ModelCompare
Compare

AI coding agent usage

What was the most used AI coding agent on ?

OpenClaw from OpenClaw, with a usage score of 48 out of 100 across 3 of 4 sources. Claude Code was next at 41.

Usage score over time, week by week

Usage ranking

AI coding agents by usage on May 1, 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
    OpenClaw
    OpenClaw · open source
    Usage score 48
    • npm 14 · 1.2M
    • OpenRouter 29 · 263B
    • GitHub 100 · 344k
    • npm: 141,162,043 downloads of openclaw in the 7 days to May 1, 2026. The leader here is Claude Code with 8.3M, so OpenClaw scores 1.2M ÷ 8.3M × 100 = 14. Source
    • OpenRouter: 29263B tokens sent through OpenRouter by OpenClaw in the week to May 1, 2026. The leader here is Cline with 918B, so OpenClaw scores 263B ÷ 918B × 100 = 29. 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: (14 + 29 + 100) ÷ 3 = 48. OpenClaw website

  2. 2
    Claude Code
    Anthropic · closed source
    Usage score 41
    • npm 100 · 8.3M
    • OpenRouter 14 · 126B
    • GitHub 35 · 120k
    • VS Code 17 · 12M
    • npm: 1008,292,242 downloads of @anthropic-ai/claude-code in the 7 days to May 1, 2026. That's the most of any agent in this source, so it scores 100. Source
    • OpenRouter: 14126B tokens sent through OpenRouter by Claude Code in the week to May 1, 2026. The leader here is Cline with 918B, so Claude Code scores 126B ÷ 918B × 100 = 14. Source
    • GitHub: 35119,766 stars on github.com/anthropics/claude-code on May 2, 2026. The leader here is OpenClaw with 344k, so Claude Code scores 120k ÷ 344k × 100 = 35. Source
    • VS Code: 1712,441,402 installs of the anthropic.claude-code extension on May 2, 2026. The leader here is GitHub Copilot with 73M, so Claude Code scores 12M ÷ 73M × 100 = 17. Source

    Usage score: (100 + 14 + 35 + 17) ÷ 4 = 41. Claude Code website

  3. 3
    GitHub Copilot
    GitHub · closed source
    Usage score 35
    • npm 5 · 424k
    • VS Code 100 · 73M
    • npm: 5423,920 downloads of @github/copilot in the 7 days to May 1, 2026. The leader here is Claude Code with 8.3M, so GitHub Copilot scores 424k ÷ 8.3M × 100 = 5. Source
    • VS Code: 10072,915,732 installs of the GitHub.copilot-chat extension on May 1, 2026. That's the most of any agent in this source, so it scores 100. Source

    Not counted: OpenRouter, because it doesn't show up in OpenRouter's app rankings; GitHub, because it has no public GitHub repo.

    Usage score: (5 + 100) ÷ 3 = 35, 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 31
    • npm 2 · 177k
    • OpenRouter 100 · 918B
    • GitHub 17 · 60k
    • VS Code 5 · 3.8M
    • npm: 2177,127 downloads of cline in the 7 days to May 1, 2026. The leader here is Claude Code with 8.3M, so Cline scores 177k ÷ 8.3M × 100 = 2. Source
    • OpenRouter: 100918B tokens sent through OpenRouter by Cline in the week to May 1, 2026. That's the most of any agent in this source, so it scores 100. 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: 53,804,410 installs of the saoudrizwan.claude-dev extension on May 1, 2026. The leader here is GitHub Copilot with 73M, so Cline scores 3.8M ÷ 73M × 100 = 5. Source

    Usage score: (2 + 100 + 17 + 5) ÷ 4 = 31. Cline website

  5. 5
    Codex CLI
    OpenAI · open source
    Usage score 24
    • npm 62 · 5.2M
    • OpenRouter 2 · 18B
    • GitHub 23 · 79k
    • VS Code 9 · 6.4M
    • npm: 625,168,161 downloads of @openai/codex in the 7 days to May 1, 2026. The leader here is Claude Code with 8.3M, so Codex CLI scores 5.2M ÷ 8.3M × 100 = 62. Source
    • OpenRouter: 218B tokens sent through OpenRouter by Codex CLI in the week to May 1, 2026. The leader here is Cline with 918B, so Codex CLI scores 18B ÷ 918B × 100 = 2. Source
    • GitHub: 2379,184 stars on github.com/openai/codex on May 1, 2026. The leader here is OpenClaw with 344k, so Codex CLI scores 79k ÷ 344k × 100 = 23. Source
    • VS Code: 96,441,680 installs of the openai.chatgpt extension on Apr 1, 2026. The leader here is GitHub Copilot with 73M, so Codex CLI scores 6.4M ÷ 73M × 100 = 9. Source

    Usage score: (62 + 2 + 23 + 9) ÷ 4 = 24. Codex CLI website

  6. 6
    Roo Code
    Roo Code · open source
    Usage score 23
    • OpenRouter 59 · 539B
    • GitHub 7 · 23k
    • VS Code 2 · 1.6M
    • OpenRouter: 59539B tokens sent through OpenRouter by Roo Code in the week to May 1, 2026. The leader here is Cline with 918B, so Roo Code scores 539B ÷ 918B × 100 = 59. Source
    • 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: 21,560,247 installs of the RooVeterinaryInc.roo-cline extension on May 1, 2026. The leader here is GitHub Copilot with 73M, so Roo Code scores 1.6M ÷ 73M × 100 = 2. Source

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

    Usage score: (59 + 7 + 2) ÷ 3 = 23. Roo Code website

  7. 7
    OpenCode
    Anomaly · open source
    Usage score 20
    • npm 15 · 1.2M
    • GitHub 44 · 153k
    • VS Code 1 · 376k
    • npm: 151,226,625 downloads of opencode-ai in the 7 days to May 1, 2026. The leader here is Claude Code with 8.3M, so OpenCode scores 1.2M ÷ 8.3M × 100 = 15. Source
    • GitHub: 44152,728 stars on github.com/anomalyco/opencode on May 1, 2026. The leader here is OpenClaw with 344k, so OpenCode scores 153k ÷ 344k × 100 = 44. Source
    • VS Code: 1376,328 installs of the sst-dev.opencode extension on Apr 11, 2026. The leader here is GitHub Copilot with 73M, so OpenCode scores 376k ÷ 73M × 100 = 1. Source

    Not counted: OpenRouter, because it doesn't show up in OpenRouter's app rankings.

    Usage score: (15 + 44 + 1) ÷ 3 = 20. OpenCode website

  8. 8
    Hermes Agent
    Nous Research · open source
    Usage score 19
    • OpenRouter 21 · 196B
    • GitHub 37 · 128k
    • OpenRouter: 21196B tokens sent through OpenRouter by Hermes Agent in the week to May 1, 2026. The leader here is Cline with 918B, so Hermes Agent scores 196B ÷ 918B × 100 = 21. Source
    • GitHub: 37127,554 stars on github.com/NousResearch/hermes-agent on May 1, 2026. The leader here is OpenClaw with 344k, so Hermes Agent scores 128k ÷ 344k × 100 = 37. Source

    Not counted: npm, because it has no command-line package on npm; VS Code, because it has no VS Code extension.

    Usage score: (21 + 37) ÷ 3 = 19, divided by 3 rather than 2 because every agent's average counts at least 3 sources. Hermes Agent website

  9. 9
    Gemini CLI
    Google · open source
    Usage score 13
    • npm 10 · 792k
    • GitHub 30 · 103k
    • VS Code 1 · 755k
    • npm: 10791,504 downloads of @google/gemini-cli in the 7 days to May 1, 2026. The leader here is Claude Code with 8.3M, so Gemini CLI scores 792k ÷ 8.3M × 100 = 10. Source
    • GitHub: 30102,847 stars on github.com/google-gemini/gemini-cli on May 1, 2026. The leader here is OpenClaw with 344k, so Gemini CLI scores 103k ÷ 344k × 100 = 30. 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 73M, so Gemini CLI scores 755k ÷ 73M × 100 = 1. Source

    Not counted: OpenRouter, because it doesn't show up in OpenRouter's app rankings.

    Usage score: (10 + 30 + 1) ÷ 3 = 13. Gemini CLI website

  10. 10
    OpenHands
    All Hands AI · open source
    Usage score 12
    • OpenRouter 17 · 152B
    • GitHub 21 · 71k
    • OpenRouter: 17152B tokens sent through OpenRouter by OpenHands in the week to May 1, 2026. The leader here is Cline with 918B, so OpenHands scores 152B ÷ 918B × 100 = 17. Source
    • GitHub: 2170,602 stars on github.com/OpenHands/OpenHands on Apr 5, 2026. The leader here is OpenClaw with 344k, so OpenHands scores 71k ÷ 344k × 100 = 21. Source

    Not counted: npm, because it has no command-line package on npm; VS Code, because it has no VS Code extension.

    Usage score: (17 + 21) ÷ 3 = 12, divided by 3 rather than 2 because every agent's average counts at least 3 sources. OpenHands website

  11. 11
    Kilo Code
    Kilo · open source
    Usage score 7
    • npm 0 · 39k
    • OpenRouter 21 · 190B
    • GitHub 5 · 19k
    • VS Code 1 · 957k
    • npm: 039,288 downloads of @kilocode/cli in the 7 days to May 1, 2026. The leader here is Claude Code with 8.3M, so Kilo Code scores 39k ÷ 8.3M × 100 = 0. Source
    • OpenRouter: 21190B tokens sent through OpenRouter by Kilo Code in the week to May 1, 2026. The leader here is Cline with 918B, so Kilo Code scores 190B ÷ 918B × 100 = 21. Source
    • GitHub: 518,792 stars on github.com/Kilo-Org/kilocode on May 1, 2026. The leader here is OpenClaw with 344k, so Kilo Code scores 19k ÷ 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 73M, so Kilo Code scores 957k ÷ 73M × 100 = 1. Source

    Usage score: (0 + 21 + 5 + 1) ÷ 4 = 7. Kilo Code website

  12. 12
    Qwen Code
    Alibaba · open source
    Usage score 5
    • npm 1 · 84k
    • OpenRouter 8 · 74B
    • GitHub 7 · 24k
    • npm: 184,052 downloads of @qwen-code/qwen-code in the 7 days to May 1, 2026. The leader here is Claude Code with 8.3M, so Qwen Code scores 84k ÷ 8.3M × 100 = 1. Source
    • OpenRouter: 874B tokens sent through OpenRouter by Qwen Code in the week to May 1, 2026. The leader here is Cline with 918B, so Qwen Code scores 74B ÷ 918B × 100 = 8. Source
    • GitHub: 724,092 stars on github.com/QwenLM/qwen-code on May 2, 2026. The leader here is OpenClaw with 344k, so Qwen Code scores 24k ÷ 344k × 100 = 7. Source

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

    Usage score: (1 + 8 + 7) ÷ 3 = 5. Qwen Code website

  13. 13
    Aider
    Aider · open source
    Usage score 5
    • OpenRouter 1 · 12B
    • GitHub 13 · 44k
    • OpenRouter: 112B tokens sent through OpenRouter by Aider in the week to May 1, 2026. The leader here is Cline with 918B, so Aider scores 12B ÷ 918B × 100 = 1. Source
    • GitHub: 1344,252 stars on github.com/Aider-AI/aider on May 2, 2026. The leader here is OpenClaw with 344k, so Aider scores 44k ÷ 344k × 100 = 13. Source

    Not counted: npm, because it has no command-line package on npm; VS Code, because it has no VS Code extension.

    Usage score: (1 + 13) ÷ 3 = 5, divided by 3 rather than 2 because every agent's average counts at least 3 sources. Aider website

  14. 14
    pi
    Mario Zechner · open source
    Usage score 5
    • npm 0 · 7.6k
    • OpenRouter 4 · 35B
    • GitHub 10 · 33k
    • npm: 07,588 downloads of @mariozechner/pi-coding-agent in the 7 days to May 1, 2026. The leader here is Claude Code with 8.3M, so pi scores 7.6k ÷ 8.3M × 100 = 0. Source
    • OpenRouter: 435B tokens sent through OpenRouter by pi in the week to May 1, 2026. The leader here is Cline with 918B, so pi scores 35B ÷ 918B × 100 = 4. 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 + 4 + 10) ÷ 3 = 5. pi website

  15. 15
    Crush
    Charm · open source
    Usage score 2
    • npm 0 · 13k
    • GitHub 7 · 24k
    • npm: 013,111 downloads of @charmland/crush in the 7 days to May 1, 2026. The leader here is Claude Code with 8.3M, so Crush scores 13k ÷ 8.3M × 100 = 0. Source
    • GitHub: 723,742 stars on github.com/charmbracelet/crush on May 2, 2026. The leader here is OpenClaw with 344k, so Crush scores 24k ÷ 344k × 100 = 7. Source

    Not counted: OpenRouter, because it doesn't show up in OpenRouter's app rankings; 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

  16. 16
    Auggie
    Augment Code · closed source
    Usage score 0
    • npm 0 · 38k
    • VS Code 1 · 739k
    • npm: 037,953 downloads of @augmentcode/auggie in the 7 days to May 1, 2026. The leader here is Claude Code with 8.3M, so Auggie scores 38k ÷ 8.3M × 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 73M, so Auggie scores 739k ÷ 73M × 100 = 1. Source

    Not counted: OpenRouter, because it doesn't show up in OpenRouter's app rankings; 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

  17. 17
    Amp
    Sourcegraph · closed source
    Usage score 0
    • npm 1 · 50k
    • VS Code 0 · 105k
    • npm: 150,186 downloads of @sourcegraph/amp in the 7 days to May 1, 2026. The leader here is Claude Code with 8.3M, so Amp scores 50k ÷ 8.3M × 100 = 1. Source
    • VS Code: 0105,204 installs of the sourcegraph.amp extension on Apr 16, 2026. The leader here is GitHub Copilot with 73M, so Amp scores 105k ÷ 73M × 100 = 0. Source

    Not counted: OpenRouter, because it doesn't show up in OpenRouter's app rankings; GitHub, because it has no public GitHub repo.

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

  18. 18
    Letta Code
    Letta · open source
    Usage score 0
    • npm 0 · 9.2k
    • OpenRouter 0 · 0
    • GitHub 1 · 2.1k
    • npm: 09,201 downloads of @letta-ai/letta-code in the 7 days to May 1, 2026. The leader here is Claude Code with 8.3M, so Letta Code scores 9.2k ÷ 8.3M × 100 = 0. Source
    • OpenRouter: 00 tokens sent through OpenRouter by Letta Code in the week to May 1, 2026. The leader here is Cline with 918B, so Letta Code scores 0 ÷ 918B × 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 + 0 + 1) ÷ 3 = 0. Letta Code website

Not ranked that day, only one source has them: Droid (npm, 1.9k).

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 May 1, 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

  • OpenRouterTokens via OpenRouter, 7 days · data from May 1, 2026

    Tokens each app sent through OpenRouter in a week. It only sees traffic routed through OpenRouter, so agents that mostly call their own lab's API (Claude Code, Codex) look smaller than they are, and open-source agents that default to OpenRouter look bigger. Source

  • GitHubStars · data from May 2, 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 May 2, 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.