# Gensyn

## Home

- [Welcome](https://docs.gensyn.ai/welcome.md): Welcome to Gensyn's official developer documentation.

## Tech

- [Reproducible Execution Environment (REE)](https://docs.gensyn.ai/tech/ree.md): Run AI model inference in a machine-agnostic environment where the same model and inputs produce the same outputs across supported hardware.
- [Get Started](https://docs.gensyn.ai/tech/ree/get-started.md): Install REE, launch the TUI, and run your first reproducible generation.
- [Using the TUI](https://docs.gensyn.ai/tech/ree/using-the-tui.md): Select models, set prompts, tune parameters, and interpret the output inside of the TUI.
- [Receipts](https://docs.gensyn.ai/tech/ree/receipts.md): Understand what receipts prove, what they contain, and how to validate them.
- [Supported Models](https://docs.gensyn.ai/tech/ree/supported-models.md): A list of models verified to work with REE.
- [Examples](https://docs.gensyn.ai/tech/ree/examples.md): Short, practical recipes for the most common REE workflows.
- [Advanced Usage & CLI Reference](https://docs.gensyn.ai/tech/ree/advanced-usage.md): Skip the TUI and work directly with the SDK CLI, pipeline stages, and container configuration.
- [Internals](https://docs.gensyn.ai/tech/ree/advanced-usage/internals.md): How the Gensyn Compiler and RepOp kernels achieve bitwise reproducibility under the hood.
- [Troubleshooting](https://docs.gensyn.ai/tech/ree/troubleshooting.md): Common errors, their causes, and how to fix them.
- [Agent eXchange Layer (AXL)](https://docs.gensyn.ai/tech/agent-exchange-layer.md): What AXL is, what it does, and what you can build with it.
- [Get Started](https://docs.gensyn.ai/tech/agent-exchange-layer/get-started.md): Instructions on how to get started with AXL.
- [Configuration](https://docs.gensyn.ai/tech/agent-exchange-layer/configuration.md): CLI flags, node settings, and example configurations.
- [How it Works](https://docs.gensyn.ai/tech/agent-exchange-layer/how-it-works.md): In-depth information on AXL's architecture, encryption, peering, privacy model, wire format, and node internals.
- [Building Applications & Examples](https://docs.gensyn.ai/tech/agent-exchange-layer/examples-and-building.md): Shipped examples and step-by-step patterns for building your own services with send/recv, MCP, and A2A, plus patterns for building your own applications on top of it.
- [Troubleshooting](https://docs.gensyn.ai/tech/agent-exchange-layer/troubleshooting.md): Common build, peering, and runtime issues with their causes and fixes.

## Testnet

- [Overview](https://docs.gensyn.ai/testnet/overview.md): A live, open test network for decentralised machine learning.
- [RL Swarm (Paused)](https://docs.gensyn.ai/testnet/rl-swarm.md): RL Swarm lets anyone, anywhere, join and participate in a distributed reinforcement learning system that learns faster together than alone.
- [How It Works](https://docs.gensyn.ai/testnet/rl-swarm/how-it-works.md): Learn how RL Swarm functions under the hood, from GenRL’s modular architecture to multi-agent learning, coordination, and reward cycles.
- [CodeZero](https://docs.gensyn.ai/testnet/rl-swarm/how-it-works/codezero.md): Learn about CodeZero, the cooperative coding environment powering RL Swarm.
- [Legacy Environments](https://docs.gensyn.ai/testnet/rl-swarm/how-it-works/legacy-environments.md): An archive of legacy RL Swarm environments, including Reasoning Gym, which has been replaced by CodeZero.
- [Getting Started](https://docs.gensyn.ai/testnet/rl-swarm/getting-started.md): Browse resources for getting started with RL Swarm.
- [Windows (WSL 2)](https://docs.gensyn.ai/testnet/rl-swarm/getting-started/windows-wsl-2.md): Spin up your node and participate in the swarm in a Windows (WSL 2) environment.
- [Linux](https://docs.gensyn.ai/testnet/rl-swarm/getting-started/linux.md): Spin up your node and participate in the swarm in a Linux (Ubuntu 22.04+) environment.
- [macOS](https://docs.gensyn.ai/testnet/rl-swarm/getting-started/macos.md): Spin up your node and participate in the swarm in a macOS environment.
- [Node Management](https://docs.gensyn.ai/testnet/rl-swarm/node-management.md): Learn how to monitor, maintain, and control your RL Swarm node once it’s running.
- [Troubleshooting](https://docs.gensyn.ai/testnet/rl-swarm/troubleshooting.md): Stuck? Get unblocked with RL Swarm on Windows (WSL 2), Linux, or macOS, or reach out to support for more help.
- [BlockAssist (Paused)](https://docs.gensyn.ai/testnet/blockassist.md): BlockAssist is an interactive, AI-driven Minecraft environment where reinforcement learning agents learn from your actions.
- [Getting Started](https://docs.gensyn.ai/testnet/blockassist/getting-started.md): Get up and running with BlockAssist and start training your own model.
- [Windows (WSL 2)](https://docs.gensyn.ai/testnet/blockassist/getting-started/windows-wsl-2.md): Get up and running with BlockAssist on your Windows device with a WSL 2 environment.
- [Linux](https://docs.gensyn.ai/testnet/blockassist/getting-started/linux.md): Get up and running with BlockAssist in your Ubuntu 22.04+ Linux environment.
- [Running BlockAssist on a Remote Linux Desktop](https://docs.gensyn.ai/testnet/blockassist/getting-started/linux/running-blockassist-on-a-remote-linux-desktop.md): Learn how to run BlockAssist on a remote Linux environment using several types of devices.
- [macOS](https://docs.gensyn.ai/testnet/blockassist/getting-started/macos.md): Get up and running with BlockAssist in your macOS environment.
- [Using BlockAssist](https://docs.gensyn.ai/testnet/blockassist/using-blockassist.md): Use the platform-agnostic guide below to launch BlockAssist after installation, complete tasks, train your models, and upload them via Hugging Face.
- [Running BlockAssist with Cursor](https://docs.gensyn.ai/testnet/blockassist/using-blockassist/running-blockassist-with-cursor.md): This guide shows non-technical users how to set up and run BlockAssist on macOS using Cursor, an AI-powered code editor with an integrated chat assistant.
- [Hugging Face Guide](https://docs.gensyn.ai/testnet/blockassist/hugging-face-guide.md): Follow this quick tutorial to sign up for Hugging Face and generate a private token for use with BlockAssist.
- [CodeAssist (Paused)](https://docs.gensyn.ai/testnet/codeassist.md): CodeAssist is an AI assistant that learns from every edit, keystroke, and solution, adapting to your style and training itself to become the perfect coding partner for you.
- [Getting Started](https://docs.gensyn.ai/testnet/codeassist/getting-started.md): Get up and running with CodeAssist and start training local models based to code like you.
- [Windows (WSL 2)](https://docs.gensyn.ai/testnet/codeassist/getting-started/windows-wsl-2.md): Get up and running with CodeAssist in your Windows (WSL 2) environment.
- [Linux](https://docs.gensyn.ai/testnet/codeassist/getting-started/linux.md): Get up and running with CodeAssist in your Linux (Ubuntu 22.04+) environment.
- [macOS](https://docs.gensyn.ai/testnet/codeassist/getting-started/macos.md): Get up and running with CodeAssist in your macOS environment.
- [Using CodeAssist](https://docs.gensyn.ai/testnet/codeassist/using-codeassist.md): Read the end-to-end CodeAssist user guide and start training your own personal coding model.
- [Hugging Face Guide](https://docs.gensyn.ai/testnet/codeassist/hugging-face-guide.md): Follow this quick tutorial to sign up for Hugging Face and generate a private token for use with CodeAssist.
- [Troubleshooting](https://docs.gensyn.ai/testnet/codeassist/troubleshooting.md): Stuck? Get unblocked with CodeAssist on Windows (WSL 2), Linux, or macOS, or reach out to support for more help.

## Litepaper (legacy)

- [Litepaper](https://docs.gensyn.ai/litepaper/litepaper.md): The hyperscale, cost-efficient compute protocol for the world’s deep learning models