docs: simplify interactive agent installation

[miyoungc]

Summary

The Hermes and LangChain Deep Agents Code quickstarts previously told interactive users to set agent and sandbox environment variables before launching the installer. The standard installer already prompts for both values, so this change gives all three agents the same one-command start while explaining the recommended express install mode and the optional interactive path.

Changes

• Use the bare hosted installer command in the Hermes and LangChain Deep Agents Code interactive quickstarts.
• Tell users which agent to select and how to choose or accept the suggested sandbox name during onboarding.
• Recommend express install mode when supported, explain that it installs OpenClaw by default, and direct Hermes and Deep Agents users to the OpenClaw quickstart.
• Tell users to enter n when they want interactive Hermes or LangChain Deep Agents Code onboarding or custom settings.
• Preserve environment-variable examples for scripted and advanced installation flows.

Type of Change

• Code change (feature, bug fix, or refactor)
• Code change with doc updates
• Doc only (prose changes, no code sample modifications)
• Doc only (includes code sample changes)

Quality Gates

• Tests added or updated for changed behavior
• Existing tests cover changed behavior — justification:
• Tests not applicable — justification: Documentation-only correction; installer behavior is unchanged.
• Docs updated for user-facing behavior changes
• Docs not applicable — justification:
• Sensitive paths changed (security, policy, credentials, preflight, onboarding, inference, runner, sandbox, or messaging)
• Sensitive-path review completed or maintainer-approved waiver recorded — reviewer/approval link/justification:
• Non-success, skipped, or missing CI check accepted by maintainer — check name, approval link, and follow-up issue:

Documentation Writer Review

• Documentation writer subagent reviewed the completed changes
• Result: docs-updated
• Evidence: README.md, docs/get-started/quickstart.mdx, docs/get-started/quickstart-hermes.mdx, and docs/get-started/quickstart-langchain-deepagents-code.mdx; reviewed this documentation-only change against the writing rules and documentation style, including terminology, structure, voice, code-sample presentation, links, routes, and product-scope claims. Verified installer and onboarding behavior against scripts/install.sh and checked-in onboarding sources. npm run docs passed with 0 errors and two unrelated warnings: the unauthenticated Fern redirect check and the existing light-theme contrast warning. Normal pre-commit, commit-msg, and pre-push hooks passed.
• Agent: Codex Desktop

DGX Station Hardware Evidence

• Tested on DGX Station
• Tested commit:
• Station profile/scenario:
• Result:
• Supporting evidence:

Verification

• PR description includes a Signed-off-by: line and every commit appears as Verified in GitHub
• Normal pre-commit, commit-msg, and pre-push hooks passed, or npm run validate:pr passed after refreshing origin/main when hooks were skipped or unavailable
• Targeted behavior tests pass for the current change set, or tests are marked not applicable above — command/result or justification: Tests are not applicable to this documentation-only correction.
• Applicable broad gate passed — npm test for broad runtime/test-harness changes; npm run check for repo-wide validation/coverage changes — command/result:
• Quality Gates section completed with required justifications or waivers
• No secrets, API keys, or credentials committed
• npm run docs builds without warnings (doc changes only)
• Doc pages follow the style guide (doc changes only)
• New doc pages include SPDX header and frontmatter (new pages only)

npm run docs completed with 0 errors. Fern reported one unrelated light-mode accent contrast warning (2.41:1); this PR does not change theme configuration.

---

Signed-off-by: Miyoung Choi miyoungc@nvidia.com

[coderabbitai]

Note

Reviews paused

It looks like this branch is under active development. To avoid overwhelming you with review comments due to an influx of new commits, CodeRabbit has automatically paused this review. You can configure this behavior by changing the reviews.auto_review.auto_pause_after_reviewed_commits setting.

Use the following commands to manage reviews:

• @coderabbitai resume to resume automatic reviews.
• @coderabbitai review to trigger a single review.

Use the checkboxes below for quick actions:

• ▶️ Resume reviews
• 🔍 Trigger review

📝 Walkthrough

Walkthrough

The installer documentation now describes interactive onboarding and Express-mode behavior. Users can select agents, sandboxes, inference settings, and credentials. The quickstart documents post-install access for the default my-assistant sandbox.

Changes

Interactive onboarding

Layer / File(s)	Summary
Interactive installer flows README.md, docs/get-started/quickstart-hermes.mdx, docs/get-started/quickstart-langchain-deepagents-code.mdx, docs/get-started/quickstart.mdx	The documentation uses hosted installation and interactive selection for agents, sandbox names, inference providers, models, and credentials.
Express mode and post-install access docs/get-started/quickstart-hermes.mdx, docs/get-started/quickstart-langchain-deepagents-code.mdx, docs/get-started/quickstart.mdx	The quickstarts describe Express-mode presets, interactive opt-out behavior, managed local inference, default sandbox names, status checks, dashboard access, and terminal connections.

Estimated code review effort: 2 (Simple) | ~10 minutes

Suggested labels: area: onboarding

Suggested reviewers: aasthajh

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title clearly summarizes the documentation changes that simplify interactive agent installation.

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Commit unit tests in branch codex/docs-unified-agent-install

---

_{Comment @coderabbitai help to get the list of available commands.}

[github-actions]

🌿 Preview your docs: https://nvidia-preview-pr-8187.docs.buildwithfern.com/nemoclaw

[coderabbitai]

Actionable comments posted: 1

🤖 Prompt for all review comments with AI agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Inline comments:
In `@README.md`:
- Line 37: Format the Express installer option consistently as bold UI text in
README.md at lines 37-37, docs/get-started/quickstart-hermes.mdx at lines 47-47,
and docs/get-started/quickstart-langchain-deepagents-code.mdx at lines 50-50;
update each occurrence to use **Express**.

🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

• Push a commit to this branch (recommended)
• Create a new PR with the fixes

---

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: 64aa72ee-fbcd-4349-9427-ddae18a1dc7a

📥 Commits

Reviewing files that changed from the base of the PR and between 6a838ff and 7fa23c5.

📒 Files selected for processing (3)

• README.md
• docs/get-started/quickstart-hermes.mdx
• docs/get-started/quickstart-langchain-deepagents-code.mdx

[github-actions]

PR Review Advisor — No blocking findings reported

Advisor assessment: No blocking advisor findings reported
Next action: No advisor follow-up needed.
Findings: 0 blockers · 0 warnings · 0 suggestions

Model lanes

• GPT-5.6 Terra (primary): Completed · high confidence · 0 blockers · 0 warnings · 0 suggestions
• Nemotron 3 Ultra (second opinion): Completed · high confidence · 0 blockers · 0 warnings · 0 suggestions
• Model comparison: normalized findings match; normalized terminology decisions differ; normalized E2E selections differ; severity counts match.

1 terminology difference from the second opinion

Advisory only. These are normalized differences from the primary terminology receipt.

• express install at README.md:36: selected only by the second-opinion lane as established.

7 additional E2E selections from the second opinion

Advisory only. The primary lane did not select these E2E jobs or targets.

• spark-install: The completed second-opinion lane identified E2E coverage that the primary lane omitted.
• bootstrap-install-smoke: The completed second-opinion lane identified E2E coverage that the primary lane omitted.
• onboard-resume: The completed second-opinion lane identified E2E coverage that the primary lane omitted.
• onboard-repair: The completed second-opinion lane identified E2E coverage that the primary lane omitted.
• hermes-e2e: The completed second-opinion lane identified E2E coverage that the primary lane omitted.
• ubuntu-repo-cloud-openclaw: The completed second-opinion lane identified E2E coverage that the primary lane omitted.
• ubuntu-repo-cloud-langchain-deepagents-code: The completed second-opinion lane identified E2E coverage that the primary lane omitted.

Second-opinion terminology and E2E selections are advisory. They do not change the primary assessment or E2E / PR Gate.

3 semantic terminology decisions

Terminology decisions are advisory. They affect the assessment only when a separate finding identifies concrete semantic impact.

• define — express install mode at README.md:37: Define the term at first use with its preset and non-interactive behavior, then use it consistently.
• define — recommended preset settings at README.md:36: Name the applied settings or refer directly to express install mode when the exact preset is not relevant.
• established — interactive onboarding at docs/get-started/quickstart-hermes.mdx:168: Use the established term consistently for the prompted onboarding path.

E2E guidance

Advisory only. E2E / PR Gate selects and runs jobs independently.

Recommended E2E: None

Workflow run details

This automated review informs maintainers. Warnings and suggestions do not require a response. A maintainer decides whether to merge.

[cv]

Reviewed commit 1531c3a1ae. The OpenClaw, Hermes, and Deep Agents quickstarts now match the installer order: the Express prompt can precede agent selection, Express installs OpenClaw by default, and n continues to interactive agent and sandbox choices. The command samples, sandbox names, active voice, links, and UI formatting are consistent across the changed pages.

Approval is blocked by the failed Nemotron Advisor job and a documentation-writer receipt tied to pre-merge commit 5b544a483 rather than this commit.