Claude Code vs Crush: pricing, features and which to choose

Claude Code is Anthropic's agentic coding tool, launched in June 2025. It reads repositories, edits files, runs commands, and operates through the terminal, VS Code, JetBrains, desktop app, and web. The product targets developers working on features, bugs, tests, dependency updates, migrations, and release tasks. Anthropic added Claude Code to enterprise offerings in August 2025 after first making it available through individual accounts. Anthropic does not publish a standalone Claude Code user count or funding figure. The company said in March 2026 that Claude Code's run-rate revenue had surpassed $2.5 billion, although TechCrunch reported that figure as a company statement rather than a user metric. The product remains active, with frequent releases and changing model availability.

A typical session starts in a project directory or connected repository. The developer describes a task, Claude Code examines relevant files, proposes a plan, edits files, runs tests or shell commands, and reports results. It can stage changes, write commit messages, create branches, and open pull requests. Developers can guide behavior with CLAUDE.md files, skills, hooks, permissions, and MCP connections to services such as Jira, Slack, or Google Drive. GitHub Actions and GitLab CI/CD support automated review and issue triage. Desktop and web sessions add visual diff review, parallel cloud tasks, and scheduled work. The agent can spawn subagents, but command approvals, test results, generated edits, and security findings still need engineering review.

Claude Code suits developers who can review diffs, run tests, manage permissions, and control token spending. It is less suitable for unattended production changes, deterministic analysis, or users who only want inline completion. GitHub Copilot CLI offers a closer GitHub-centered alternative, Gemini CLI emphasizes Google's tooling and models, and Cursor remains more editor-centered. Claude Code's strongest case is repository-wide work combining planning, file edits, shell commands, tests, Git, and external tools. Its main tradeoffs are shared subscription limits, changing model access, and the need to inspect generated work. Pick Claude Code if terminal or repository-wide agent workflows matter more than lightweight autocomplete.

Crush is a Go terminal coding agent made by Charmbracelet, the company behind Bubble Tea and other terminal tools. The repository was created in May 2025 and has grown to more than 28,000 stars on GitHub. It runs on macOS, Linux, Windows through PowerShell or WSL, Android, FreeBSD, OpenBSD, and NetBSD. The application is free to install, but it does not include unlimited model inference. Charm lists Hyper as its official subscription provider, while users can connect hosted APIs or local models. That split matters for budgeting because Crush is the client, while the selected provider normally bills model usage. The project uses the FSL-1.1-MIT license, with each version converting to MIT on its second anniversary.

The normal workflow begins in a project directory, where Crush opens an interactive terminal interface and asks for a model or API key. Users can maintain multiple sessions and preserve context while switching models. Language Server Protocol integration supplies code intelligence, while Model Context Protocol support adds tools through HTTP, stdio, or SSE servers. The agent can inspect files, propose edits, and run commands, with configuration controlling permissions. Crush supports OpenAI-compatible and Anthropic-compatible custom providers, alongside Anthropic, OpenAI, Gemini, OpenRouter, Bedrock, Vertex AI, and Groq. Its security documentation says crushrc is trusted shell code and warns that shell substitutions in crush.json run during configuration loading. Configuration review therefore belongs in the normal deployment process.

Crush combines LSP context, MCP extensibility, sessions, local-model support, and broad operating-system coverage in one terminal client. Its cost and model quality depend on external providers, while its FSL license restricts some competing commercial redistribution before conversion. Configuration can execute shell code, so teams need permission discipline and repository review. Aider focuses on repository editing with an open-source license, Claude Code is Anthropic's first-party coding agent, and GitHub Copilot CLI is more closely tied to GitHub accounts and Copilot plans. Those products offer clearer single-vendor operating models. Pick Crush if endpoint flexibility, local inference, and terminal portability matter more than one bundled subscription or conventional open-source licensing.