• Landmark project

  140,581 stars

• Actively maintained

  Pushed within 48 hours

• Continuous integration

  Automated checks passing

• Repeat trending

  22 trending appearances

• Top 10% tracked

  Rank 39 of 1058

Claude Code is an advanced, terminal-based AI coding assistant developed by Anthropic that deeply integrates with local codebases. It allows developers to execute routine tasks, perform complex refactoring, and handle git workflows entirely through natural language commands directly in their CLI. The tool indexes the local environment to provide context-aware suggestions and can autonomously execute multi-step engineering tasks. By living in the terminal, it aims to keep developers in their flow state without constantly switching between IDEs, browsers, and chat interfaces.

Claude Code is designed for software engineers, DevOps professionals, and power users who prefer working in the terminal and want to accelerate their development workflow using AI.

• Terminal Native: Operates directly within the command line, integrating seamlessly with existing Unix tools and workflows.
• Contextual Awareness: Automatically reads and understands the structure and logic of the local codebase for accurate modifications.
• Autonomous Execution: Capable of breaking down natural language requests into concrete commands and code edits.
• Git Integration: Handles complex source control workflows, including staging, committing, and resolving merge conflicts.
• Natural Language Interface: Allows developers to instruct the tool using plain English instead of memorizing complex command flags.

Getting started: npm install -g @anthropic-ai/claude-code

1. v2.1.222v2.1.222Aug 4, 202636 downloads

   ## What's changed - Fixed worktree-isolated sessions and their subagents being able to run destructive git commands against the main checkout; isolation now applies to file edits and Bash in every session type - Fixed PreToolUse auto-allow hooks bypassing tool restrictions in background agent tasks (summaries, compaction, renames) - Fixed `/usage-credits` on Team and Enterprise showing "you've already sent a usage credit request" for members whose earlier request was dismissed, blocking them from sending a new one - Fixed the startup connectivity check hanging and then failing behind an HTTPS proxy; it now uses the same proxy-aware transport as API requests and times out with a clear message - Fixed "Connection closed mid-response" errors being reported on responses that had actually completed - Fixed `/usage` overattributing usage to MCP servers: a server's share now reflects only the requests that actually consumed its tool results, instead of every turn after any call to it - Fixed sessions not linking to pull requests created after the branch was pushed, including through the GitHub REST API - Fixed org-restricted `model: opus`-style subagent and teammate family aliases droppi

2. v2.1.221v2.1.221Aug 4, 20261.6K downloads

   ## What's changed - [VSCode] Added Focus view: a chat-menu toggle that hides tool activity behind an expandable per-turn summary with a live running-tool indicator, toggled with `Ctrl+Alt+F` or the "Claude Code: Toggle Focus view" command - Added `mode: "mask"` for sandbox credential files on Linux and WSL — sandboxed commands read a sentinel copy (the whole file, or just the spans captured by an `extract` regex) while the sandbox proxy substitutes the real value on egress; on macOS file masking falls back to `deny` - Added warnings to `claude plugin validate` when a marketplace or plugin name would be rejected by Claude Desktop's managed marketplace sync - Added a `prompt-audit` subcommand to the `claude-api` skill for auditing prompts and tool descriptions for patterns written for older models - Fixed a Bash tool permission-check bypass where zsh could execute hidden commands in `[[ ]]` regex conditionals; affected commands now prompt for permission - Fixed PowerShell permission checks mishandling paths containing quote characters on Windows; such paths now prompt for approval - Fixed the thinking toggle having no effect for the rest of a session that started with thinking off;

3. v2.1.220v2.1.220Jul 25, 202612K downloads

   ## What's changed - Bug fixes and reliability improvements

4. v2.1.219v2.1.219Jul 24, 2026803 downloads

   ## What's changed - Added Claude Opus 5 (`claude-opus-5`), now the default Opus model — 1M context, fast mode at $10/$50 per Mtok - Added `sandbox.network.strictAllowlist` setting to deny non-allowlisted hosts for sandboxed commands without prompting - Added `DirectoryAdded` hook that fires after `/add-dir` or the SDK `register_repo_root` control request registers a new working directory mid-session - Added `mcp_server_errors` to the headless stream-json init event, listing `--mcp-config` entries skipped by config validation; terminal runs print a startup warning - Added the `workflowSizeGuideline` settings key so the advisory Dynamic workflow size guideline can be set from any settings file; the `/config` row is hidden while one does - Added nested subagent forwarding in stream-json: subagents spawned at depth-2+ now appear when `--forward-subagent-text` is set, keyed by their spawning Agent `tool_use` id - Fixed `claude -p` text output dropping the answer already produced when a turn dies on a mid-stream API error - Added HTTP status and error text to `claude mcp list` and `/mcp` when a server fails to connect, and a warning for MCP config values with hidden leading or trailing

5. v2.1.218v2.1.218Jul 22, 20262.8K downloads

   ## What's changed - Changed `/code-review` to run as a background subagent, so review work no longer fills your conversation and keeps stacked slash commands as its review target - Added screen-reader announcements of deleted text for word and line deletions (`Option+Delete`, `Ctrl+W`, `Cmd+Backspace`, `Ctrl+U`, `Ctrl+K`) in `--ax-screen-reader` mode - Fixed Windows paths with `\u`-prefixed segments (like `C:\Users\unicorn`) being corrupted into CJK characters in tool inputs, which made those files inaccessible - Fixed the left arrow key discarding the conversation with no undo: presses right after editing now ask to confirm, and Esc in the agent view returns to the conversation it backgrounded - Added HTTP status and error text to `claude mcp list` and `/mcp` when a server fails to connect, and a warning for MCP config values with hidden leading or trailing whitespace - Fixed multi-line paste collapsing into one line with `j` in place of newlines in terminals that encode pasted newlines as Ctrl+J - Fixed `/context` reporting stale pre-compact token usage after compacting from the message picker - Fixed `/ultrareview` failing on descriptive arguments like "review my auth changes"

• public-apis/public-apis

  A collective list of free APIs

  454.9K stars · Python

• donnemartin/system-design-primer

  Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

  362.2K stars · Python

• practical-tutorials/project-based-learning

  Curated list of project-based tutorials

  277.1K stars · Python

• NousResearch/hermes-agent

  The agent that grows with you

  227K stars · Python

• Significant-Gravitas/AutoGPT

  AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

  186.2K stars · Python

• yt-dlp/yt-dlp

  A feature-rich command-line audio/video downloader

  183K stars · Python