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) — harness | Claude Code (Anthropic) | |
|---|---|---|
| Capability band | competent | frontier |
| Capability composite | 68 | 88 |
| Cost tier | mid | mid |
| Use cases | Code Generation Focused, Scoped Agentic | Code 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) — harness | Claude Code (Anthropic) | |
|---|---|---|
| Capability band | competent | frontier |
| Capability composite | 68 | 88 |
| Use cases | Code Generation Focused, Scoped Agentic | Code Generation Focused, Long Running Session, Scoped Agentic |
| Type | Browser-only AI app builder (StackBlitz WebContainer) | Terminal-native agentic coding harness |
| Pricing | Free + 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 storage | browser (WebContainer) + cloud session | local CLAUDE.md + ~/.claude state + git |
| Deployment | Cloud (browser) | Cloud (terminal runs locally; API in cloud) |
| API surface | Web app | CLI (Node.js); subagents; hooks; MCP |
| Multi-tenancy | per-user | per-user (terminal-local) |
| MCP | searched not found | native — Claude Code is the reference MCP client |
| Optimised for | prompt-to-deployed-webapp inside a browser tab | Anthropic Claude as a long-running coding agent; MCP + skills + hooks composable surface |
| Anti-fit | best for small-to-medium webapps; harder for backend/system code; cost spikes on long sessions | Anthropic-only (no GPT, Gemini); terminal-only — no GUI |
At a glance
| Bolt.new (StackBlitz) — harness | Claude Code (Anthropic) | |
|---|---|---|
| Section | Agent IDEs & coding harnesses | Agent IDEs & coding harnesses |
| Tier | T1 | T1 |
| Type | Browser-only AI app builder (StackBlitz WebContainer) | Terminal-native agentic coding harness |
| Created | 2024-10 | 2024-10 |
| Latest release | — | Claude Code 1.x (2025-2026, rolling) |
| License | — | Proprietary (Anthropic) — JavaScript runtime open under separate terms |
| Pricing | Free + 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 storage | browser (WebContainer) + cloud session | local CLAUDE.md + ~/.claude state + git |
| Deployment | Cloud (browser) | Cloud (terminal runs locally; API in cloud) |
| API surface | Web app | CLI (Node.js); subagents; hooks; MCP |
| Multi-tenancy | per-user | per-user (terminal-local) |
| MCP | searched not found | native — Claude Code is the reference MCP client |
| A2A | searched not found | searched not found |
| OpenTelemetry | searched not found | searched not found |
| Optimised for | prompt-to-deployed-webapp inside a browser tab | Anthropic Claude as a long-running coding agent; MCP + skills + hooks composable surface |
| Anti-fit | best 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
| Axis | Bolt.new (StackBlitz) — harness | Claude Code (Anthropic) |
|---|---|---|
| storage | kv | file |
| retrieval | injection | injection |
| persistence | session | cross-session |
| update | agent-controlled | hybrid |
| unit | document | document |
| governance | inspectable | inspectable |
| conflict | llm-arbitrate | human-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.