Start

Common tasks

Find the guide for setting up Redgold, building a pipeline application, running coding agents, calling models, or querying application data.

Use this page as the task index for the public documentation. The website, terminal client, coding agents, model API, pipeline applications, and data tools share one account, so you can use several of them in the same workflow.

TaskGuideCurrent access
Set up an account and use the hosted websiteQuickstartInvite-only
Install the terminal clientInstall the clientAvailable with an API key
Build or change a managed backend applicationPipeline application walkthroughManaged preview
Give repository work to a persistent coding agentCoding agentsAvailable
Organize application work across agents and sessionsAgent operationsManaged onboarding
Understand the managed request and delivery pathsArchitecturePublic guide
Call hosted models from an existing applicationFirst API callAvailable with an API key
Use Redgold models from a coding clientCoding-client setupAvailable with an API key
Query data owned by your workspaceQuery application dataPreview onboarding

Set up your account and clients

The quickstart covers the hosted website, repository access, API keys, the terminal client, and the first model-list request. Use the installation recipe when you need platform-specific terminal instructions and troubleshooting.

Build and understand pipeline applications

A pipeline application is the main application-building model. Its reviewed contract consists of Rust schemas, a pipeline manifest, transforms, inline tests, and API routes. Redgold operates the edge, executor, data engine, storage, and deployment around that contract.

The walkthrough shows one complete managed application at an introductory level. The developer Pipeline Apps section covers the deeper architecture, current runtime, portable application preview, and release lifecycle. The Applications section documents concrete products and case studies built on the platform.

Work with coding agents

Coding agents work in persistent repository checkouts with inspectable conversations, tool calls, and diffs. Fleet controls, budgets, live Stream sessions, pull-request review, and CI all belong to this path. Start with Coding agents for the product model and available access paths.

For ongoing work, follow workstreams and issues, agent lifecycle, and the application workstream example. These connect individual tasks to a verified managed deployment.

Agents can author changes to a pipeline application. Coding agents also work in repositories deployed elsewhere, and pipeline applications can be maintained directly through Git. The quickstart covers account and repository setup before the first task.

Use hosted models

Existing OpenAI and Anthropic clients can use https://api.redgold.ai/v1 with an sk-rg- API key. Redgold provides the account's model list, authentication, usage accounting, and provider routing. Follow the first API call recipe, configure a supported coding client, or use the model API reference.

Access application data

Pipeline applications and agent activity write owner-scoped records to the platform data layer. Onboarded workspaces can run read-only queries over their datasets through the supported MCP query path. The pipeline application guides cover application schemas, transforms, and datasets. Dataset onboarding remains coordinated during the preview.

Copyright © 2026