taTanStack
GitHubaiWorkspace
GitHub
  • CI Pipeline Executions
    • Current executionSucceeded
      docs/vercel-comparison-harness-mcp-apps
    • Runs and Agents
    • Configuration
    • Self-Healing CI
    • Project Graph
    • Resource Usage
    • Analysis
    • Conformance
  • Runs
    • Current runSucceeded
    • Tasks
    • Resource Usage
Insights
  • Compare tasks
  • Analytics
    docs(comparison): cover coding-agent sandboxes and MCP Apps vs Vercel AI SDK Vercel AI SDK 7 added a HarnessAgent API (coding-agent harness in a sandbox) and MCP Apps support. Update the comparison page to cover both surfaces: - Coding Agent Sandboxes: first-party Grok Build/Claude Code/Codex/OpenCode harnesses + any ACP agent via acpCompatible, runnable on local/Docker/ Daytona/Vercel/Sprites/Cloudflare, vs Vercel's experimental HarnessAgent centered on Vercel Sandbox with a fixed harness list. - MCP Apps: multi-framework (React + Preact + framework-agnostic bridge), multi-server routing, pluggable session store vs Vercel's React-only experimental_MCPAppRenderer; credit Vercel's model-vs-app tool split. Add matrix rows for both, a When-to-Choose bullet, and bump updatedAt.
    nx run-many --targets=build --exclude=examples/**,testing/**
Succeeded
Linux
4 CPU cores
2c1ed65d878
100%

Cache hits

47 of 47 tasks used cache.

Get faster results

Learn how to enable distribution.

Atomizer enabled

47 groups of tasks optimized.

Resource usage reports are turned off for this workspace

Your organization has the Resource usage add-on, but this workspace does not collect metrics for non distributed runs. Turn it back on in workspace settings.

© 2026 - Nx Cloud

Terms of ServicePrivacy PolicyChangelogStatusDocsContact Nx CloudPricingCompany@NxDevTools