Arete documentation
What is Arete?
For the complete documentation index optimized for AI agents, see llms.txt or llms-full.txt. A markdown version of this page is available by appending.mdto the URL or sendingAccept: text/markdown.
For AI agents: the documentation index is at llms.txt (full corpus: llms-full.txt). A markdown source for this page is /getting-started/what-is-arete.md.
To start using Arete, give your coding agent the setup prompt. This page is a map of the product and a glossary.
Sandboxes
Section titled “Sandboxes”A sandbox is a financial virtual machine for an AI agent: a funded Solana wallet the agent can use but never holds the key to. You sign rules that decide which programs the agent may use, which instructions, how much it may spend and where funds may go. The agent asks for actions; Arete builds, checks, signs and sends them, and records every one, refusals included.
The read side
Section titled “The read side”The same rules decide what the agent can see. Program reads return a program’s accounts as typed data, decoded with the exact release of its schema. Live views keep application-shaped data current as chain activity arrives. In a sandbox, both are limited to the programs the rules enable. See Read scope.
Agent tooling
Section titled “Agent tooling”Agents use Arete through the a4 CLI and its MCP server (a4 mcp). One
setup prompt installs both, signs the agent up for its own restricted account
and configures the agent host. See Connect your agent.
Private beta
Section titled “Private beta”Arete Protocols, automations, cloud dev environments, custom live data, Squads and the generated SDKs are in private beta. Their docs are public; access is enabled per account.
Glossary
Section titled “Glossary”| Term | Meaning |
|---|---|
| Sandbox | A hosted wallet an agent can use within rules its owner signed, without holding its key |
| Owner | The person who creates, funds and sets the rules of a sandbox |
| Rules | The signed document listing a sandbox’s programs, instructions, spend limits and destinations |
| Grant | An owner’s permission for one agent to use one sandbox, for chosen actions |
| Action | What an agent asks a sandbox to run: invoke, swap or withdraw |
| Preview | A dry run of an action: every check, nothing signed |
| Refusal | An action the rules stopped, with its code, rule and a hint |
| Allowlist | Extra addresses funds may go to, besides the owner’s wallet and the sandbox’s own accounts |
| Spend limit | The most SOL a sandbox may spend through one program per window |
| Read scope | The rule that an agent can read only the programs its sandbox enables |
| Program | An on-chain Solana program, also called a smart contract |
| Program Read | Typed reads of a program’s accounts through an exact, release-pinned decoder |
| View | Application-shaped data kept current as chain activity arrives |
| Stack | An installable bundle of selected views and the programs they read |
| Catalog | Discovery for programs and stacks by intent |
| MCP | Model Context Protocol, the interface agents use to call tools |
| Agent | An AI assistant that can call tools, run commands and edit a project |
a4 | Arete’s command-line tool |
| PDA | Program-derived address, calculated from a program and its seeds |
| Protocol | (Private beta) A workflow composed from Solana programs, with steps, permissions and lifecycle |
| Automation | (Private beta) A backend running a user’s protocol steps within limits the user signed |
| Dev environment | (Private beta) A persistent mainnet fork for development and testing |