Shipped a billing migration with it last week that I'd been putting off for two months. It read the schema, wrote the migration, ran the tests, fixed the two it broke. I reviewed the diff over coffee. That's the whole review.

Claude Code
An AI coding agent for terminal, IDE, web, and Slack

About Claude Code
Claude Code is Anthropic's coding tool for developers. It works directly in a codebase to help build, debug, and ship software by understanding code, editing files, and running commands.
It is available for macOS, Linux, and Windows, with additional access through the terminal, web, iOS, Android, GitHub, VS Code, JetBrains, and Slack. Claude Code is included with Claude Pro, Max 5x, and Max 20x plans.
Pro costs $17 per month with an annual subscription discount or $20 billed monthly. Max 5x costs $100 per month, and Max 20x costs $200 per month. Usage limits apply.
Highlights
- Understands codebases and explains repository behavior
- Edits files and runs commands
- Supports terminal and IDE workflows
- Available on macOS, Linux, and Windows
- Included with Claude Pro and Max plans
It is very good and it is also very expensive if you let it run without a plan. My advice: write the plan yourself, make it small, and only then let the agent execute. Used this way the quality is consistently high. Used as a slot machine it is not.
Does what it says. The UI is a bit cluttered and I wish it had better keyboard shortcuts, but the results are reliable.
Great for prototyping. I wouldn't let it touch production without review, but for getting to a working demo in an afternoon it's unbeatable.
Very good for refactor, I think best one. But sometimes it is too confident and change file I didn't ask. I always use git worktree now, so no problem. Japanese comment in code is also handled ok.
Similar tools
ECC
— Open agent harness for coding workflows, GitHub automation, and securityOpen agent harness for coding workflows, GitHub automation, and security
Hermes Agent
— Open-source self-hosted AI agent with persistent memoryOpen-source self-hosted AI agent with persistent memory
DeepSeek Harness
— A modular, plugin-based framework for building and running agentsA modular, plugin-based framework for building and running agents
Firecrawl
— Context API for searching, scraping, and interacting with the webContext API for searching, scraping, and interacting with the web
Open WebUI
— Self-hosted interface for connecting and extending AI modelsSelf-hosted interface for connecting and extending AI models

LangChain
— Open platform for building, testing, deploying, and governing agentsOpen platform for building, testing, deploying, and governing agents