docs(library): restore content dropped by automated refreshes

[waleedlatif1]

Summary

Four automated library refreshes dropped accurate content. This PR adds it back into each post's current structure. It does not revert the refreshes.

• byok-multi-model-ai-agent-builder (lost in docs(library): update byok-multi-model-ai-agent-builder #8323): restores the 1.1x hosted-key multiplier and the BYOK provider list (models plus search/enrichment providers), checked against apps/docs/content/docs/platform/costs.mdx. Removes the false claim that BYOK is an Enterprise capability: workspace keys work on any Sim Cloud plan, and organization keys need Pro/Max for Teams or Enterprise. Removes the "Enterprise-only local models" framing, since self-hosted Sim connects to Ollama/vLLM through OLLAMA_URL/VLLM_BASE_URL with no Enterprise gate. Cites the docker#ollama and environment-variables docs.
• best-ai-agent-platforms-2026 (lost in docs(library): update best-ai-agent-platforms-2026 #8298): restores the Logs / Chat / Tables operational passages as a new "How does Sim handle agents after deployment?" section. Each claim now cites first-party docs: logs-debugging/logging, logs-debugging/alerts, chat, chat/workflows, tables, tables/using-in-workflows.
• best-no-code-ai-agent-builders-2026 (lost in docs(library): update best-no-code-ai-agent-builders-2026 #8299): restores a dated, first-party-cited pricing comparison for the vendors this post still covers: Sim, n8n, Gumloop, and Zapier Agents. Each price was re-checked against the vendor's own pricing page and is marked "as of October 2026". Changes since the August figures: Sim now also lists Max at $100; Gumloop has no permanent free plan (14-day Pro trial) and charges a 16% BYOK orchestration fee; n8n figures are shown in the currency the page displays for your locale, and the Business price is no longer quoted. Lindy, MindStudio, Botpress, and Vellum are not restored because the current post no longer covers them. The TL;DR line saying the guide "does not reproduce figures" is updated to match.
• best-ai-agents-support-ticket-triage (docs(library): update best-ai-agents-support-ticket-triage #8296): the n8n license FAQ now says September 2026, matching the body's "License facts as of September 2026" instead of "as of August 2026".
• License wording (all four posts): "Sim is Apache 2.0 / free to self-host" claims now say Sim's core is Apache 2.0 and note that features in apps/sim/ee are under the Sim Enterprise License. The phrasing matches existing library posts.

updated is bumped to 2026-10-01 on all four posts. best-ai-agent-platforms-2026 already had that date. Authors and date are unchanged.

Testing

• All four files parse against ContentFrontmatterSchema (strict, no canonical) and compile with @mdx-js/mdx + remark-gfm (scratch script outside the repo).
• FAQ answers contain no Markdown links or URLs.
• All internal /library/ links resolve to existing folders, and none point to a retired slug in LIBRARY_MERGED_SLUGS.
• bun run check:site-urls passes.

🤖 Generated with Claude Code

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

1 Skipped Deployment

Project	Deployment	Actions	Updated
docs	Skipped		Oct 1, 2026 6:09pm UTC

[cubic-dev-ai]

No issues found across 4 files

Confidence score: 5/5

• Automated review surfaced no issues in the provided summaries.
• No files require special attention.

_{Re-trigger cubic}

[greptile-apps]

Confidence Score: 5/5

[Low risk] Restores marketing content dropped by automated updates.

The PR appears safe to merge; no outstanding findings or new actionable issues were identified.

Summary

The PR restores and updates four library guides with BYOK, pricing, operational, and licensing information. Since the previous review, it has clarified the BYOK provider categories and hosted-key fallback, and qualified the workflow-snapshot claim. The three previous findings are addressed and their threads are resolved.

_{Reviews (2) · Last reviewed commit: "fix(library): scope BYOK providers by us..."}

[waleedlatif1]

@greptile

[waleedlatif1]

@cubic-dev-ai review this PR

[cubic-dev-ai]

@cubic-dev-ai review this PR

@waleedlatif1 I have started the AI code review. It will take a few minutes to complete.

[cubic-dev-ai]

No issues found across 4 files

Confidence score: 5/5

• Automated review surfaced no issues in the provided summaries.
• No files require special attention.

_{Re-trigger cubic}