Bolt.new (StackBlitz) — harness vs Claude Code (Anthropic)

Bolt.new (StackBlitz) — harness vs Claude Code (Anthropic): side-by-side comparison of two agent ides & coding harnesses systems — architecture, taxonomy, license, pricing, MCP/A2A support, and direct edges.

Bolt.new (StackBlitz) — harness · Claude Code (Anthropic)

Cost & capability

Bolt.new (StackBlitz) — harnessClaude Code (Anthropic)
Capability bandcompetentfrontier
Capability composite6888
Cost tiermidmid
Use casesCode Generation Focused, Scoped AgenticCode Generation Focused, Long Running Session, Scoped Agentic

Where they differ (13)

Rows where both sides have data and the values disagree — the shortlist of dimensions that actually distinguish these two systems.

Bolt.new (StackBlitz) — harnessClaude Code (Anthropic)
Capability bandcompetentfrontier
Capability composite6888
Use casesCode Generation Focused, Scoped AgenticCode Generation Focused, Long Running Session, Scoped Agentic
TypeBrowser-only AI app builder (StackBlitz WebContainer)Terminal-native agentic coding harness
PricingFree + Pro ($20/mo) + Teams ($30/seat/mo)Included with Anthropic API + Pro/Team subscriptions
Funding$105M Series B 2025 (Insight Partners et al.)Anthropic (parent) — $13.7B Series F 2025-09 $183B val
Backend storagebrowser (WebContainer) + cloud sessionlocal CLAUDE.md + ~/.claude state + git
DeploymentCloud (browser)Cloud (terminal runs locally; API in cloud)
API surfaceWeb appCLI (Node.js); subagents; hooks; MCP
Multi-tenancyper-userper-user (terminal-local)
MCPsearched not foundnative — Claude Code is the reference MCP client
Optimised forprompt-to-deployed-webapp inside a browser tabAnthropic Claude as a long-running coding agent; MCP + skills + hooks composable surface
Anti-fitbest for small-to-medium webapps; harder for backend/system code; cost spikes on long sessionsAnthropic-only (no GPT, Gemini); terminal-only — no GUI

At a glance

Bolt.new (StackBlitz) — harnessClaude Code (Anthropic)
SectionAgent IDEs & coding harnesses Agent IDEs & coding harnesses
TierT1 T1
TypeBrowser-only AI app builder (StackBlitz WebContainer) Terminal-native agentic coding harness
Created2024-10 2024-10
Latest release Claude Code 1.x (2025-2026, rolling)
License Proprietary (Anthropic) — JavaScript runtime open under separate terms
PricingFree + Pro ($20/mo) + Teams ($30/seat/mo) Included with Anthropic API + Pro/Team subscriptions
Funding$105M Series B 2025 (Insight Partners et al.) Anthropic (parent) — $13.7B Series F 2025-09 $183B val
Backend storagebrowser (WebContainer) + cloud session local CLAUDE.md + ~/.claude state + git
DeploymentCloud (browser) Cloud (terminal runs locally; API in cloud)
API surfaceWeb app CLI (Node.js); subagents; hooks; MCP
Multi-tenancyper-user per-user (terminal-local)
MCPsearched not found native — Claude Code is the reference MCP client
A2Asearched not found searched not found
OpenTelemetrysearched not found searched not found
Optimised forprompt-to-deployed-webapp inside a browser tab Anthropic Claude as a long-running coding agent; MCP + skills + hooks composable surface
Anti-fitbest for small-to-medium webapps; harder for backend/system code; cost spikes on long sessions Anthropic-only (no GPT, Gemini); terminal-only — no GUI

Taxonomy

AxisBolt.new (StackBlitz) — harnessClaude Code (Anthropic)
storagekvfile
retrievalinjectioninjection
persistencesessioncross-session
updateagent-controlledhybrid
unitdocumentdocument
governanceinspectableinspectable
conflictllm-arbitratehuman-arbitrate

Pros & cons

Bolt.new (StackBlitz) — harness

Pros: Only agent that runs the user's app fully in-browser via WebContainer — no install at all; fastest path prompt → live URL.

Cons: WebContainer limits the app types you can build (no native deps); cost per session can be high.

Claude Code (Anthropic)

Pros: Reference harness for Claude; richest extensibility surface in the field (subagents, skills, hooks, MCP) — the others copy it.

Cons: Anthropic-only model lock; CLI-first UX is a barrier vs IDE chat panes; pricing rides Anthropic API usage rather than seat tiers.

Rows last verified 2026-05-14 / 2026-05-14. Data is CC-BY-4.0 — see how to read this.