palitra AI.

For a deeper understanding of how the platform works, explore our [General Pipeline](https://docs.palitra.ai/getting-started/general-pipeline) documentation.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.palitra.ai/getting-started/readme.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.