Claude Code
Agentic coding tool that runs in your terminal
Description
𝐂𝐥𝐚𝐮𝐝𝐞 Code is a command-line coding agent built by Anthropic. It reads a project's full codebase, plans changes across files, runs commands, and iterates on test failures until the work is done. The tool targets developers who want to delegate full tasks rather than accept line-by-line autocomplete suggestions.
Key Capabilities:
✓ Terminal-first CLI for editing files, running shell commands, and managing projects through natural language
✓ Project-level codebase understanding for multi-file refactors and feature implementation
✓ Native git workflows including staged commits, branch creation, and pull request authoring
✓ Test-fix iteration loop that reads CI errors, edits code, and reruns until suites pass
✓ VS Code extension and GitHub Action surfaces, including @**𝐂𝐥𝐚𝐮𝐝𝐞** mentions in issues and pull requests
✓ MCP integration for connecting Google Drive, Jira, Slack, and custom tooling
✓ 𝐂𝐥𝐚𝐮𝐝𝐞.md project configuration for code style, review criteria, and repository conventions
✓ Configurable permission modes covering manual approval, classifier-based auto-approval, and scheduled routines
✓ Plugin system with slash commands, agents, and skills installable through /plugin install
✓ Python and TypeScript agent SDKs, with provider support for 𝐂𝐥𝐚𝐮𝐝𝐞 API, AWS Bedrock, Google Vertex AI, and Microsoft Foundry
Alternative tools
- OpenAI Codex CLI
Terminal coding agent built on OpenAI reasoning models
- Aider
AI pair programming in your terminal
- Cline
Open-source AI coding agent for any editor
- Braintrust Evals
Trace every step your LLM agent takes, from prompt to response
- Giskard
Scan AI agents for vulnerabilities before and after deployment
- Promptfoo
Test and red team LLM applications from the command line
