## What this adds Two new docs pages for **Agent Relay**, a feature that connects a supported cloud-hosted AI agent provider's hosted sessions to self-hosted Coder workspaces. The provider's orchestration and AI inference stay cloud-hosted; a worker process inside the workspace executes the agent's tool calls. - `docs/ai-coder/agent-relay/index.md` — top-level overview: what it is, what it does, what it is and isn't, business value, current state, and supported providers. - `docs/ai-coder/agent-relay/cursor.md` — the Cursor-specific child page, naming Cursor Cloud Agents and Cursor's own bring-your-own-machine (BYOM) terminology. Both pages are tagged `"state": ["early access"]` in the manifest and state the feature is in **closed preview with select customers**, pointing readers to their Coder account team or `sales@coder.com` for access. ## Also included - `docs/user-guides/workspace-management.md`: broadened the workspace definition to include coding agents alongside developers. - `docs/reference/glossary.md`: added an Agent Relay entry (alphabetized between Agent Firewall and AI Gateway) and added it to the existing "agent" term-disambiguation callout, since it's easy to conflate with Coder Agents. ## Scope note for reviewers `Agent Relay` itself (the underlying service, config, and worker implementation) lives in a separate, non-public repository. I don't have access to that source from this environment, so I deliberately kept both pages high-level and didn't invent specifics like CLI flags, config file structure, or exact command syntax. Before this goes further, someone with access to that repo should verify the mechanics described here (workspace-per-session lifecycle, provider pool mapping, worker connection model) against the real implementation, and a follow-up PR should add a step-by-step "Getting started" section once the feature moves past closed preview to something self-serve. ## Validation - `docs/manifest.json` is valid JSON. - `markdownlint-cli2`: 0 issues across all changed/added Markdown files. - `vale --no-exit`: 0 errors on every changed/added file (a handful of pre-existing gerund-heading warnings on `workspace-management.md` and `glossary.md` predate this branch and aren't touched here). - `scripts/check_emdash.sh`: passes. - Confirmed every relative link target in the new pages resolves to a real file in the repo. <details> <summary>Decision log</summary> - Dropped an "air-gap capable" claim and a "Coder AI Gateway" claim that would have been present in an earlier draft: the integration requires the in-workspace worker to hold an outbound connection to the cloud provider for inference/orchestration, so true air-gapping isn't possible, and Coder's AI Gateway isn't in the inference path for this feature. - Named the specific Cursor product as **Cursor Cloud Agents** and linked Cursor's own "bring-your-own-machine (BYOM)" terminology (`cursor.com/docs/cloud-agent/bring-your-own-machine`) rather than inventing Coder-specific naming for the same concept. - Kept "workspace" lowercase per the existing style guide (`workspace` is the documented generic-concept casing, distinct from named features like "Workspace Proxy"), while still linking the term to the Workspace Management page. - Used "closed preview with select customers" rather than "Preview," and removed a blanket "not feature-complete or stable" disclaimer sentence per explicit direction. </details> --- 🤖 This PR was created by Coder Agents on behalf of @mattvollmer. --------- Co-authored-by: Nick Vigilante <nickvigilante@users.noreply.github.com>
4.4 KiB
title
| title |
|---|
| Run AI Coding Agents in Coder |
Learn how to run & manage coding agents with Coder, both alongside existing workspaces and for background task execution.
Coder supports several ways to run and govern coding agents, depending on how much control you need over execution and orchestration:
- Coder Agents, self-hosted AI workflow infrastructure best suited for headless, automated background tasks and parallel agentic development in a conversational UI.
- Agent Relay, best suited for preserving the cloud agent experience developers already know while running execution in self-hosted Coder workspaces.
- Agents in the IDE, best suited for in-editor code assist use cases alongside a developer's existing workflow.
- Agents in workspace templates, best suited for developers who want to pair one-on-one with an agent like Claude Code or Codex in a workspace.
Coder Agents
In cases where the IDE is secondary, such as prototyping, research, or long-running background jobs, Coder Agents is the recommended way to delegate development work to coding agents in your Coder deployment.
Coder Agents is a native AI coding agent built into Coder. The agent loop runs in the Coder control plane on your infrastructure rather than inside the workspace, so workspaces can be completely network isolated. Developers interact with agents through the web UI or the REST API.
Learn more about Coder Agents for architecture details, supported LLM providers, and how to get started.
Agent Relay
Agent Relay connects a supported cloud-hosted AI agent provider's hosted sessions to self-hosted Coder workspaces. The provider's orchestration and AI inference stay cloud-hosted; a worker process inside the workspace executes the agent's tool calls. Cursor Cloud Agents is the first supported provider.
Agent Relay is in early access and is in closed preview with select customers.
Learn more about Agent Relay for architecture details and supported providers.
Agents in the IDE
Coder integrates with IDEs such as Cursor, Devin Desktop, and Zed that include built-in coding agents to work alongside developers. Additionally, template admins can pre-install extensions for agents such as GitHub Copilot.
These agents work well inside existing Coder workspaces as they can simply be enabled via an extension or are built-into the editor.
Agents in workspace templates
Template admins can install terminal-based coding agents, such as Claude Code or Codex, directly into a workspace template using a registry module. Pick from a curated list of agent modules in the template builder, or add a module directly in Terraform:
module "claude-code" {
source = "registry.coder.com/coder/claude-code/coder"
version = "~> 5.2"
agent_id = coder_agent.main.id
}
Visit the Coder Registry for the full list of available agent modules.
Learn more about extending templates.
Govern AI activity with AI Governance
AI coding tools are quickly becoming core to how engineering teams ship software. As adoption grows, platform teams want a clear picture of how AI is being used, consistent guardrails across teams, and predictable cost controls so they can confidently scale AI tooling to the whole organization.
AI Governance is included with a Premium license and adds observability, management, and policy controls for AI tooling across your Coder deployment. It includes:
- AI Gateway for centralized authentication, audit trails of prompts and tool invocations, and policy enforcement against upstream LLM providers.
- Agent Firewall for process-level network and command policies that restrict what agents can reach and do inside a workspace.
Learn more about AI Governance for use cases, entitlements, and how to enable it in your deployment.
