ModelCompare
Compare

AI coding agent usage

What was the most used AI coding agent on ?

OpenClaw from OpenClaw, with a usage score of 49 out of 100 across 3 of 4 sources. GitHub Copilot was next at 35.

Usage score over time, week by week

Usage ranking

AI coding agents by usage on June 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 49
    • npm 20 · 2.7M
    • OpenRouter 29 · 263B
    • GitHub 100 · 368k
    • npm: 202,681,511 downloads of openclaw in the 7 days to Jun 1, 2026. The leader here is Codex CLI with 14M, so OpenClaw scores 2.7M ÷ 14M × 100 = 20. 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: 100367,602 stars on github.com/openclaw/openclaw on May 3, 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: (20 + 29 + 100) ÷ 3 = 49. OpenClaw website

  2. 2
    GitHub Copilot
    GitHub · closed source
    Usage score 35
    • npm 5 · 675k
    • VS Code 100 · 75M
    • npm: 5674,834 downloads of @github/copilot in the 7 days to Jun 1, 2026. The leader here is Codex CLI with 14M, so GitHub Copilot scores 675k ÷ 14M × 100 = 5. Source
    • VS Code: 10074,635,976 installs of the GitHub.copilot-chat extension on Jun 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

  3. 3
    Codex CLI
    OpenAI · open source
    Usage score 34
    • npm 100 · 14M
    • OpenRouter 2 · 18B
    • GitHub 22 · 79k
    • VS Code 13 · 9.7M
    • npm: 10013,706,861 downloads of @openai/codex in the 7 days to Jun 1, 2026. That's the most of any agent in this source, so it scores 100. 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: 2279,184 stars on github.com/openai/codex on May 1, 2026. The leader here is OpenClaw with 368k, so Codex CLI scores 79k ÷ 368k × 100 = 22. Source
    • VS Code: 139,651,527 installs of the openai.chatgpt extension on Jun 1, 2026. The leader here is GitHub Copilot with 75M, so Codex CLI scores 9.7M ÷ 75M × 100 = 13. Source

    Usage score: (100 + 2 + 22 + 13) ÷ 4 = 34. Codex CLI website

  4. 4
    Claude Code
    Anthropic · closed source
    Usage score 34
    • npm 65 · 8.9M
    • OpenRouter 14 · 126B
    • GitHub 35 · 129k
    • VS Code 21 · 16M
    • npm: 658,880,366 downloads of @anthropic-ai/claude-code in the 7 days to Jun 1, 2026. The leader here is Codex CLI with 14M, so Claude Code scores 8.9M ÷ 14M × 100 = 65. 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: 35129,226 stars on github.com/anthropics/claude-code on Jun 1, 2026. The leader here is OpenClaw with 368k, so Claude Code scores 129k ÷ 368k × 100 = 35. Source
    • VS Code: 2115,998,815 installs of the anthropic.claude-code extension on Jun 2, 2026. The leader here is GitHub Copilot with 75M, so Claude Code scores 16M ÷ 75M × 100 = 21. Source

    Usage score: (65 + 14 + 35 + 21) ÷ 4 = 34. Claude Code website

  5. 5
    Cline
    Cline · open source
    Usage score 31
    • npm 1 · 79k
    • OpenRouter 100 · 918B
    • GitHub 17 · 61k
    • VS Code 5 · 3.8M
    • npm: 179,083 downloads of cline in the 7 days to Jun 1, 2026. The leader here is Codex CLI with 14M, so Cline scores 79k ÷ 14M × 100 = 1. 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: 1761,436 stars on github.com/cline/cline on May 7, 2026. The leader here is OpenClaw with 368k, so Cline scores 61k ÷ 368k × 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 75M, so Cline scores 3.8M ÷ 75M × 100 = 5. Source

    Usage score: (1 + 100 + 17 + 5) ÷ 4 = 31. Cline website

  6. 6
    Hermes Agent
    Nous Research · open source
    Usage score 23
    • OpenRouter 21 · 196B
    • GitHub 48 · 175k
    • 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: 48174,961 stars on github.com/NousResearch/hermes-agent on Jun 1, 2026. The leader here is OpenClaw with 368k, so Hermes Agent scores 175k ÷ 368k × 100 = 48. 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 + 48) ÷ 3 = 23, divided by 3 rather than 2 because every agent's average counts at least 3 sources. Hermes Agent website

  7. 7
    Roo Code
    Roo Code · open source
    Usage score 22
    • OpenRouter 59 · 539B
    • GitHub 7 · 24k
    • 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: 723,949 stars on github.com/RooCodeInc/Roo-Code on May 9, 2026. The leader here is OpenClaw with 368k, so Roo Code scores 24k ÷ 368k × 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 75M, so Roo Code scores 1.6M ÷ 75M × 100 = 2. Source

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

    Usage score: (59 + 7 + 2) ÷ 3 = 22. Roo Code website

  8. 8
    OpenCode
    Anomaly · open source
    Usage score 19
    • npm 12 · 1.6M
    • GitHub 46 · 168k
    • VS Code 1 · 527k
    • npm: 121,606,383 downloads of opencode-ai in the 7 days to Jun 1, 2026. The leader here is Codex CLI with 14M, so OpenCode scores 1.6M ÷ 14M × 100 = 12. Source
    • GitHub: 46168,137 stars on github.com/anomalyco/opencode on Jun 1, 2026. The leader here is OpenClaw with 368k, so OpenCode scores 168k ÷ 368k × 100 = 46. Source
    • VS Code: 1526,969 installs of the sst-dev.opencode extension on May 11, 2026. The leader here is GitHub Copilot with 75M, so OpenCode scores 527k ÷ 75M × 100 = 1. Source

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

    Usage score: (12 + 46 + 1) ÷ 3 = 19. OpenCode website

  9. 9
    OpenHands
    All Hands AI · open source
    Usage score 12
    • OpenRouter 17 · 152B
    • GitHub 20 · 73k
    • 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: 2072,633 stars on github.com/OpenHands/OpenHands on May 5, 2026. The leader here is OpenClaw with 368k, so OpenHands scores 73k ÷ 368k × 100 = 20. 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 + 20) ÷ 3 = 12, divided by 3 rather than 2 because every agent's average counts at least 3 sources. OpenHands website

  10. 10
    Gemini CLI
    Google · open source
    Usage score 11
    • npm 5 · 706k
    • GitHub 28 · 103k
    • VS Code 1 · 755k
    • npm: 5706,279 downloads of @google/gemini-cli in the 7 days to Jun 1, 2026. The leader here is Codex CLI with 14M, so Gemini CLI scores 706k ÷ 14M × 100 = 5. Source
    • GitHub: 28102,847 stars on github.com/google-gemini/gemini-cli on May 1, 2026. The leader here is OpenClaw with 368k, so Gemini CLI scores 103k ÷ 368k × 100 = 28. 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 75M, so Gemini CLI scores 755k ÷ 75M × 100 = 1. Source

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

    Usage score: (5 + 28 + 1) ÷ 3 = 11. Gemini CLI website

  11. 11
    Kilo Code
    Kilo · open source
    Usage score 7
    • npm 0 · 54k
    • OpenRouter 21 · 190B
    • GitHub 5 · 19k
    • VS Code 1 · 1.1M
    • npm: 054,458 downloads of @kilocode/cli in the 7 days to Jun 1, 2026. The leader here is Codex CLI with 14M, so Kilo Code scores 54k ÷ 14M × 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 368k, so Kilo Code scores 19k ÷ 368k × 100 = 5. Source
    • VS Code: 11,091,095 installs of the kilocode.Kilo-Code extension on May 14, 2026. The leader here is GitHub Copilot with 75M, so Kilo Code scores 1.1M ÷ 75M × 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 · 74k
    • OpenRouter 8 · 74B
    • GitHub 7 · 24k
    • npm: 173,611 downloads of @qwen-code/qwen-code in the 7 days to Jun 1, 2026. The leader here is Codex CLI with 14M, so Qwen Code scores 74k ÷ 14M × 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 368k, so Qwen Code scores 24k ÷ 368k × 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 12 · 46k
    • 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: 1245,608 stars on github.com/Aider-AI/aider on Jun 1, 2026. The leader here is OpenClaw with 368k, so Aider scores 46k ÷ 368k × 100 = 12. 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 + 12) ÷ 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 4
    • npm 0 · 7.6k
    • OpenRouter 4 · 35B
    • GitHub 9 · 33k
    • npm: 07,588 downloads of @mariozechner/pi-coding-agent in the 7 days to Jun 1, 2026. The leader here is Codex CLI with 14M, so pi scores 7.6k ÷ 14M × 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: 932,973 stars on github.com/badlogic/pi-mono on Apr 8, 2026. The leader here is OpenClaw with 368k, so pi scores 33k ÷ 368k × 100 = 9. Source

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

    Usage score: (0 + 4 + 9) ÷ 3 = 4. pi website

  15. 15
    Crush
    Charm · open source
    Usage score 2
    • npm 0 · 3.1k
    • GitHub 6 · 24k
    • npm: 03,109 downloads of @charmland/crush in the 7 days to Jun 1, 2026. The leader here is Codex CLI with 14M, so Crush scores 3.1k ÷ 14M × 100 = 0. Source
    • GitHub: 623,742 stars on github.com/charmbracelet/crush on May 2, 2026. The leader here is OpenClaw with 368k, so Crush scores 24k ÷ 368k × 100 = 6. 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 + 6) ÷ 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 · 31k
    • VS Code 1 · 739k
    • npm: 031,232 downloads of @augmentcode/auggie in the 7 days to Jun 1, 2026. The leader here is Codex CLI with 14M, so Auggie scores 31k ÷ 14M × 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 75M, so Auggie scores 739k ÷ 75M × 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
    Letta Code
    Letta · open source
    Usage score 0
    • npm 0 · 9.1k
    • OpenRouter 0 · 0
    • GitHub 1 · 2.6k
    • npm: 09,059 downloads of @letta-ai/letta-code in the 7 days to Jun 1, 2026. The leader here is Codex CLI with 14M, so Letta Code scores 9.1k ÷ 14M × 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: 12,553 stars on github.com/letta-ai/letta-code on May 24, 2026. The leader here is OpenClaw with 368k, so Letta Code scores 2.6k ÷ 368k × 100 = 1. Source

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

    Usage score: (0 + 0 + 1) ÷ 3 = 0. Letta Code website

  18. 18
    Amp
    Sourcegraph · closed source
    Usage score 0
    • npm 0 · 20k
    • VS Code 0 · 105k
    • npm: 020,136 downloads of @sourcegraph/amp in the 7 days to Jun 1, 2026. The leader here is Codex CLI with 14M, so Amp scores 20k ÷ 14M × 100 = 0. Source
    • VS Code: 0105,204 installs of the sourcegraph.amp extension on Apr 16, 2026. The leader here is GitHub Copilot with 75M, so Amp scores 105k ÷ 75M × 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: (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: 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 Jun 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 Jun 1, 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 Jun 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.