> For the complete documentation index, see [llms.txt](https://docs.palliora.org/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.palliora.org/readme.md).
# Overview
**The private computer for the open internet.**
Privacy is what lets people and businesses act freely. Accountability is what keeps everyone safe. Palliora is how the open internet gets both: private by default, accountable by design. See [Why Palliora](/why-palliora.md).
Palliora plugs into the chains and platforms you already use. Its Guardian network runs computation and moves value while keeping both private and accountable. Your users, assets and liquidity stay where they are. See [Where Palliora runs](/learn/where-palliora-runs.md).
It starts with finance and AI, the two places where private, accountable computation is needed most today.
## Two inventions
* **Compute Contracts.** A publicly recorded agreement that names what runs, on whose data, under what confidentiality, and who gets paid. Terms are locked before anything executes, and every step after that is recorded. Compute Contracts connect private, off-chain work to public, on-chain accountability. See [Compute Contracts](/learn/concepts/compute-contracts.md).
* **Accountable Privacy.** Data and identities stay sealed by default. A specific record can be revealed only when a signed, publicly logged request is approved by a quorum of independent Guardians, and only that record. Users can also share time-bound view keys on their own terms. See [Accountable privacy](/learn/concepts/accountable-privacy.md).
Two pieces of infrastructure deliver them:
* **The Guardian network.** Independent nodes that hold key shares, sign contracts, run computation and approve disclosure. No single Guardian can decrypt anything on its own. See [Guardian](/learn/concepts/guardian.md).
* **Encrypted Data Availability.** Data is encrypted before it reaches Palliora. Anyone can check that it exists and hasn't changed. No one can read it alone. See [Data availability](/learn/concepts/data-availability.md).
See [How Palliora works](/learn/how-it-works.md) for the full picture.
## Built on Palliora
Palliora's first two products are built in-house, as proof of what it can do and as SDKs for platforms to integrate:
* [**Palliora DeFi**](/products/palliora-defi.md): private trading on any chain, accountable to regulators. *Privacy for traders. Answers for regulators.*
* [**Palliora AI**](/products/palliora-ai.md): private, accountable compute for AI, from running models privately to a verifiable record of what an agent did. *Private data. Accountable agents.*
Anything else that needs private data with a public guarantee can be built the same way. See [What you can build](/products/use-cases.md).
## What's live today
Everything below runs on Manas, Palliora's public testnet, as Palliora prepares for mainnet.
* Guardians, validators and compute nodes, at about 700 transactions per second, 6-second blocks and 15 to 20 second finality.
* Confidential compute in Intel TDX on Guardians that have the hardware. Not every Guardian has it.
* Verifiers, checking results against each contract's own tests.
* Palliora DeFi, live on testnet on Hyperliquid and Ethereum, with a demo app.
* Palliora AI's SDK, in development on testnet: one Guardian runs a small model inside Intel TDX. Its demo app, AI Workbench, is live at [ai.palliora.org](https://ai.palliora.org/).
* A completed security audit.
For the full picture, see [Status and roadmap](/learn/status-and-roadmap.md).
## Where to start
| If you are… | Start here |
| ---------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Evaluating Palliora or trying to understand how it fits together | [Why Palliora](/why-palliora.md), then [How Palliora works](/learn/how-it-works.md) |
| A platform that wants private trading or private AI | [Products](/products/products.md) |
| Building it yourself | [Quickstart](/build/quickstart.md) |
| Handing the build to a coding agent | [Build with a coding agent](/build/coding-agents/build-with-a-coding-agent.md) |
| Running infrastructure | [Participate](/participate/participate.md) |
| Just trying it | [Try the Palliora DeFi demo app](/use/demo-apps.md) or the [Palliora AI demo app](https://github.com/palliora-org/palliora-docs-with-ai/tree/main/ai/use/demo-apps.md) |
| An AI coding agent reading this page | [For agent-assisted developers](/build/coding-agents/for-agent-assisted-devs.md) and [llms.txt](https://github.com/palliora-org/palliora-docs-with-ai/tree/main/llms.txt) |
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.
Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:
```
GET https://docs.palliora.org/readme.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.
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.
