# Crynux Documentation

## Crynux Network

- [Crynux Network](https://docs.crynux.io/readme.md): Truly permissionless DeAI on GPU@edge
- [Lithium Network](https://docs.crynux.io/releases/lithium-network.md): \[Jun 17, 2026] The First Mainnet
- [Helium Network](https://docs.crynux.io/releases/helium-network.md): \[Jan 30, 2024] Decentralized GPT Task Execution Engine
- [Hydrogen Network](https://docs.crynux.io/releases/hydrogen-network.md): \[Nov 8, 2023] Decentralized Stable Diffusion Task Execution Engine
- [Network Architecture](https://docs.crynux.io/system-design/network-architecture.md): Crynux Network Overview
- [Consensus Protocol](https://docs.crynux.io/system-design/consensus-protocol.md): Decentralize the Infrastructure
- [Inference Task Validation](https://docs.crynux.io/system-design/consensus-protocol/inference-task-validation.md)
- [Training/FT Task Validation](https://docs.crynux.io/system-design/consensus-protocol/training-ft-task-validation.md)
- [Verifiable Secret Sampling](https://docs.crynux.io/system-design/verifiable-secret-sampling.md): Reduce the Task Validation Overhead
- [Task Lifecycle](https://docs.crynux.io/system-design/task-lifecycle.md): From the task creation to the task success
- [Task State Transitions](https://docs.crynux.io/system-design/task-lifecycle/task-state-transitions.md): Task as Finite State Machine (FSM)
- [Task Dispatching](https://docs.crynux.io/system-design/task-dispatching.md): Find the best node to execute the task
- [Task Execution Time Estimation](https://docs.crynux.io/system-design/task-execution-time.md): Estimate task execution time from successful tasks
- [Task Pricing](https://docs.crynux.io/system-design/task-pricing.md)
- [Quality of Service (QoS)](https://docs.crynux.io/system-design/quality-of-service-qos.md)
- [Model Distribution](https://docs.crynux.io/system-design/model-distribution.md): Distribute models across the nodes
- [Start a Node](https://docs.crynux.io/node-hosting/start-a-node.md)
- [Start a Node - Windows](https://docs.crynux.io/node-hosting/start-a-node/start-a-node-windows.md): Start a node to join the Crynux Network on Windows
- [Start a Node - Mac](https://docs.crynux.io/node-hosting/start-a-node/start-a-node-mac.md): Start a node to join the Crynux Network on Mac
- [Start a Node - Linux](https://docs.crynux.io/node-hosting/start-a-node/start-a-node-linux.md): Start a node using binary package on Linux (Ubuntu)
- [Start a Node - Docker](https://docs.crynux.io/node-hosting/start-a-node/start-a-node-docker.md): Start a node to join the Crynux Network using Docker images
- [Start a Node - LXC](https://docs.crynux.io/node-hosting/start-a-node/start-a-node-lxc.md): Start a node to join the Crynux Network using LXC images
- [Start a Node - Vast](https://docs.crynux.io/node-hosting/start-a-node/start-a-node-vast.md): Start a node on Vast.ai
- [Start a Node - Octa](https://docs.crynux.io/node-hosting/start-a-node/start-a-node-octa.md): Start a node on Octa.space
- [Private Key Security](https://docs.crynux.io/node-hosting/private-key-security.md)
- [Proxy Settings](https://docs.crynux.io/node-hosting/proxy-settings.md)
- [Multi-GPU Node](https://docs.crynux.io/node-hosting/multi-gpu-node.md): How Crynux Node uses multiple GPUs on a single machine
- [Docker Compose Options](https://docs.crynux.io/node-hosting/docker-compose-options.md): Start the Node using Docker Compose
- [Advanced Configuration](https://docs.crynux.io/node-hosting/advanced-configuration.md)
- [How to Run LLM using Crynux Network](https://docs.crynux.io/application-development/how-to-run-llm-using-crynux-network.md)
- [Supported Models](https://docs.crynux.io/application-development/how-to-run-llm-using-crynux-network/supported-models.md)
- [Tool Use/Function Calling](https://docs.crynux.io/application-development/how-to-run-llm-using-crynux-network/tool-use.md)
- [Structured Output](https://docs.crynux.io/application-development/how-to-run-llm-using-crynux-network/structured-ouput.md)
- [Vision Language Models (VLM)](https://docs.crynux.io/application-development/how-to-run-llm-using-crynux-network/vision-language-models.md)
- [Responses API](https://docs.crynux.io/application-development/how-to-run-llm-using-crynux-network/responses-api.md)
- [Integration with LangChain & LangGraph](https://docs.crynux.io/application-development/how-to-run-llm-using-crynux-network/langchain.md)
- [Hermes Agent Integration](https://docs.crynux.io/application-development/how-to-run-llm-using-crynux-network/hermes-agent-integration.md)
- [How to Fine-tune a Stable Diffusion Model using Crynux Network](https://docs.crynux.io/application-development/how-to-finetune-a-stable-diffusion-model-using-crynux-network.md)
- [Crynux Bridge](https://docs.crynux.io/application-development/crynux-bridge.md): How to Start a Crynux Bridge Locally
- [Application Workflow](https://docs.crynux.io/application-development/application-workflow.md): Use the Crynux Network as the inference API
- [Execute Tasks](https://docs.crynux.io/application-development/execute-tasks.md)
- [Text-to-Image Task](https://docs.crynux.io/application-development/execute-tasks/text-to-image-task.md): How to define a text-to-image task
- [Text-to-Text Task](https://docs.crynux.io/application-development/execute-tasks/text-to-text-task.md): How to define a text-to-text task
- [Text-to-Music Task](https://docs.crynux.io/application-development/execute-tasks/text-to-music-task.md): How to define a text-to-music task
- [Text-to-Video Task](https://docs.crynux.io/application-development/execute-tasks/text-to-video-task.md): How to define a text-to-video task
- [Fine-Tuning Task](https://docs.crynux.io/application-development/execute-tasks/fine-tuning-task.md)
- [API Specification of the Relay](https://docs.crynux.io/application-development/api-specification-of-the-relay.md): The OpenAPI specification of the Relay
- [Crynux SDK](https://docs.crynux.io/application-development/crynux-sdk.md): SDKs to bootstrap the application development
- [Multi-chain Architecture](https://docs.crynux.io/crynux-blockchains/multi-chain.md): Crynux Multi-chain Architecture
- [Token Flow](https://docs.crynux.io/crynux-blockchains/token-flow.md)
- [FAQ](https://docs.crynux.io/troubleshooting/faq.md)
- [Locate the Error Message](https://docs.crynux.io/troubleshooting/locate-the-error-message.md): Find out what exactly goes wrong
- [Exceptions in WebUI](https://docs.crynux.io/troubleshooting/exceptions-in-webui.md)
- [Privacy Policy](https://docs.crynux.io/misc/privacy-policy.md): How Crynux Network handles user data


---

# 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
This site has an agentic ask interface you may use to query the documentation dynamically by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.crynux.io/index.md?ask=<question>&goal=<user_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.