Terminal agent · active

Claude Code

An agentic coding tool that reads, edits, and runs a codebase across terminal, IDE, desktop, and browser surfaces.

Visit Claude Code ↗Verified ·Jul 31, 2026
Best for
Developers who prefer a terminal-first agent but want the same workflow available in editors and remote sessions.
Avoid if
You need local model execution or predictable fixed-cost usage at high volume.

01 / Editorial view

Where it fits

Strengths

  • Deep terminal workflow
  • Multiple first-party surfaces
  • MCP, skills, hooks, and instruction support

Limitations

  • Usage cost varies by access method and workload
  • The service and models are proprietary

02 / Workflow

Surfaces and capabilities

Autocomplete
No
Chat
Yes
Agent
Yes
Background agent
Yes
Review
Yes
Testing
Yes

Editors

VS Code, Cursor, JetBrains

Operating systems

macOS, Windows, Linux

Repository hosts

GitHub, GitLab

Languages

Language-agnostic

Bring your own key

Yes

Bring your own model

No

03 / Cost and deployment

What it costs to run

Individual

Most surfaces require a Claude subscription or Anthropic Console account.

Team

Team and Enterprise subscriptions are available.

Enterprise

Subscription or cloud-provider billing.

API cost varies with model choice, context, and workload.

04 / Privacy

Data handling

Code processing
The local CLI can connect to Anthropic, Amazon Bedrock, or Google Vertex AI; web sessions run remotely.
Indexing
Unknown
Retention
Retention depends on account type, provider, and user settings.
Training policy
Anthropic states commercial code and prompts are not used for training unless the customer opts into model improvement.
Enterprise controls
Managed settings, Cloud-provider deployment options, Audit and policy controls

05 / Evidence

Primary sources

Changelog

What changed

  • Claude Code surfaces verifiedJul 31, 2026Updated the profile to reflect terminal, editor, desktop, and web access rather than treating Claude Code as CLI-only.

Next