Bolt New vs Claude Code
A feature-by-feature comparison of Bolt New and Claude Code across 7 capability categories.
Modalities — Claude Code Wins
| Feature | Bolt New | Claude Code |
|---|---|---|
Text Input | Yes. Auto populated | Yes, requires pro plan. Plain-language prompts drive the agent across the CLI, IDE, desktop, and web. |
Image Upload / Vision | No. Auto populated | Yes, requires pro plan. Attached photos in the Claude app are passed into the session as vision context. |
Image Generation | No. Auto populated | No. Documented as a coding agent that edits files and runs commands, not an image generator. |
Voice Mode | Partial. Auto populated | Unknown. Voice exists on the Claude consumer app; Code surfaces do not document a voice loop of their own. |
Video Understanding | No. Auto populated | Unknown. Not described in the Claude Code overview or mobile client docs. |
Video Generation | No. Not a video generation product. | No. Not a video generation product. |
File Upload (PDF, DOCX) | Yes. Auto populated | Yes, requires pro plan. Reads and edits the workspace; mobile Remote Control downloads attached files onto the machine. |
Code Execution | Yes. Auto populated | Yes, requires pro plan. Runs shell commands, tests, and git operations as part of the agent loop. |
Audio Input | No. Auto populated | Unknown. Audio-file input is not documented for Claude Code. |
Canvas / Artifact Editor | Yes. Auto populated | Yes, requires pro plan. Desktop and VS Code surfaces review diffs visually beside the session. |
Screen Sharing / Computer Use | No. Auto populated | Partial. Claude in Chrome can drive a live web app; that is not full-desktop computer use. |
Memory & Context — Claude Code Wins
| Feature | Bolt New | Claude Code |
|---|---|---|
Persistent Memory | Yes. Auto populated | Yes, requires pro plan. CLAUDE.md plus auto memory that saves learnings across sessions. |
Large Context Window | Yes. Auto populated | Yes, requires pro plan. Indexes the repository; Pro lists a 200k context window for Claude. |
Custom Instructions | No. Auto populated | Yes, requires pro plan. Project CLAUDE.md, path-scoped rules, and --append-system-prompt steer behavior. |
Conversation History | Yes. Auto populated | Yes, requires pro plan. Sessions persist across terminal, IDE, web, and mobile, including VS Code history. |
Integrations — Claude Code Wins
| Feature | Bolt New | Claude Code |
|---|---|---|
Web Search / Browsing | Yes. Auto populated | Yes, requires pro plan. Paid Claude plans include web search; Code also pulls live context through MCP servers. |
Plugins / Extensions | No. Auto populated | Yes, requires pro plan. MCP servers and the plugin system connect Drive, Jira, Slack, and custom tools. |
API Access | Partial. Auto populated | Partial. The Agent SDK and Console API keys automate Claude Code; there is no separate public Code REST product besides the Anthropic API. |
Zapier Integration | No. Auto populated | Unknown. No first-party Zapier listing was checked. |
Custom GPTs / Bots | No. Auto populated | Partial. Skills and sub-agents package workflows; they are not a Custom GPT store. |
Real-time Collaboration | No. Auto populated | Unknown. Multiplayer editing of one Code session was not confirmed. |
Live Social Data Integration | No. Not a live social-firehose product. | |
Live Citation Mapping | No. Not a citation-mapping search product. |
Developer — Claude Code Wins
| Feature | Bolt New | Claude Code |
|---|---|---|
Function Calling | No. Auto populated | Yes, requires pro plan. Built-in tools plus MCP and the Agent SDK invoke structured tool calls. |
Streaming Responses | Yes. Auto populated | Yes, requires pro plan. The CLI and IDE surfaces stream tokens as the agent works. |
Fine-Tuning | No. Auto populated | No. Claude Code runs Anthropic-hosted models; no custom-weight training is offered. |
Embeddings API | No. Auto populated | No. Not an embeddings product. |
Structured Output (JSON) | No. Auto populated | Unknown. JSON-schema guarantees are not documented as a Claude Code product switch. |
Reasoning / Thinking Mode | No. Auto populated | Yes, requires pro plan. Runs Claude models with extended thinking for complex work. |
Local Execution | No. The CLI runs on your machine; the model stays on Anthropic (or a third-party provider) infrastructure. | |
Open Weights | No. Claude model weights are not published. | |
Multi-Agent Orchestration | Yes, requires pro plan. A lead agent can spawn sub-agents and merge results; Agent SDK covers custom orchestration. |
Platforms — Claude Code Wins
| Feature | Bolt New | Claude Code |
|---|---|---|
Web App | Yes. Auto populated | Yes, requires pro plan. claude.ai/code runs cloud sessions in the browser with no local install. |
iOS App | No. Auto populated | Yes, requires pro plan. The Claude iOS app has a Code tab for cloud sessions and Remote Control. |
Android App | No. Auto populated | Yes, requires pro plan. The Claude Android app exposes the same Code tab as iOS. |
Desktop App | No. Auto populated | Yes, requires pro plan. Standalone macOS and Windows app; docs say a paid subscription is required. |
Chrome Extension | No. Auto populated | Yes, requires pro plan. Claude in Chrome is listed as a Code surface for debugging live web apps. |
Privacy — Bolt New Wins
| Feature | Bolt New | Claude Code |
|---|---|---|
GDPR Compliant | Yes. Auto populated | Unknown. Needs a read of Anthropic’s current DPA before we assert GDPR. |
Opt Out of Data Training | Yes. Auto populated | Yes, requires pro plan. Individual plans list model-training opt-out; Team and Enterprise default to no training. |
Enterprise Privacy Mode | Yes. Auto populated | Yes, requires enterprise plan. Team and Enterprise add SSO, SCIM, audit logs, custom retention, and a HIPAA-ready option. |
Workspaces — Claude Code Wins
| Feature | Bolt New | Claude Code |
|---|---|---|
Projects / Folders | No. Auto populated | Yes, requires pro plan. Each repository is a workspace; CLAUDE.md and settings travel across surfaces. |