ModelCompare
Compare

AI coding agent usage

What was the most used AI coding agent on ?

Claude Code from Anthropic, with a usage score of 47 out of 100 across 3 of 3 sources. OpenClaw was next at 36.

Usage score over time, week by week

Usage ranking

AI coding agents by usage on April 21, 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. 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 47
    • npm 100 · 12M
    • GitHub 28 · 97k
    • VS Code 13 · 8.8M
    • npm: 10012,412,350 downloads of @anthropic-ai/claude-code in the 7 days to Apr 21, 2026. That's the most of any agent in this source, so it scores 100. Source
    • GitHub: 2896,883 stars on github.com/anthropics/claude-code on Apr 1, 2026. The leader here is OpenClaw with 344k, so Claude Code scores 97k ÷ 344k × 100 = 28. Source
    • VS Code: 138,753,902 installs of the anthropic.claude-code extension on Apr 1, 2026. The leader here is GitHub Copilot with 69M, so Claude Code scores 8.8M ÷ 69M × 100 = 13. Source

    Usage score: (100 + 28 + 13) ÷ 3 = 47. Claude Code website

  2. 2
    OpenClaw
    OpenClaw · open source
    Usage score 36
    • npm 8 · 1M
    • GitHub 100 · 344k
    • npm: 81,045,989 downloads of openclaw in the 7 days to Apr 21, 2026. The leader here is Claude Code with 12M, so OpenClaw scores 1M ÷ 12M × 100 = 8. Source
    • GitHub: 100343,810 stars on github.com/openclaw/openclaw on Apr 1, 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.

    Usage score: (8 + 100) ÷ 3 = 36, divided by 3 rather than 2 because every agent's average counts at least 3 sources. OpenClaw website

  3. 3
    GitHub Copilot
    GitHub · closed source
    Usage score 35
    • npm 4 · 491k
    • VS Code 100 · 69M
    • npm: 4490,512 downloads of @github/copilot in the 7 days to Apr 21, 2026. The leader here is Claude Code with 12M, so GitHub Copilot scores 491k ÷ 12M × 100 = 4. Source
    • VS Code: 10069,165,482 installs of the GitHub.copilot-chat extension on Apr 1, 2026. 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: (4 + 100) ÷ 3 = 35, divided by 3 rather than 2 because every agent's average counts at least 3 sources. GitHub Copilot website

  4. 4
    Codex CLI
    OpenAI · open source
    Usage score 23
    • npm 39 · 4.8M
    • GitHub 21 · 71k
    • VS Code 9 · 6.4M
    • npm: 394,786,201 downloads of @openai/codex in the 7 days to Apr 21, 2026. The leader here is Claude Code with 12M, so Codex CLI scores 4.8M ÷ 12M × 100 = 39. Source
    • GitHub: 2170,609 stars on github.com/openai/codex on Apr 1, 2026. The leader here is OpenClaw with 344k, so Codex CLI scores 71k ÷ 344k × 100 = 21. Source
    • VS Code: 96,441,680 installs of the openai.chatgpt extension on Apr 1, 2026. The leader here is GitHub Copilot with 69M, so Codex CLI scores 6.4M ÷ 69M × 100 = 9. Source

    Usage score: (39 + 21 + 9) ÷ 3 = 23. Codex CLI website

  5. 5
    OpenCode
    Anomaly · open source
    Usage score 17
    • npm 12 · 1.4M
    • GitHub 39 · 134k
    • VS Code 1 · 376k
    • npm: 121,437,303 downloads of opencode-ai in the 7 days to Apr 21, 2026. The leader here is Claude Code with 12M, so OpenCode scores 1.4M ÷ 12M × 100 = 12. Source
    • GitHub: 39134,191 stars on github.com/anomalyco/opencode on Apr 1, 2026. The leader here is OpenClaw with 344k, so OpenCode scores 134k ÷ 344k × 100 = 39. Source
    • VS Code: 1376,328 installs of the sst-dev.opencode extension on Apr 11, 2026. The leader here is GitHub Copilot with 69M, so OpenCode scores 376k ÷ 69M × 100 = 1. Source

    Usage score: (12 + 39 + 1) ÷ 3 = 17. OpenCode website

  6. 6
    Gemini CLI
    Google · open source
    Usage score 13
    • npm 7 · 918k
    • GitHub 29 · 100k
    • VS Code 1 · 755k
    • npm: 7917,755 downloads of @google/gemini-cli in the 7 days to Apr 21, 2026. The leader here is Claude Code with 12M, so Gemini CLI scores 918k ÷ 12M × 100 = 7. Source
    • GitHub: 2999,785 stars on github.com/google-gemini/gemini-cli on Apr 1, 2026. The leader here is OpenClaw with 344k, so Gemini CLI scores 100k ÷ 344k × 100 = 29. Source
    • VS Code: 1755,019 installs of the Google.gemini-cli-vscode-ide-companion extension on Apr 13, 2026. The leader here is GitHub Copilot with 69M, so Gemini CLI scores 755k ÷ 69M × 100 = 1. Source

    Usage score: (7 + 29 + 1) ÷ 3 = 13. Gemini CLI website

  7. 7
    Cline
    Cline · open source
    Usage score 8
    • npm 1 · 99k
    • GitHub 17 · 60k
    • VS Code 5 · 3.6M
    • npm: 199,182 downloads of cline in the 7 days to Apr 21, 2026. The leader here is Claude Code with 12M, so Cline scores 99k ÷ 12M × 100 = 1. Source
    • GitHub: 1759,755 stars on github.com/cline/cline on Apr 1, 2026. The leader here is OpenClaw with 344k, so Cline scores 60k ÷ 344k × 100 = 17. Source
    • VS Code: 53,570,409 installs of the saoudrizwan.claude-dev extension on Apr 10, 2026. The leader here is GitHub Copilot with 69M, so Cline scores 3.6M ÷ 69M × 100 = 5. Source

    Usage score: (1 + 17 + 5) ÷ 3 = 8. Cline website

  8. 8
    pi
    Mario Zechner · open source
    Usage score 3
    • npm 0 · 7.6k
    • GitHub 10 · 33k
    • npm: 07,588 downloads of @mariozechner/pi-coding-agent in the 7 days to Apr 21, 2026. The leader here is Claude Code with 12M, so pi scores 7.6k ÷ 12M × 100 = 0. Source
    • GitHub: 1032,973 stars on github.com/badlogic/pi-mono on Apr 8, 2026. The leader here is OpenClaw with 344k, so pi scores 33k ÷ 344k × 100 = 10. Source

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

    Usage score: (0 + 10) ÷ 3 = 3, divided by 3 rather than 2 because every agent's average counts at least 3 sources. pi website

  9. 9
    Roo Code
    Roo Code · open source
    Usage score 3
    • GitHub 7 · 23k
    • VS Code 2 · 1.4M
    • GitHub: 722,980 stars on github.com/RooCodeInc/Roo-Code on Apr 5, 2026. The leader here is OpenClaw with 344k, so Roo Code scores 23k ÷ 344k × 100 = 7. Source
    • VS Code: 21,426,494 installs of the RooVeterinaryInc.roo-cline extension on Apr 1, 2026. The leader here is GitHub Copilot with 69M, so Roo Code scores 1.4M ÷ 69M × 100 = 2. Source

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

    Usage score: (7 + 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 1 · 150k
    • GitHub 6 · 21k
    • npm: 1149,708 downloads of @qwen-code/qwen-code in the 7 days to Apr 21, 2026. The leader here is Claude Code with 12M, so Qwen Code scores 150k ÷ 12M × 100 = 1. Source
    • GitHub: 621,485 stars on github.com/QwenLM/qwen-code on Apr 1, 2026. The leader here is OpenClaw with 344k, so Qwen Code scores 21k ÷ 344k × 100 = 6. Source

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

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

  11. 11
    Kilo Code
    Kilo · open source
    Usage score 2
    • npm 0 · 55k
    • GitHub 5 · 17k
    • VS Code 1 · 957k
    • npm: 055,268 downloads of @kilocode/cli in the 7 days to Apr 21, 2026. The leader here is Claude Code with 12M, so Kilo Code scores 55k ÷ 12M × 100 = 0. Source
    • GitHub: 517,441 stars on github.com/Kilo-Org/kilocode on Apr 1, 2026. The leader here is OpenClaw with 344k, so Kilo Code scores 17k ÷ 344k × 100 = 5. Source
    • VS Code: 1956,529 installs of the kilocode.Kilo-Code extension on Apr 10, 2026. The leader here is GitHub Copilot with 69M, so Kilo Code scores 957k ÷ 69M × 100 = 1. Source

    Usage score: (0 + 5 + 1) ÷ 3 = 2. Kilo Code website

  12. 12
    Crush
    Charm · open source
    Usage score 2
    • npm 0 · 15k
    • GitHub 7 · 22k
    • npm: 015,065 downloads of @charmland/crush in the 7 days to Apr 21, 2026. The leader here is Claude Code with 12M, so Crush scores 15k ÷ 12M × 100 = 0. Source
    • GitHub: 722,432 stars on github.com/charmbracelet/crush on Apr 3, 2026. The leader here is OpenClaw with 344k, so Crush scores 22k ÷ 344k × 100 = 7. Source

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

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

  13. 13
    Auggie
    Augment Code · closed source
    Usage score 0
    • npm 0 · 37k
    • VS Code 1 · 739k
    • npm: 037,338 downloads of @augmentcode/auggie in the 7 days to Apr 21, 2026. The leader here is Claude Code with 12M, so Auggie scores 37k ÷ 12M × 100 = 0. Source
    • VS Code: 1738,960 installs of the augment.vscode-augment extension on Apr 14, 2026. The leader here is GitHub Copilot with 69M, so Auggie scores 739k ÷ 69M × 100 = 1. Source

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

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

  14. 14
    Letta Code
    Letta · open source
    Usage score 0
    • npm 0 · 6.5k
    • GitHub 1 · 2.1k
    • npm: 06,451 downloads of @letta-ai/letta-code in the 7 days to Apr 21, 2026. The leader here is Claude Code with 12M, so Letta Code scores 6.5k ÷ 12M × 100 = 0. Source
    • GitHub: 12,109 stars on github.com/letta-ai/letta-code on Apr 7, 2026. The leader here is OpenClaw with 344k, so Letta Code scores 2.1k ÷ 344k × 100 = 1. Source

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

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

  15. 15
    Amp
    Sourcegraph · closed source
    Usage score 0
    • npm 0 · 29k
    • VS Code 0 · 105k
    • npm: 029,039 downloads of @sourcegraph/amp in the 7 days to Apr 21, 2026. The leader here is Claude Code with 12M, so Amp scores 29k ÷ 12M × 100 = 0. Source
    • VS Code: 0105,204 installs of the sourcegraph.amp extension on Apr 16, 2026. The leader here is GitHub Copilot with 69M, so Amp scores 105k ÷ 69M × 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

Not ranked that day, only one source has them: OpenHands (GitHub, 71k), Aider (GitHub, 43k), Hermes Agent (GitHub, 21k), Droid (npm, 1.8k).

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 Apr 21, 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 Apr 9, 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 Apr 16, 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

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.