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
- Patronus AI
Score, benchmark, and stress-test LLM outputs for enterprise deployments
- Harness
AI-powered software delivery platform for the post-code lifecycle.
- Spacelift
IaC orchestration platform for Terraform, OpenTofu, and Pulumi teams.
- Kiro
AWS spec-driven AI IDE with GovCloud certification
- CodeRabbit
AI code review platform for pull requests and agent output
- Qodo
AI code review platform built around code integrity
