anthropics/claude-codePublic

What is claude-code?

Agentic coding tool by Anthropic that executes complex software engineering tasks directly in your terminal.

What does claude-code do?

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

Who is claude-code for?

Software engineers and DevOps professionals looking to drastically reduce boilerplate work and navigate complex codebases faster. It acts as a highly capable, autonomous pair programmer that lives where developers already work.

How do I get started with claude-code?

curl -fsSL https://claude.ai/install.sh | bash

How popular is claude-code on GitHub?

anthropics/claude-code has 149,399 stars and 25,482 forks on GitHub, and gained 1,054 stars in the last 7 days.

• Landmark project

  149,399 stars

• Very active

  562 commits in 52 weeks

• Continuous integration

  Automated checks passing

• Repeat trending

  45 trending appearances

• Top 10% tracked

  Rank 37 of 1135

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

Software engineers and DevOps professionals looking to drastically reduce boilerplate work and navigate complex codebases faster. It acts as a highly capable, autonomous pair programmer that lives where developers already work.

• Terminal Integration: Operates entirely within the command line, providing a natural language interface to the underlying OS.
• Agentic Execution: Capable of autonomously breaking down and executing complex, multi-step software engineering tasks.
• Codebase Context: Deeply indexes and understands the local repository to ensure all generated code is relevant and accurate.
• Git Workflow Automation: Handles staging, committing, branching, and PR generation directly from simple conversational prompts.
• Plugin Ecosystem: Supports custom extensions and specialized agents to tailor the tool's capabilities to specific organizational needs.
• Iterative Debugging: Analyzes error logs, proposes fixes, and safely executes test suites to resolve complex application bugs.

Getting started: curl -fsSL https://claude.ai/install.sh | bash

1. v2.1.285v2.1.285Sep 29, 20268.1K downloads

   ## What's changed - Added `CLAUDE_CODE_DISABLE_WEB_FETCH` environment variable to turn off the WebFetch tool - Added `claude --desktop` to open the Claude desktop app on the current directory, or on a session with `--continue` / `--resume <id>` - Added `claude plugin configure <plugin>` to show a plugin's options and which are unset, or save new values read from stdin with `--values-stdin` - Added `<server>.<key>=<value>` to `claude plugin install --config`, so a bundled `.mcpb` MCP server's own settings can be set at install time and it starts without visiting `/plugin` → Configure - Added `allowedProviders` managed setting to limit which API providers a machine may use (Anthropic API, a custom endpoint, Bedrock, Mantle, Vertex AI, Foundry, Claude Platform on AWS, or a Cloud gateway) - Added `CLAUDE_CODE_NONSTREAMING_TIMEOUT_RETRIES` environment variable to cap re-sends of a non-streaming fallback request that timed out - Fixed `claude -p` with `CLAUDE_CODE_FORK_SUBAGENT=1`: a subagent's own Agent call now runs in the foreground, so the subagent gets the child's result - Fixed plugin and marketplace installs and updates over SSH ignoring the ssh program set in `GIT_SSH` or in you

2. v2.1.284v2.1.284Sep 28, 202616.2K downloads

   ## What's changed - Added Claude Sonnet 5.5 (`claude-sonnet-5-5`), now the default Sonnet model on the Anthropic API — 1M context, $2/$10 per Mtok with $0.20/Mtok cache reads - Added a "Yes, but ask again next time" answer to auto mode's prompt before a read outside the working directories, so you can allow that one read and still be asked about later ones - Added dollar amounts to the Claude apps gateway spend limit in `/usage` and the status line (for example "$271.40 / $500.00 spent this month") when the gateway runs this version or later; the status line's `rate_limits.spend_limit` also gains `used_usd`, `limit_usd` and `period` - Added `effortSlider:decreaseEffort`, `increaseEffort` and `toggleUltracode` keybinding actions, so the `/effort` slider's arrow and Tab keys can be rebound in `keybindings.json` - Added `/rate-limit-options` to `/help` and the command menu for claude.ai subscribers, so the usage-limit notices that mention it point to a command you can find - Added `/mcp reconnect all` in the interactive terminal to retry every MCP server that failed to connect or needs authentication at once - Added Claude apps gateway startup warnings when a managed policy's `availa

3. v2.1.283v2.1.283Sep 25, 202635.6K downloads

   ## What's changed - Added `x-claude-code-prompt-id` to the gateway hint headers so LLM gateways can group the requests that serve one user prompt; opt in with `CLAUDE_CODE_GATEWAY_HINT_HEADERS=1` - Added `availableModelsMatch` managed setting: with `"exact"`, an `availableModels` entry allows only the model version it names, so new releases stay blocked until listed - Added `deniedModels` managed setting to block specific models, even when `availableModels` allows them - Added MCP tool, WebFetch and WebSearch outputs to the `tool.output` OpenTelemetry span event when `OTEL_LOG_TOOL_CONTENT=1` - Added `/doctor prompt-audit` (also `/checkup prompt-audit`) to audit your CLAUDE.md files, skills, agents and commands for prompting patterns written for older models - Added click-to-expand for truncated messages from your other sessions in fullscreen mode - Added `path` to `--plugin-dir` load-failure entries in the stream-json `system/init` `plugin_errors`, naming the directory that did not load - Added an opt-in `load_test_mode` block to the Claude apps gateway config: requests are built and signed but not sent upstream, and clients get a canned reply, so a deployment can be load tested

4. v2.1.282v2.1.282Sep 24, 202616.2K downloads

   ## What's changed - Added a `maxProseWidth` setting that caps the width of Claude's prose in wide terminals while tables and code blocks keep the full width - Added a startup notice, and `/status` and `claude doctor` entries, listing telemetry variables in a project's settings files that were ignored or that turned telemetry off - Added the `allowClaudeInChromeWithManagedMcp` managed setting to let `claude --chrome` run alongside an exclusive `managed-mcp.json`; the error shown when Chrome is blocked now names it - Added `store.readiness_grace_seconds` to the Claude apps gateway so `/readyz` can stay ready through a short Postgres outage such as a database failover - Added a scrollbar to the `/feedback` drafts list in fullscreen mode; it appears while the mouse is over the list - Fixed every request failing with a 400 error in conversations whose history holds web search results the API cannot decrypt (for example, from a turn answered through a third-party gateway) - Fixed more cases of continued or resumed sessions (`--continue`, `--resume`) re-sending earlier messages in a changed form, which could make the API drop Claude's earlier reasoning - Fixed earlier extended thinking b

5. v2.1.281v2.1.281Sep 23, 202616.4K downloads

   ## What's changed - Added Claude apps gateway support for newer Claude Desktop keys in `desktop` policy blocks, including `blockReadsOutsideWorkingDirectories` and `disableBypassPermissionsMode` - Added `assume_role` on Claude apps gateway Bedrock upstreams: the gateway calls Bedrock as an IAM role it assumes through STS, in another AWS account if needed, optionally one session per developer - Added `guardrail: {id, version}` on Claude apps gateway Bedrock upstreams to apply an Amazon Bedrock guardrail to every request sent through them (set it on all Bedrock upstreams or none) - Added `telemetry.resource_attributes` to the Claude apps gateway config, to put fixed labels on the telemetry of Claude Desktop and `/login` sessions - Added `"attribution": false` in `settings.json` to hide all commit and PR attribution; older CLI versions skip a settings file that holds it, so keep the object form in files shared across versions - Added MCP URL-mode elicitation on 2026-07-28 protocol connections, so servers can ask Claude Code to open a browser-based flow; no waiting dialog is left on screen when the server has no way to confirm completion - Added MCP server checks to `claude plugin val

• freeCodeCamp/freeCodeCamp

  freeCodeCamp.org's open-source codebase and curriculum. Learn math, programming, and computer science for free.

  456.7K stars · TypeScript

• openclaw/openclaw

  The AI that really does things. Any OS. Any Platform. The lobster way. 🦞

  391.3K stars · TypeScript

• anomalyco/opencode

  The open source coding agent.

  211.7K stars · TypeScript

• n8n-io/n8n

  Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

  206.7K stars · TypeScript

• microsoft/vscode

  Visual Studio Code

  193.5K stars · TypeScript

• firecrawl/firecrawl

  Supercharge your AI agents with data from the web and beyond. Building the library for superintelligence. 🔥

  188.6K stars · TypeScript