Claude Code · Anthropic

confidence: highactive136,749

Anthropic's terminal-native agentic coding tool and the category-defining harness, distinguished by its layered extensibility model (CLAUDE.md memory, Agent Skills, subagents, hooks, plugins, MCP) plus permission modes, checkpoints, and optional sandboxing, available from CLI/IDE/desktop/web with an Agent SDK for building on top.

Homepagehttps://claude.com/claude-code
Repositoryhttps://github.com/anthropics/claude-code
Licenseproprietary
Domaincoding
Form factorcli · tui · ide-extension · desktop-app · web-app · sdk · ci-step
Model-agnosticpartial
Native modelsClaude Opus 4.x · Claude Sonnet 4.x · Claude Haiku 4.5
Local models○ no
Pricingsubscription
MCP client✓ yes
Agent Skills support✓ yes
Plugins / hooks✓ yes
Sandboxingoptional
Autonomy spectrumsupervised → semi-autonomous → autonomous-local → background-cloud
Subagents✓ yes
Parallel sessions✓ yes
Context managementcompaction · persistent-memory
Headless / API✓ yes
GitHub integration✓ yes
Sources

✓ profile last verified 2026-07-08 · benchmark figures are vendor-reported unless a source states otherwise