ModelCompare
Compare

AI coding agent usage

What was the most used AI coding agent on ?

Claude Code from Anthropic, with a usage score of 58 out of 100 across 4 of 4 sources. GitHub Copilot was next at 55.

Usage score over time, week by week

Usage ranking

AI coding agents by usage on August 4, 2026

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. 4 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 58
    • npm 65 · 11M
    • GitHub 37 · 140k
    • VS Code 29 · 22M
    • JetBrains 100 · 39%
    • npm: 6511,145,008 downloads of @anthropic-ai/claude-code in the 7 days to Aug 4, 2026. The leader here is Codex CLI with 17M, so Claude Code scores 11M ÷ 17M × 100 = 65. Source
    • GitHub: 37139,840 stars on github.com/anthropics/claude-code on Aug 1, 2026. The leader here is OpenClaw with 382k, so Claude Code scores 140k ÷ 382k × 100 = 37. Source
    • VS Code: 2922,430,605 installs of the anthropic.claude-code extension on Aug 5, 2026. The leader here is GitHub Copilot with 77M, so Claude Code scores 22M ÷ 77M × 100 = 29. Source
    • JetBrains Developer Ecosystem 2026: 10039% of 15,000 respondents said they use it. Question: AI coding tools used at work, May to July 2026. That's the most of any agent in this source, so it scores 100. Source

    Usage score: (65 + 37 + 29 + 100) ÷ 4 = 58. Claude Code website

  2. 2
    GitHub Copilot
    GitHub · closed source
    Usage score 55
    • npm 10 · 1.7M
    • VS Code 100 · 77M
    • JetBrains 54 · 21%
    • npm: 101,727,217 downloads of @github/copilot in the 7 days to Aug 4, 2026. The leader here is Codex CLI with 17M, so GitHub Copilot scores 1.7M ÷ 17M × 100 = 10. Source
    • VS Code: 10077,249,711 installs of the GitHub.copilot-chat extension on Aug 4, 2026. That's the most of any agent in this source, so it scores 100. Source
    • JetBrains Developer Ecosystem 2026: 5421% of 15,000 respondents said they use it. Question: AI coding tools used at work, May to July 2026. The leader here is Claude Code with 39%, so GitHub Copilot scores 21% ÷ 39% × 100 = 54. Source

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

    Usage score: (10 + 100 + 54) ÷ 3 = 55. GitHub Copilot website

  3. 3
    Codex CLI
    OpenAI · open source
    Usage score 46
    • npm 100 · 17M
    • GitHub 27 · 103k
    • VS Code 15 · 11M
    • JetBrains 41 · 16%
    • npm: 10017,206,375 downloads of @openai/codex in the 7 days to Aug 4, 2026. That's the most of any agent in this source, so it scores 100. Source
    • GitHub: 27103,323 stars on github.com/openai/codex on Aug 2, 2026. The leader here is OpenClaw with 382k, so Codex CLI scores 103k ÷ 382k × 100 = 27. Source
    • VS Code: 1511,321,010 installs of the openai.chatgpt extension on Jul 6, 2026. The leader here is GitHub Copilot with 77M, so Codex CLI scores 11M ÷ 77M × 100 = 15. Source
    • JetBrains Developer Ecosystem 2026: 4116% of 15,000 respondents said they use it. Question: AI coding tools used at work, May to July 2026. The leader here is Claude Code with 39%, so Codex CLI scores 16% ÷ 39% × 100 = 41. Source

    Usage score: (100 + 27 + 15 + 41) ÷ 4 = 46. Codex CLI website

  4. 4
    OpenClaw
    OpenClaw · open source
    Usage score 39
    • npm 18 · 3.2M
    • GitHub 100 · 382k
    • npm: 183,163,704 downloads of openclaw in the 7 days to Aug 4, 2026. The leader here is Codex CLI with 17M, so OpenClaw scores 3.2M ÷ 17M × 100 = 18. Source
    • GitHub: 100381,823 stars on github.com/openclaw/openclaw on Jul 5, 2026. That's the most of any agent in this source, so it scores 100. Source

    Not counted: VS Code, because it has no VS Code extension; JetBrains Developer Ecosystem 2026, because the survey didn't list it.

    Usage score: (18 + 100) ÷ 3 = 39, divided by 3 rather than 2 because every agent's average counts at least 3 sources. OpenClaw website

  5. 5
    OpenCode
    Anomaly · open source
    Usage score 21
    • npm 14 · 2.5M
    • GitHub 47 · 181k
    • VS Code 1 · 849k
    • npm: 142,463,237 downloads of opencode-ai in the 7 days to Aug 4, 2026. The leader here is Codex CLI with 17M, so OpenCode scores 2.5M ÷ 17M × 100 = 14. Source
    • GitHub: 47181,008 stars on github.com/anomalyco/opencode on Jul 1, 2026. The leader here is OpenClaw with 382k, so OpenCode scores 181k ÷ 382k × 100 = 47. Source
    • VS Code: 1849,452 installs of the sst-dev.opencode extension on Jul 14, 2026. The leader here is GitHub Copilot with 77M, so OpenCode scores 849k ÷ 77M × 100 = 1. Source

    Not counted: JetBrains Developer Ecosystem 2026, because the survey didn't list it.

    Usage score: (14 + 47 + 1) ÷ 3 = 21. OpenCode website

  6. 6
    Gemini CLI
    Google · open source
    Usage score 10
    • npm 2 · 396k
    • GitHub 28 · 106k
    • npm: 2395,583 downloads of @google/gemini-cli in the 7 days to Aug 4, 2026. The leader here is Codex CLI with 17M, so Gemini CLI scores 396k ÷ 17M × 100 = 2. Source
    • GitHub: 28106,320 stars on github.com/google-gemini/gemini-cli on Aug 3, 2026. The leader here is OpenClaw with 382k, so Gemini CLI scores 106k ÷ 382k × 100 = 28. Source

    Not counted: VS Code, because there's no snapshot of its extension page from around that day; JetBrains Developer Ecosystem 2026, because the survey didn't list it.

    Usage score: (2 + 28) ÷ 3 = 10, divided by 3 rather than 2 because every agent's average counts at least 3 sources. Gemini CLI website

  7. 7
    Cline
    Cline · open source
    Usage score 8
    • npm 1 · 140k
    • GitHub 17 · 65k
    • VS Code 6 · 4.9M
    • npm: 1140,193 downloads of cline in the 7 days to Aug 4, 2026. The leader here is Codex CLI with 17M, so Cline scores 140k ÷ 17M × 100 = 1. Source
    • GitHub: 1765,354 stars on github.com/cline/cline on Aug 1, 2026. The leader here is OpenClaw with 382k, so Cline scores 65k ÷ 382k × 100 = 17. Source
    • VS Code: 64,863,603 installs of the saoudrizwan.claude-dev extension on Aug 3, 2026. The leader here is GitHub Copilot with 77M, so Cline scores 4.9M ÷ 77M × 100 = 6. Source

    Not counted: JetBrains Developer Ecosystem 2026, because the survey didn't list it.

    Usage score: (1 + 17 + 6) ÷ 3 = 8. Cline website

  8. 8
    Kilo Code
    Kilo · open source
    Usage score 3
    • npm 0 · 42k
    • GitHub 7 · 27k
    • VS Code 2 · 1.3M
    • npm: 041,817 downloads of @kilocode/cli in the 7 days to Aug 4, 2026. The leader here is Codex CLI with 17M, so Kilo Code scores 42k ÷ 17M × 100 = 0. Source
    • GitHub: 726,698 stars on github.com/Kilo-Org/kilocode on Aug 4, 2026. The leader here is OpenClaw with 382k, so Kilo Code scores 27k ÷ 382k × 100 = 7. Source
    • VS Code: 21,336,331 installs of the kilocode.Kilo-Code extension on Jul 21, 2026. The leader here is GitHub Copilot with 77M, so Kilo Code scores 1.3M ÷ 77M × 100 = 2. Source

    Not counted: JetBrains Developer Ecosystem 2026, because the survey didn't list it.

    Usage score: (0 + 7 + 2) ÷ 3 = 3. Kilo Code website

  9. 9
    Roo Code
    Roo Code · open source
    Usage score 3
    • GitHub 6 · 24k
    • VS Code 2 · 1.8M
    • GitHub: 624,303 stars on github.com/RooCodeInc/Roo-Code on Jul 4, 2026. The leader here is OpenClaw with 382k, so Roo Code scores 24k ÷ 382k × 100 = 6. Source
    • VS Code: 21,842,390 installs of the RooVeterinaryInc.roo-cline extension on Jul 18, 2026. The leader here is GitHub Copilot with 77M, so Roo Code scores 1.8M ÷ 77M × 100 = 2. Source

    Not counted: npm, because it has no command-line package on npm; JetBrains Developer Ecosystem 2026, because the survey didn't list it.

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

  10. 10
    Qwen Code
    Alibaba · open source
    Usage score 2
    • npm 0 · 59k
    • GitHub 7 · 26k
    • npm: 059,022 downloads of @qwen-code/qwen-code in the 7 days to Aug 4, 2026. The leader here is Codex CLI with 17M, so Qwen Code scores 59k ÷ 17M × 100 = 0. Source
    • GitHub: 725,693 stars on github.com/QwenLM/qwen-code on Jul 1, 2026. The leader here is OpenClaw with 382k, so Qwen Code scores 26k ÷ 382k × 100 = 7. Source

    Not counted: VS Code, because it has no VS Code extension; JetBrains Developer Ecosystem 2026, because the survey didn't list it.

    Usage score: (0 + 7) ÷ 3 = 2, divided by 3 rather than 2 because every agent's average counts at least 3 sources. Qwen Code website

  11. 11
    Crush
    Charm · open source
    Usage score 2
    • npm 0 · 3.3k
    • GitHub 7 · 26k
    • npm: 03,343 downloads of @charmland/crush in the 7 days to Aug 4, 2026. The leader here is Codex CLI with 17M, so Crush scores 3.3k ÷ 17M × 100 = 0. Source
    • GitHub: 725,963 stars on github.com/charmbracelet/crush on Jul 2, 2026. The leader here is OpenClaw with 382k, so Crush scores 26k ÷ 382k × 100 = 7. Source

    Not counted: VS Code, because it has no VS Code extension; JetBrains Developer Ecosystem 2026, because the survey didn't list it.

    Usage score: (0 + 7) ÷ 3 = 2, divided by 3 rather than 2 because every agent's average counts at least 3 sources. Crush website

Not ranked that day, only one source has them: Hermes Agent (GitHub, 224k), Cursor (JetBrains, 12%), OpenHands (GitHub, 83k), Aider (GitHub, 47k), Auggie (npm, 39k), Letta Code (npm, 25k), Amp (npm, 14k), pi (npm, 7.6k), Droid (npm, 1.4k).

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 Aug 4, 2026

    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 Aug 4, 2026

    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 Aug 5, 2026

    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

  • JetBrains Developer Ecosystem 2026% of 15,000 respondents · data from Jul 31, 2026

    Share of developers in the survey who said they use each tool. Surveys only list the biggest tools. 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 November 4, 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.