ModelCompare
Compare

AI coding agent usage

What was the most used AI coding agent on ?

Claude Code from Anthropic, with a usage score of 49 out of 100 across 3 of 3 sources. Gemini CLI was next at 35.

Usage score over time, week by week

Usage ranking

AI coding agents by usage on October 21, 2025

This ranks how much each agent is used and followed, not how good it is: a popular agent can be a worse fit for your work than a small one. Click an agent to see where its numbers come from. Each source's column shows the agent's scaled score (the leader is 100) over the raw number. 3 sources had data on this day. The score averages an agent's scaled values over the sources that can measure it (at least three).

  1. 1
    Claude Code
    Anthropic · closed source
    Usage score 49
    • npm 100 · 6.1M
    • GitHub 46 · 35k
    • VS Code 2 · 1M
    • npm: 1006,062,178 downloads of @anthropic-ai/claude-code in the 7 days to Oct 21, 2025. That's the most of any agent in this source, so it scores 100. Source
    • GitHub: 4635,408 stars on github.com/anthropics/claude-code on Oct 3, 2025. The leader here is Gemini CLI with 78k, so Claude Code scores 35k ÷ 78k × 100 = 46. Source
    • VS Code: 21,030,795 installs of the anthropic.claude-code extension on Oct 6, 2025. The leader here is GitHub Copilot with 43M, so Claude Code scores 1M ÷ 43M × 100 = 2. Source

    Usage score: (100 + 46 + 2) ÷ 3 = 49. Claude Code website

  2. 2
    Gemini CLI
    Google · open source
    Usage score 35
    • npm 4 · 235k
    • GitHub 100 · 78k
    • VS Code 0 · 184k
    • npm: 4235,089 downloads of @google/gemini-cli in the 7 days to Oct 21, 2025. The leader here is Claude Code with 6.1M, so Gemini CLI scores 235k ÷ 6.1M × 100 = 4. Source
    • GitHub: 10077,576 stars on github.com/google-gemini/gemini-cli on Oct 1, 2025. That's the most of any agent in this source, so it scores 100. Source
    • VS Code: 0184,450 installs of the Google.gemini-cli-vscode-ide-companion extension on Oct 5, 2025. The leader here is GitHub Copilot with 43M, so Gemini CLI scores 184k ÷ 43M × 100 = 0. Source

    Usage score: (4 + 100 + 0) ÷ 3 = 35. Gemini CLI website

  3. 3
    GitHub Copilot
    GitHub · closed source
    Usage score 34
    • npm 1 · 78k
    • VS Code 100 · 43M
    • npm: 178,211 downloads of @github/copilot in the 7 days to Oct 21, 2025. The leader here is Claude Code with 6.1M, so GitHub Copilot scores 78k ÷ 6.1M × 100 = 1. Source
    • VS Code: 10043,410,767 installs of the GitHub.copilot-chat extension on Oct 4, 2025. That's the most of any agent in this source, so it scores 100. Source

    Not counted: GitHub, because it has no public GitHub repo.

    Usage score: (1 + 100) ÷ 3 = 34, divided by 3 rather than 2 because every agent's average counts at least 3 sources. GitHub Copilot website

  4. 4
    Cline
    Cline · open source
    Usage score 24
    • npm 0 · 23k
    • GitHub 66 · 51k
    • VS Code 5 · 2.3M
    • npm: 022,650 downloads of cline in the 7 days to Oct 21, 2025. The leader here is Claude Code with 6.1M, so Cline scores 23k ÷ 6.1M × 100 = 0. Source
    • GitHub: 6650,972 stars on github.com/cline/cline on Oct 1, 2025. The leader here is Gemini CLI with 78k, so Cline scores 51k ÷ 78k × 100 = 66. Source
    • VS Code: 52,345,153 installs of the saoudrizwan.claude-dev extension on Oct 1, 2025. The leader here is GitHub Copilot with 43M, so Cline scores 2.3M ÷ 43M × 100 = 5. Source

    Usage score: (0 + 66 + 5) ÷ 3 = 24. Cline website

  5. 5
    Codex CLI
    OpenAI · open source
    Usage score 22
    • npm 3 · 207k
    • GitHub 59 · 46k
    • VS Code 3 · 1.1M
    • npm: 3207,022 downloads of @openai/codex in the 7 days to Oct 21, 2025. The leader here is Claude Code with 6.1M, so Codex CLI scores 207k ÷ 6.1M × 100 = 3. Source
    • GitHub: 5945,626 stars on github.com/openai/codex on Oct 2, 2025. The leader here is Gemini CLI with 78k, so Codex CLI scores 46k ÷ 78k × 100 = 59. Source
    • VS Code: 31,133,275 installs of the openai.chatgpt extension on Oct 4, 2025. The leader here is GitHub Copilot with 43M, so Codex CLI scores 1.1M ÷ 43M × 100 = 3. Source

    Usage score: (3 + 59 + 3) ÷ 3 = 22. Codex CLI website

  6. 6
    Roo Code
    Roo Code · open source
    Usage score 9
    • GitHub 26 · 20k
    • VS Code 2 · 913k
    • GitHub: 2620,016 stars on github.com/RooCodeInc/Roo-Code on Oct 2, 2025. The leader here is Gemini CLI with 78k, so Roo Code scores 20k ÷ 78k × 100 = 26. Source
    • VS Code: 2912,733 installs of the RooVeterinaryInc.roo-cline extension on Oct 12, 2025. The leader here is GitHub Copilot with 43M, so Roo Code scores 913k ÷ 43M × 100 = 2. Source

    Not counted: npm, because it has no command-line package on npm.

    Usage score: (26 + 2) ÷ 3 = 9, divided by 3 rather than 2 because every agent's average counts at least 3 sources. Roo Code website

  7. 7
    Qwen Code
    Alibaba · open source
    Usage score 6
    • npm 1 · 89k
    • GitHub 18 · 14k
    • npm: 188,963 downloads of @qwen-code/qwen-code in the 7 days to Oct 21, 2025. The leader here is Claude Code with 6.1M, so Qwen Code scores 89k ÷ 6.1M × 100 = 1. Source
    • GitHub: 1813,868 stars on github.com/QwenLM/qwen-code on Oct 4, 2025. The leader here is Gemini CLI with 78k, so Qwen Code scores 14k ÷ 78k × 100 = 18. Source

    Not counted: VS Code, because it has no VS Code extension.

    Usage score: (1 + 18) ÷ 3 = 6, divided by 3 rather than 2 because every agent's average counts at least 3 sources. Qwen Code website

  8. 8
    Crush
    Charm · open source
    Usage score 6
    • npm 0 · 1.8k
    • GitHub 17 · 14k
    • npm: 01,817 downloads of @charmland/crush in the 7 days to Oct 21, 2025. The leader here is Claude Code with 6.1M, so Crush scores 1.8k ÷ 6.1M × 100 = 0. Source
    • GitHub: 1713,550 stars on github.com/charmbracelet/crush on Oct 4, 2025. The leader here is Gemini CLI with 78k, so Crush scores 14k ÷ 78k × 100 = 17. Source

    Not counted: VS Code, because it has no VS Code extension.

    Usage score: (0 + 17) ÷ 3 = 6, divided by 3 rather than 2 because every agent's average counts at least 3 sources. Crush website

  9. 9
    Kilo Code
    Kilo · open source
    Usage score 5
    • npm 0 · 692
    • GitHub 14 · 11k
    • VS Code 1 · 366k
    • npm: 0692 downloads of @kilocode/cli in the 7 days to Oct 21, 2025. The leader here is Claude Code with 6.1M, so Kilo Code scores 692 ÷ 6.1M × 100 = 0. Source
    • GitHub: 1410,656 stars on github.com/Kilo-Org/kilocode on Oct 1, 2025. The leader here is Gemini CLI with 78k, so Kilo Code scores 11k ÷ 78k × 100 = 14. Source
    • VS Code: 1366,405 installs of the kilocode.Kilo-Code extension on Oct 3, 2025. The leader here is GitHub Copilot with 43M, so Kilo Code scores 366k ÷ 43M × 100 = 1. Source

    Usage score: (0 + 14 + 1) ÷ 3 = 5. Kilo Code website

  10. 10
    Auggie
    Augment Code · closed source
    Usage score 1
    • npm 0 · 17k
    • VS Code 1 · 586k
    • npm: 016,587 downloads of @augmentcode/auggie in the 7 days to Oct 21, 2025. The leader here is Claude Code with 6.1M, so Auggie scores 17k ÷ 6.1M × 100 = 0. Source
    • VS Code: 1586,020 installs of the augment.vscode-augment extension on Oct 18, 2025. The leader here is GitHub Copilot with 43M, so Auggie scores 586k ÷ 43M × 100 = 1. Source

    Not counted: GitHub, because it has no public GitHub repo.

    Usage score: (0 + 1) ÷ 3 = 1, divided by 3 rather than 2 because every agent's average counts at least 3 sources. Auggie website

  11. 11
    Amp
    Sourcegraph · closed source
    Usage score 0
    • npm 0 · 30k
    • VS Code 0 · 39k
    • npm: 030,306 downloads of @sourcegraph/amp in the 7 days to Oct 21, 2025. The leader here is Claude Code with 6.1M, so Amp scores 30k ÷ 6.1M × 100 = 0. Source
    • VS Code: 038,707 installs of the sourcegraph.amp extension on Sep 15, 2025. The leader here is GitHub Copilot with 43M, so Amp scores 39k ÷ 43M × 100 = 0. Source

    Not counted: GitHub, because it has no public GitHub repo.

    Usage score: (0 + 0) ÷ 3 = 0, divided by 3 rather than 2 because every agent's average counts at least 3 sources. Amp website

  12. 12
    pi
    Mario Zechner · open source
    Usage score 0
    • npm 0 · 0
    • GitHub 0 · 8
    • npm: 00 downloads of @mariozechner/pi-coding-agent in the 7 days to Oct 21, 2025. The leader here is Claude Code with 6.1M, so pi scores 0 ÷ 6.1M × 100 = 0. Source
    • GitHub: 08 stars on github.com/badlogic/pi-mono on Sep 20, 2025. The leader here is Gemini CLI with 78k, so pi scores 8 ÷ 78k × 100 = 0. Source

    Not counted: VS Code, because it has no VS Code extension.

    Usage score: (0 + 0) ÷ 3 = 0, divided by 3 rather than 2 because every agent's average counts at least 3 sources. pi website

Not ranked that day, only one source has them: Aider (GitHub, 38k), OpenCode (npm, 52k), Droid (npm, 16).

Method

How the usage score is made

No single public number measures how much each AI coding agent is used, so we blend the ones that exist. In each source the leader scores 100 and the rest are scaled to it. An agent's score is the average over the sources that can measure it. Sources that can't see an agent at all (Cursor has no npm package) are left out of its average, but the average always counts at least three sources, so an agent seen by only one or two can't outrank one that leads everywhere. An agent needs two sources to be ranked.

  • npmCLI downloads, 7 days · data from Oct 21, 2025

    Downloads of each agent's command-line package in the 7 days to the date, with one-off bursts (mirrors, bots) capped. Downloads count installs and CI runs, not people, and agents with their own installer are undercounted. Source

  • GitHubStars · data from Oct 4, 2025

    Stars on the agent's GitHub repo, from monthly snapshots. Stars measure interest, and build up over time. Source

  • VS CodeExtension installs, all time · data from Oct 18, 2025

    All-time installs of the agent's VS Code extension, from monthly snapshots. Cursor and Windsurf install from Open VSX instead, which isn't counted. Source

Browse

The most used AI coding agent, month by month

2026
2025

Pick the model behind your agent

Most of these agents let you choose the model. Send one prompt to up to six models and see which answer you'd actually use, with what each one cost.

Compare models

Data through October 21, 2026 for 20 agents. npm downloads from the npm registry; OpenRouter app rankings from OpenRouter (CC BY 4.0); GitHub stars and VS Code installs from monthly snapshots in the Internet Archive and the live APIs; survey figures as published by Stack Overflow and JetBrains.