Skip to content
Agents tracked: 492 Releases (7d): 545 Agent status: 1 with issuesSince last limit reset: Claude 9d · Codex 7d For AI agents: Markdown Updated Nov 20, 2026

Claude Code by Anthropic

Anthropic's agentic coding tool that reads a codebase, edits files and runs commands from the terminal, with VS Code and JetBrains integrations plus desktop, web and mobile access. It runs Claude models through a Claude subscription, an Anthropic Console API key or supported third-party cloud providers.

Terminal coding agents Terminal agent + IDE extensionsProprietaryUp Live statusLast limit reset: 9d ago

Use it in: CLI IDE Desktop app Web app Mobile app API / SDK Works with: MCP Own API key Multi-agent Headless / CI

Price
$20/mo
no free tier listed
Popularity
#1 in Terminal
Gid Score 88 / 100 · #1 of 251 ranked AI agents
Trend
Growing
downloads up 15.5% over 30 days · up 15.1% last week
Development
Actively updated
latest 2.1.328, yesterday
Community
156K GitHub stars
VS Code rating 3.7 / 5

Usage data: latest readings Nov 17 to Nov 19, 2026, last checked Nov 19, 06:26 UTC. Date of each number

What Claude Code does

Claude Code is a terminal agent + IDE extensions from Anthropic, first released in February 2025. You use it through a command-line tool, IDE extensions, a desktop app, a web app, mobile apps and an SDK on macOS, Linux and Windows. Its documentation covers MCP servers, subagents or parallel agents, a non-interactive mode for scripts and CI and your own API key. It can run models from Anthropic, Amazon Bedrock and Google. Paid plans start at $20 a month; there is no free tier.

Teams use it for: Building apps, Code review, Security, Workflow automation, Incident response. See examples.

Key facts

MakerAnthropic
TypeTerminal agent + IDE extensions
First releasedFebruary 2025
LicenseProprietary
InterfacesCLI, IDE extension, Desktop, Web, Mobile, SDK
PlatformsmacOS, Linux, Windows
ModelsAnthropic Claude models via Claude plans, a Console API key or supported third-party cloud providers
Bring your own API keyYes
Main languageTypeScript
Open issues and PRs17,095
Open VSX downloads67,828,194 (includes updates)
Homebrew installs61,690 in 30 days · 1,164,631 in a year

Pricing

What each Claude Code plan includes: usage limits →

Limit resets: Anthropic last reset Claude usage limits on Nov 10, 2026 (9d ago), as a reset to apply yourself. 14 resets since Apr 16, 2026, about every 16.0 days. All Claude resets →

Claude Code is included in Pro ($17/month annual or $20/month monthly), Max ($100/month), and Ultra ($200/month) plans. The Free plan does not include Claude Code. Team plans offer standard seats at $20/seat/month annual ($25 monthly) and premium seats at $100/seat/month annual ($125 monthly), both with Claude Code. Enterprise seats cost $20/seat/month annual (20 seat minimum) plus usage at API rates.

Source: official pricing page, checked Nov 19, 2026. Prices change often; confirm before you buy.

Claude Code pricing history since 2024 · Compare prices of all agents

Quick answers

  • Free to start?No
  • Open source?No
  • Bring your own API key?Yes
  • Runs onmacOS, Linux, Windows
  • Where you use itCLI, IDE extension, Desktop, Web, Mobile, SDK
  • Supports MCP?Yes
  • Model providersanthropic, amazon, google
  • Subagents / multi-agent?Yes
  • Runs in scripts / CI?Yes
  • Feature comparisonAll agents
  • Closest alternativeOpenAI Codex · all alternatives

What's new in Claude Code: November 2026 so far

Full monthly summary

November brought expanded auto mode support across cloud platforms, new Code Mode for JavaScript-based tool calling, and improved security and permission handling. The month focused on reliability, cost tracking, and better control over automated behavior.

Action needed: auto mode behavior changed when telemetry or feature flags are disabled: now asks about or denies unchecked server calls instead of falling back to built-in classifier.
  • Code Mode now available as an experimental opt-in for Claude to write JavaScript to call its tools.
  • Auto mode extended to Claude Opus 4.6 and Sonnet 4.6 on Bedrock, Google Cloud Agent Platform, Microsoft Foundry and Claude apps gateway.
  • New permission controls including deny-instead-of-prompting mode and onFailure blocking for hooks to prevent unwanted actions.
  • Claude Fable 5.2 released as default Fable model with 1M context and improved pricing.

10 releases this month · summarised from the official release notes · all months

How teams use Claude Code

All Claude Code use cases · All use cases

Case studyLeague

League halved product cycle times with Claude Code and overnight agent teams

League, which builds member health apps for health plans and providers, rolled Claude out company-wide and moved its engineers to Claude Code. Small pods now ship production code …

Cycle times from idea through pull request cut in half in the four months after the Accelatron, as reported by Anthropic.

Claude CodeClaude EnterpriseClaude PlatformBuilding apps · Code review
Case studyEon

How Eon unified multi-cloud incident tooling behind one MCP Gateway on AgentCore

Eon, a cloud data protection vendor, replaced per-tool credentials and local MCP servers with a single authenticated MCP gateway on Amazon Bedrock AgentCore. Developers and an aut…

As reported by AWS (guest post co-written with Eon): developer onboarding dropped from 2 days to 2 minutes.

Claude CodeCursorOpenAI CodexAmazon Bedrock AgentCoreAgentCore GatewayIncident response · DevOps and CI
Recipe

Turn a Figma frame into code by connecting the Figma MCP server

Figma's hosted MCP server gives a coding agent the variables, components and layout data of a frame you link to, so the code it writes matches the design.

The agent gets design context such as variables, components and layout for the selected frame. (as reported by Figma)

Claude CodeCursorVS CodePrototyping · Building apps
Recipe

Review every pull request with Claude Code in GitHub Actions

A GitHub Actions workflow runs Claude Code whenever a pull request is opened or updated. Claude leaves inline comments on the problems it finds, and anyone can also call it from a…

Claude leaves an inline comment on each issue it finds, or a single summary comment when it finds nothing. (as reported by Anthropic)

Claude CodeCode review · DevOps and CI
Case studySpotify

How Spotify used its Honk background coding agent to open 240 data-pipeline migration PRs

Spotify used Honk, its internal background coding agent built on Claude Code capabilities, to move downstream consumers off two deprecated datasets. The agent opened 240 migration…

As reported by Spotify, the team 'successfully rolled out 240 automated migration PRs using Fleetshift'.

Claude CodeHonkCode migration · Data analysis
ShowcaseAnthropic

16 parallel Claude agents wrote a C compiler that builds the Linux kernel

An Anthropic researcher ran a team of Claude agents in a loop on a shared repository to write a Rust-based C compiler from scratch. The write-up and the code are both public.

Over nearly 2,000 Claude Code sessions and $20,000 in API costs, the agents produced a 100,000-line compiler. (as reported by Anthropic)

Claude CodeBuilding apps · Testing

AgentGid articles about Claude Code

All guides

Get started with Claude Code

npmnpm install -g @anthropic-ai/claude-code
Homebrewbrew install --cask claude-code
VS Codecode --install-extension anthropic.claude-code

These commands use the packages tracked on this page. The vendor may recommend a different installer; see the official documentation.

Claude Code safety and permissions

Compare agents

Out of the boxAsks before file edits and before shell commands, except a built-in set of read-only commands.
Sandboxoptional OS-level Bash sandbox (Seatbelt on macOS, bubblewrap on Linux/WSL2), off by default; turn on with /sandbox or sandbox.enabled. Not available on native Windows.
Approval modesPermission modes: default, acceptEdits, plan, auto (a classifier reviews actions), dontAsk and bypassPermissions (--dangerously-skip-permissions); allow/ask/deny rules in settings; admins can disable bypass and auto.
HooksPreToolUse hooks can block a tool call.

From the official docs · 1 · 2 · 3, checked Oct 9, 2026.

What Claude Code users report right now

All 7 reports, questions and fixes →

Open Users report that Claude Code put the signed-in account's email address into the User-Agent header of web requests it sent to third-party sites, without asking first. Several users report that the built-in email check added in recent versions still lets some of these requests through.

Reported on GitHub · 803 👍

Open Users report that the same workload run headless with `claude -p` (or through the Agent SDK) uses about 1.8 times or more of a subscription's 5-hour usage window than in the interactive terminal, even when token counts match.

Reported on GitHub · 176 👍

Open Request Users ask for a desktop app setting where Enter inserts a new line and Ctrl+Enter (or Cmd+Enter) sends the message. They report that the desktop composer ignores the keybindings file that already allows this in the terminal.

Reported on GitHub · 122 👍

Open Users report that in auto mode Claude Code is instructed to read and edit files through shell commands such as cat, sed and heredocs instead of its own Read, Edit and Write tools, which they say wastes tokens and makes simple edits slower and riskier.

Reported on GitHub · 102 👍

Open Users report that version 2.1.323 removed the subagentStatusLine setting without a replacement, so custom rows that showed each running subagent's context use, cost, model and effort no longer appear. A project member said the removal should have come with a grace period and that work on one had started.

Reported on GitHub · 39 👍

The most discussed problems in its GitHub repository, checked Nov 17, 2026. Written by AgentGid in its own words; statuses and fix versions come from the project's own pages. Reports are users' accounts, not AgentGid tests.

Run Claude Code inside GitHub

All ways to use AI agents in GitHub

Claude Code Action v1.0: Flexible GitHub automation platform with Claude. Auto-detects mode based on event type: PR reviews, @claude mentions, or custom automation. Used in 131 public projects set up for AI coding agents (AgentGid scan).

uses: anthropics/claude-code-action@v1 · keys: anthropic_api_key, claude_code_oauth_token, github_token, ssh_signing_key

Claude Code Base Action: Run Claude Code in GitHub Actions workflows.

uses: anthropics/claude-code-base-action@<version> · keys: anthropic_api_key, claude_code_oauth_token

Claude Code Security Reviewer: AI-powered security review GitHub Action using Claude to analyze code changes for security vulnerabilities.

uses: anthropics/claude-code-security-review@<version> · keys: claude-api-key

Add the key in Settings → Secrets and variables → Actions, then add a workflow file with the line above. The model is paid through your own key; GitHub Actions minutes are free in public repositories.

Add-ons for Claude Code: save tokens, add memory and tools

All agent tooling

Listed because each tool documents support for Claude Code. Savings and results depend on your workload.

Claude Code supports Agent Skills. Add ready-made skills for code review, slides, design, marketing and more: browse the Agent Skills catalog, with install commands for Claude Code.

Compare Claude Code with another agent

vs
# Agent Gid Score Downloads 7d 7d 30d Stars Latest release Price
2 84 26.6M up 2.4% up 7.4% 136K+144/day 0.168.07d ago Free + $8/mo
3
OpenCodeAnomaly (SST team)
80 3.9M up 15.4% up 28.7% 228K+266/day 2.3.22d ago Free + $10/mo
7
PiEarendil Inc. (created by Mario Zechner)
73 6.4M up 1.6% up 36.3% 123K+193/day 1.5.210d ago Free (OSS)
15 62 495K up 16.9% up 6.8% 109K+35/day 0.69.0yesterday API usage or license
20
ClineCline Bot Inc.
58 84.3K down 8.7% up 14.9% 71.8K+38/day 4.1.2625d ago Free + $9.99/mo
22
GitHub Copilot CLIGitHub (Microsoft)
56 1.7M down 8.3% up 8.3% 11.4K+6/day 1.0.1142d ago Free + $10/mo

Head to head: Claude Code vs OpenAI Codex · Claude Code vs Cursor · Claude Code vs GitHub Copilot · Claude Code vs OpenCode · Claude Code vs Gemini CLI · Claude Code vs Aider · Claude Code vs Antigravity CLI · Claude Code vs GitHub Copilot CLI · Claude Code vs Devin Desktop · Claude Code vs Google Antigravity · Claude Code vs Kiro · Claude Code vs Devin · Claude Code vs Pi · Claude Code vs mini-SWE-agent

Tools in projects built with Claude Code

All tools

Most used libraries and frameworks in 3,264 public GitHub repos set up for Claude Code, from their dependency files.

  1. TypeScript57.8%
  2. ESLint37.3%
  3. Tailwind CSS33.2%
  4. React32.8%
  5. Zod26.5%
  6. Vitest26.2%
  7. Vite22.6%
  8. Prettier22.5%
  9. Playwright (JavaScript)21.3%
  10. Lucide React20.1%

Used far more often here than in AI-built projects overall: what sets Claude Code projects apart.

  1. oxfmt4.3% · 1.7×
  2. oxlint5.1% · 1.6×
  3. Anthropic SDK5.8% · 1.5×
  4. yaml5.0% · 1.5×

What developers connect to Claude Code

Real-world stacks

MCP servers in 2,964 public GitHub repos that configure Claude Code, updated weekly.

  1. Context717.3%
  2. Playwright MCP15.0%
  3. Chrome DevTools MCP6.4%
  4. Supabase6.2%
  5. GitHub MCP6.1%
  6. GitHub MCP (legacy)6.1%
  7. Filesystem5.8%
  8. Sequential Thinking5.8%
  9. shadcn/ui5.5%
  10. Memory (knowledge graph)4.1%

Ratings from people who use Claude Code

No ratings yet. Used Claude Code? Rate it and say what it is good and bad at.

Claude Code news

All AI agent news

  1. Incident Status page

    Claude Code: Elevated errors for Claude Mythos 5.2 and Claude Fable 5.2

    Major impact; resolved after 22 min.

  2. Release GitHub Releases

    Claude Code 2.1.328 released

    Added auto mode for Claude Opus 4.6 and Sonnet 4.6 on Amazon Bedrock, Google Cloud's Agent Platform, Microsoft Foundry and Claude apps gateway; interactive sessions with no permission mode start in it; Added "onFailure": "block" for mcp_tool hooks, as for…

  3. Release GitHub Releases

    Claude Code 2.1.327 released

    Added a confirmation before /install-github-app changes a repository; Added claude mcp add-json - to read the server's JSON from stdin, so tokens can stay off the command line; not available inside a Claude Code session; Added a line when a resumed session's…

  4. Hacker NewsHot claude.dev

    How the Claude Code team thinks about verification

    Claude Code team discusses their approach to verification.

  5. Incident Status page

    Claude Code: Elevated errors for Claude Sonnet 5.5 and Claude Fable 5.2

    Major impact; resolved after 1 h 14 min.

  6. Hacker News claude.com

    Anthropic upgrades Claude Code Projects to run parallel AI workers

    Anthropic upgraded Claude Code Projects to support parallel AI workers that can operate independently.

  7. Incident Status page

    Claude Code: Elevated errors on claude.ai, the Claude API, and Claude Code

    Major impact; resolved after 2 h 28 min.

  8. Hacker NewsHot status.claude.com

    Elevated errors on claude.ai, Claude Code, and platform.claude.com

    Claude.ai, Claude Code, and platform.claude.com experienced elevated error rates.

What changed: recent Claude Code releases

72 stable releases in the last 90 days · Monthly summary · Full changelog

2.1.328
  • Added auto mode for Claude Opus 4.6 and Sonnet 4.6 on Amazon Bedrock, Google Cloud's Agent Platform, Microsoft Foundry and Claude apps gateway; interactive sessions with no permission mode start in it
  • Added "onFailure": "block" for mcp_tool hooks, as for command and HTTP hooks: a hook whose call fails blocks the action
  • Added a warning when a message from a session that skips permission prompts may be held and dropped by a cloud session
  • Added a notice in /status and claude doctor when an OpenTelemetry exporter has no endpoint and its data would likely be lost
  • Added CLAUDE_CODE_DISABLE_DEFERRED_TOOL_RESUME, which lets a host stop claude -p --resume and --continue from running a tool call that a hook deferred
  • Added support for apps that embed Claude Code to switch on the policy plugin's allowManagedModsOnly option; an admin's managed settings still win
2.1.327
  • Added a confirmation before /install-github-app changes a repository
  • Added claude mcp add-json <name> - to read the server's JSON from stdin, so tokens can stay off the command line; not available inside a Claude Code session
  • Added a line when a resumed session's earlier messages can't be loaded
  • Added a list in /status of broken agent, skill, command and output style files, keybinding errors, an unavailable sandbox, ignored permission settings and hook matchers that never match
  • Added a note in /config when other settings override a row
  • Added x-claude-code-managed-settings-checksum to the gateway hint headers; sent where managed settings set CLAUDE_CODE_GATEWAY_HINT_HEADERS=1, including where they already do
Earlier releases
2.1.326
  • Added support for turning on Code Mode while agent teams are enabled; if you already turned it on, sessions with teams on now start in Code Mode
  • Added a startup warning when an --allowedTools, --disallowedTools or --tools value has an entry that doesn't look like a complete rule
  • Added a message explaining why MCP servers stop loading when an administrator adds managed-mcp.json during a session
  • Added a row to /status that says when your provider or an environment variable such as DISABLE_TELEMETRY turns features off
  • Added a note in /plugin and claude plugin list when a malformed plugin.json field such as author or homepage is ignored
  • Added Ctrl+O to show hidden startup notices
2.1.325
  • Fixed a security issue in how zstd-compressed responses are decoded
  • Added a spinner tip in VS Code and similar integrated terminals about re-running a notebook cell, shown once Claude has read or edited a Jupyter notebook
  • Added a line under the error shown when your organization's policy blocks a request, saying how to continue: run /rewind and change the message, or run /clear
  • Added a note for Claude when a sandboxed git checkout, git stash or autostash pull cannot update protected files such as those in .claude
  • Fixed /security-review and skills' inline git commands stopping with an error in worktrees of bare repositories, --separate-git-dir checkouts and Android repo checkouts
  • Fixed subagents with their own model being moved to the plan-mode model when the model setting is opusplan or haiku
2.1.323
  • Added Code Mode, an experimental opt-in in which Claude writes JavaScript to call its tools; see to turn it on, or to turn it off for an organization
  • Added engines["claude-code"] to plugin.json: plugins outside their stated Claude Code version range are not installed, updated or loaded, and install and update pick the newest version that fits
  • Added type checking of a plugin's TypeScript hooks module to claude plugin validate; each finding is a warning, and --strict fails on it
  • Added to claude plugin validate the $ nouns a mod's engine.create hook adds, withholds or replaces
  • Added support for CLAUDE_CODE_AUTO_MODE_MODEL in managed settings for Claude Desktop sessions on third-party providers (takes effect once Claude Desktop includes this version)
  • Added an options menu (stop, switch to usage credits, upgrade) when a model needs usage credits that are turned off or used up
2.1.322
  • Added fast mode on Vertex in the global, us and eu regions, falling back to standard speed if Vertex refuses it

Claude Code prices over time

Full pricing history →

Claude Code plan pricesfrom archived copies of the official pricing page
Cheapest paid planMost expensive self-serve plan
Token prices of Anthropic modelsnewest Anthropic model in each family, output price per 1M tokens
Anthropic OpusAnthropic SonnetAnthropic Haiku

Claude Code usage limit resets over time

All resets, timeline and your own timer →

Claude limit resets per monthannounced by @ClaudeDevs

Anthropic sometimes resets the 5-hour and weekly limits of Claude early, after a bug, an outage or a launch, and announces it on X.

Last resetNov 10, 2026 (9d ago), to apply yourself
Average gap16.0 days, longest 49.2
This waitlonger than 54% of past gaps
Resets so far14 since Apr 16, 2026

Gave a free full reset across all models and limits, usable from Settings > Usage until December 10 at 2:00PM PT, after fixed issues used more limits than intended. Post on X

Claude Code popularity and usage data

Claude Code was downloaded 18.9M times from npm in the week ending Nov 17, 2026, up 15.1% on the week before and up 15.5% over the last 30 days compared with the 30 before. Its VS Code extension has 30.6M installs and average 3.7 out of 5 across 936 marketplace ratings. The GitHub repository has 156K stars, 4,251 of them added in the last 30 days. The latest stable release is 2.1.328, published Nov 19, 2026; there were 19 stable releases in the past 30 days. On public GitHub, 798,602 pull requests were opened from branches with Claude Code's default claude/ prefix in the week of Nov 9, 2026, and 95% of the pull requests from the four weeks before that were merged. On Terminal-Bench 4.1 its best listed result is 65.8% with Opus 5.5, ranking 3 of 7 agents on that board. It was mentioned in 1,889 Hacker News posts and comments over the last 30 days.

Downloads per daynpm, 7-day average 2.7M/day
GitHub starsrunning total 156K
VS Code installsVisual Studio Marketplace, daily snapshots 30.6M
Hacker News mentionsposts and comments, rolling 7-day total 318 this week
Pull requests opened per weekpublic GitHub repositories 799K/week

Download the raw daily series: claude-code.csv

Gid Score breakdown

Adoption96
Community92
Attention93
Momentum58

Gid Score shows public popularity and activity (usage, GitHub stars, mentions, growth), not the quality of the product. Each component is scored 0 to 100 from public signals; a dash means no data for it. How the Gid Score works.

How fresh these numbers are

NumberLatest readingLast checked
Package downloadsNov 17, 2026Nov 19, 06:17 UTC
GitHub starsNov 19, 2026Nov 19, 06:26 UTC
VS Code installsNov 19, 2026Nov 19, 06:26 UTC
Open VSX downloadsNov 19, 2026Nov 19, 06:26 UTC
Homebrew installsNov 19, 2026Nov 19, 06:26 UTC
Hacker News mentionsNov 18, 2026Nov 19, 06:26 UTC

We fetch every source once a day. Registries publish downloads and page views a day or two late, so their latest reading trails the check. A reading more than 4 days old is marked out of date; the Gid Score still uses it until a newer one arrives.

Claude Code benchmark results

All agents on Terminal-Bench

BenchmarkModelEffortTasks solvedCost of runPlace
Terminal-Bench 4.1 Opus 5.5 max 65.8% ± 3.1 $4,719 #3 of 7
Fable 5.2 max 65.8% ± 2.9 $16,493
Sonnet 5.5 max 63.9% ± 3.0 $7,334
Kimi K3.1 Pro max 59.7% ± 4.2 $1,087
Terminal-Bench 4.0 Opus 5.5 max 64.8% ± 3.1 $4,719 #2 of 6
Sonnet 5.5 max 61.8% ± 2.9 $7,334
Kimi K3.1 Pro max 60.9% ± 4.1 $1,087
Fable 5.1 max 57.9% ± 3.8 $6,244
Terminal-Bench 3.0 Fable 5 max 34.0% ± 3.4 $6,481 #3 of 6
GLM 5.3 max 32.4% ± 2.9 $1,771
Opus 4.8 max 21.1% ± 3.0 $5,214
Sonnet 5 max 14.6% ± 2.9 $6,891
Terminal-Bench 2.1 Fable 5 xhigh 83.8% ± 2.3 $553 #2 of 6
Opus 4.8 high 78.9% ± 2.6 $287
Sonnet 5 high 74.6% ± 3.2 $288
Opus 4.7 max 68.9% ± 2.8 $600
Terminal-Bench 2.0 Claude Opus 4.6 · v2.1.34 — 58.0% ± 2.9 — #31 of 43
Claude Opus 4.5 · v2.0.72 — 52.1% ± 2.5 —
Claude Sonnet 4.5 · v2.0.31 — 40.1% ± 2.9 —
Claude Opus 4.1 · v2.0.31 — 34.8% ± 2.9 —

Up to four best runs per board. Scores are not comparable between Terminal-Bench versions. Source: Terminal-Bench (tbench.ai).

Pull requests by Claude Code on GitHub

Compare all coding agents

In the week of Nov 9, 2026, 798,602 pull requests matching Claude Code's signature (head:claude/) were opened in public repositories; 95% of those opened in the four weeks before were merged. A branch prefix identifies the tool; the pull request itself is usually opened under the developer's own account.

Reliability

From the vendor's public status page · now: All systems operational

15 incidents reported in the last 30 days, 11 of them major or critical, 17.6 hours in total from report to resolution.

Incidents per monthfrom the official status page

Each bar is one month; the last one is the month so far. Vendors post even short slowdowns, so read this as how often something was reported, not as downtime. Compare with other agents →

Nov 19, 2026, 09:10 UTCElevated errors for Claude Mythos 5.2 and Claude Fable 5.2 · major
Nov 16, 2026, 07:49 UTCElevated errors for Claude Sonnet 5.5 and Claude Fable 5.2 · major
Nov 13, 2026, 13:09 UTCElevated errors on claude.ai, the Claude API, and Claude Code · major
Nov 13, 2026, 09:58 UTCElevated errors on claude.ai, Claude Code, and platform.claude.com · major
Nov 8, 2026, 08:28 UTCDegraded performance for Claude Fable 5.1 · minor
Oct 28, 2026, 16:19 UTCElevated errors affecting the Google Calendar connector · minor

Claude Code FAQ

How much does Claude Code cost?

Claude Code is included in Pro ($17/month annual or $20/month monthly), Max ($100/month), and Ultra ($200/month) plans. The Free plan does not include Claude Code. Team plans offer standard seats at $20/seat/month annual ($25 monthly) and premium seats at $100/seat/month annual ($125 monthly), both with Claude Code. Enterprise seats cost $20/seat/month annual (20 seat minimum) plus usage at API rates.

Is Claude Code open source?

No. Claude Code is a proprietary product from Anthropic.

How popular is Claude Code?

Claude Code was downloaded 18.9M times from npm in the week ending Nov 17, 2026, up 15.1% on the week before and up 15.5% over the last 30 days compared with the 30 before. Its VS Code extension has 30.6M installs and average 3.7 out of 5 across 936 marketplace ratings. The GitHub repository has 156K stars, 4,251 of them added in the last 30 days.

What is the latest version of Claude Code?

The latest stable release we track is 2.1.328, published on Nov 19, 2026.

What are the alternatives to Claude Code?

The closest alternatives in the same category by Gid Score are OpenAI Codex, OpenCode, Pi, Gemini CLI.

When did Anthropic last reset Claude usage limits?

On Nov 10, 2026 (UTC): Gave a free full reset across all models and limits, usable from Settings > Usage until December 10 at 2:00PM PT, after fixed issues used more limits than intended. Source: https://x.com/ClaudeDevs/status/2120275296637321476 14 resets since Apr 16, 2026, on average every 16.0 days.

For the makers of Claude Code badges, corrections

Add a live badge to your README or site:

AgentGid: #1 in Terminal Gid Score: 88/100 downloads: 18.9M/week ▲16% 30d status: operational

[![AgentGid: #1 in Terminal](https://agentgid.com/badges/claude-code-rank.svg)](https://agentgid.com/agents/claude-code/)
[![Gid Score: 88/100](https://agentgid.com/badges/claude-code-score.svg)](https://agentgid.com/agents/claude-code/)
[![downloads: 18.9M/week ▲16% 30d](https://agentgid.com/badges/claude-code-downloads.svg)](https://agentgid.com/agents/claude-code/)
[![status: operational](https://agentgid.com/badges/claude-code-status.svg)](https://agentgid.com/agents/claude-code/)

Something wrong or outdated on this page? Send a correction with a link to the official source. More for makers.

Where these numbers come from

npm: @anthropic-ai/claude-code. GitHub: anthropics/claude-code. VS Code Marketplace: anthropic.claude-code. Homebrew: claude-code. See data sources for how each one is collected.

Product facts and pricing were checked against: claude.com, code.claude.com, registry.npmjs.org, formulae.brew.sh, marketplace.visualstudio.com, open-vsx.org, github.com, en.wikipedia.org.