AI Tools Review

Claude Code

Version: v2.1.224

By Anthropic

Released: 2026-08-07

Anthropic
AI Coding Agent
CLI
Developer Tools
Paid

Anthropic's agentic coding tool that runs in the terminal, IDE and desktop, reading and editing a codebase, running commands and shipping pull requests from natural-language instructions. The 7 August 2026 update (v2.1.224) added cross-session messaging, letting separate Claude Code sessions pass findings to each other via new ListAgents and SendMessage tools.

Visit Claude Code

AI-Powered

Leverages advanced AI technology to deliver cutting-edge capabilities and results.

Fast & Efficient

Optimized performance ensures quick results without compromising on quality.

Purpose-Built

Specifically designed for coding tasks and workflows.

Anthropic Model Timeline

Claude CodeCurrent
Claude Fable 5

1M tokens context

Claude Sonnet 5

1M tokens context

Claude Sonnet 5

1M tokens context

Claude Mythos 5
Claude Fable 5

1M tokens context

Claude Opus 4.8

Long-context context

Claude Cowork
Anthropic: Claude Opus 4.5

200k tokens context

Anthropic: Claude Haiku 4.5

200k tokens context

Claude 4.5 Haiku

200k tokens context

Anthropic: Claude Sonnet 4.5

1,000k tokens context

Anthropic: Claude Opus 4.1

200k tokens context

Anthropic: Claude Opus 4

200k tokens context

Anthropic: Claude Sonnet 4

1,000k tokens context

Anthropic: Claude 3.7 Sonnet (thinking)

200k tokens context

Anthropic: Claude 3.7 Sonnet

200k tokens context

Anthropic: Claude 3.5 Haiku

200k tokens context

Anthropic: Claude 3.5 Sonnet

200k tokens context

Anthropic: Claude 3 Haiku

200k tokens context

Specifications

pricingIncluded with Claude Pro (£16/mo) and Max (£80-£160/mo); API usage billed separately

AI Evaluation

4.6
Expert Rating

The most widely adopted terminal-native coding agent, with a fast-moving feature cadence (worktrees, agent teams, cross-session messaging) and strong default safety guardrails around permissions.

Pros

  • Deep, low-friction terminal and IDE integration
  • Frequent, substantial feature releases (agent teams, cross-session messaging, Remote Control)
  • Careful default permission model: agents can't self-approve risky actions

Cons

  • Cross-session messaging and some newer features aren't yet available on native Windows
  • Usage is metered against Claude plan limits or API billing
  • Best results depend on Claude's own models rather than being model-agnostic