Claude Code
Coding agents · Claude Code CLI, Anthropic coding agent
A coding agent from Anthropic: it reads the project, edits files, runs commands and tests, and works with git. It runs in the terminal (CLI), in VS Code and JetBrains, in the desktop app and in the browser, and it is the same agent everywhere. It has no model of its own: it runs on Claude models (Opus, Sonnet, Haiku); you switch the model with /model. It reads project rules from CLAUDE.md, keeps repeatable processes in skills and connects outside systems through MCP. Its closest alternatives are Codex and Cursor.
Claude Code vs Claude: the difference
| Claude chat | Claude Code | |
|---|---|---|
| Where it runs | browser, phone, app | terminal, VS Code and JetBrains, app, browser |
| Sees your project | no, only what you paste | yes, it reads the files |
| What it does | replies with text | edits files, runs commands and tests, works with git |
| Model | Claude models | the same Claude models, switched with /model |
| Project rules | projects and instructions | a CLAUDE.md file in the repo |
| Outside systems | connectors | MCP servers |
| Pricing | a Claude plan | the same Claude plan (Pro, Max) or pay-as-you-go API |
What they share and how they differ
| Claude Code | Codex | Cursor | Hermes | |
|---|---|---|---|---|
| Edits code, runs commands | ✓ | ✓ | ✓ | ✓ |
| Rules file | ✓ | ✓ | ✓ | ✓ |
| Own editor | ✗ | ✗ | ✓ | ✗ |
| Terminal | ✓ | ✓ | ✓ | ✓ |
| Tasks in the cloud | ✓ | ✓ | ✓ | ✗ |
| Models from several vendors | ✗ | ✗ | ✓ | ✓ |
| Your own server | ✗ | ✗ | ✗ | ✓ |
✓has✗none
Read more: Claude Code, Codex, Cursor and Hermes Agent: which to pick
Where it appears · 15
- AI agent = LLM + harness · Harness
- MCP server and AI agent for 1C · Harness
- Analytical reports with an AI agent · Harness
- Claude in Chrome · Harness
- The agent’s data plane and control plane · Harness
More 10
- Incident investigation with an AI agent · Harness
- MCP scopes in Claude Code · Harness
- MCP for an AI agent · Harness
- Claude Code, Codex, Cursor and Hermes Agent · Harness
- How to run and analyze interviews about AI use · Research
- Harness engineering in practice · Harness
- Approaches to working with a harness · Prompts and review
- A reconcile loop for specs · Specs and context
- AGENTS.md and CLAUDE.md, specs, rules and skills · Specs and context
- Prompts for work tasks · Prompts and review