ModelCompare
Compare

AI coding agent usage

What was the most used AI coding agent on ?

Claude Code from Anthropic, with a usage score of 50 out of 100 across 3 of 3 sources. OpenClaw was next at 35.

Usage score over time, week by week

Usage ranking

AI coding agents by usage on February 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. 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 50
    • npm 100 · 7.5M
    • GitHub 47 · 63k
    • VS Code 4 · 2.7M
    • npm: 1007,539,823 downloads of @anthropic-ai/claude-code in the 7 days to Feb 1, 2026. That's the most of any agent in this source, so it scores 100. Source
    • GitHub: 4763,236 stars on github.com/anthropics/claude-code on Feb 2, 2026. The leader here is OpenClaw with 135k, so Claude Code scores 63k ÷ 135k × 100 = 47. Source
    • VS Code: 42,655,617 installs of the anthropic.claude-code extension on Jan 5, 2026. The leader here is GitHub Copilot with 59M, so Claude Code scores 2.7M ÷ 59M × 100 = 4. Source

    Usage score: (100 + 47 + 4) ÷ 3 = 50. Claude Code website

  2. 2
    OpenClaw
    OpenClaw · open source
    Usage score 35
    • npm 6 · 416k
    • GitHub 100 · 135k
    • npm: 6416,067 downloads of openclaw in the 7 days to Feb 1, 2026. The leader here is Claude Code with 7.5M, so OpenClaw scores 416k ÷ 7.5M × 100 = 6. Source
    • GitHub: 100135,113 stars on github.com/openclaw/openclaw on Feb 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: (6 + 100) ÷ 3 = 35, 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 34
    • npm 2 · 155k
    • VS Code 100 · 59M
    • npm: 2155,084 downloads of @github/copilot in the 7 days to Feb 1, 2026. The leader here is Claude Code with 7.5M, so GitHub Copilot scores 155k ÷ 7.5M × 100 = 2. Source
    • VS Code: 10059,257,804 installs of the GitHub.copilot-chat extension on Feb 2, 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: (2 + 100) ÷ 3 = 34, divided by 3 rather than 2 because every agent's average counts at least 3 sources. GitHub Copilot website

  4. 4
    Gemini CLI
    Google · open source
    Usage score 26
    • npm 7 · 546k
    • GitHub 69 · 93k
    • VS Code 1 · 392k
    • npm: 7546,431 downloads of @google/gemini-cli in the 7 days to Feb 1, 2026. The leader here is Claude Code with 7.5M, so Gemini CLI scores 546k ÷ 7.5M × 100 = 7. Source
    • GitHub: 6993,254 stars on github.com/google-gemini/gemini-cli on Feb 2, 2026. The leader here is OpenClaw with 135k, so Gemini CLI scores 93k ÷ 135k × 100 = 69. Source
    • VS Code: 1392,333 installs of the Google.gemini-cli-vscode-ide-companion extension on Dec 12, 2025. The leader here is GitHub Copilot with 59M, so Gemini CLI scores 392k ÷ 59M × 100 = 1. Source

    Usage score: (7 + 69 + 1) ÷ 3 = 26. Gemini CLI website

  5. 5
    OpenCode
    Anomaly · open source
    Usage score 25
    • npm 5 · 349k
    • GitHub 70 · 94k
    • npm: 5349,156 downloads of opencode-ai in the 7 days to Feb 1, 2026. The leader here is Claude Code with 7.5M, so OpenCode scores 349k ÷ 7.5M × 100 = 5. Source
    • GitHub: 7094,012 stars on github.com/anomalyco/opencode on Feb 1, 2026. The leader here is OpenClaw with 135k, so OpenCode scores 94k ÷ 135k × 100 = 70. Source

    Not counted: VS Code, because there's no snapshot of its extension page from around that day.

    Usage score: (5 + 70) ÷ 3 = 25, divided by 3 rather than 2 because every agent's average counts at least 3 sources. OpenCode website

  6. 6
    Codex CLI
    OpenAI · open source
    Usage score 19
    • npm 8 · 618k
    • GitHub 43 · 58k
    • VS Code 6 · 3.5M
    • npm: 8618,412 downloads of @openai/codex in the 7 days to Feb 1, 2026. The leader here is Claude Code with 7.5M, so Codex CLI scores 618k ÷ 7.5M × 100 = 8. Source
    • GitHub: 4358,418 stars on github.com/openai/codex on Feb 2, 2026. The leader here is OpenClaw with 135k, so Codex CLI scores 58k ÷ 135k × 100 = 43. Source
    • VS Code: 63,531,141 installs of the openai.chatgpt extension on Feb 2, 2026. The leader here is GitHub Copilot with 59M, so Codex CLI scores 3.5M ÷ 59M × 100 = 6. Source

    Usage score: (8 + 43 + 6) ÷ 3 = 19. Codex CLI website

  7. 7
    Cline
    Cline · open source
    Usage score 16
    • npm 2 · 122k
    • GitHub 42 · 57k
    • VS Code 5 · 2.9M
    • npm: 2122,315 downloads of cline in the 7 days to Feb 1, 2026. The leader here is Claude Code with 7.5M, so Cline scores 122k ÷ 7.5M × 100 = 2. Source
    • GitHub: 4256,576 stars on github.com/cline/cline on Jan 1, 2026. The leader here is OpenClaw with 135k, so Cline scores 57k ÷ 135k × 100 = 42. Source
    • VS Code: 52,949,712 installs of the saoudrizwan.claude-dev extension on Jan 24, 2026. The leader here is GitHub Copilot with 59M, so Cline scores 2.9M ÷ 59M × 100 = 5. Source

    Usage score: (2 + 42 + 5) ÷ 3 = 16. Cline website

  8. 8
    Roo Code
    Roo Code · open source
    Usage score 6
    • GitHub 16 · 22k
    • VS Code 2 · 1.1M
    • GitHub: 1621,540 stars on github.com/RooCodeInc/Roo-Code on Jan 2, 2026. The leader here is OpenClaw with 135k, so Roo Code scores 22k ÷ 135k × 100 = 16. Source
    • VS Code: 21,146,390 installs of the RooVeterinaryInc.roo-cline extension on Jan 12, 2026. The leader here is GitHub Copilot with 59M, so Roo Code scores 1.1M ÷ 59M × 100 = 2. Source

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

    Usage score: (16 + 2) ÷ 3 = 6, divided by 3 rather than 2 because every agent's average counts at least 3 sources. Roo Code website

  9. 9
    Qwen Code
    Alibaba · open source
    Usage score 4
    • npm 1 · 43k
    • GitHub 13 · 17k
    • npm: 143,083 downloads of @qwen-code/qwen-code in the 7 days to Feb 1, 2026. The leader here is Claude Code with 7.5M, so Qwen Code scores 43k ÷ 7.5M × 100 = 1. Source
    • GitHub: 1317,172 stars on github.com/QwenLM/qwen-code on Jan 9, 2026. The leader here is OpenClaw with 135k, so Qwen Code scores 17k ÷ 135k × 100 = 13. Source

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

    Usage score: (1 + 13) ÷ 3 = 4, divided by 3 rather than 2 because every agent's average counts at least 3 sources. Qwen Code website

  10. 10
    Crush
    Charm · open source
    Usage score 4
    • npm 0 · 2.6k
    • GitHub 12 · 17k
    • npm: 02,568 downloads of @charmland/crush in the 7 days to Feb 1, 2026. The leader here is Claude Code with 7.5M, so Crush scores 2.6k ÷ 7.5M × 100 = 0. Source
    • GitHub: 1216,570 stars on github.com/charmbracelet/crush on Jan 1, 2026. The leader here is OpenClaw with 135k, so Crush scores 17k ÷ 135k × 100 = 12. Source

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

    Usage score: (0 + 12) ÷ 3 = 4, divided by 3 rather than 2 because every agent's average counts at least 3 sources. Crush website

  11. 11
    Kilo Code
    Kilo · open source
    Usage score 4
    • npm 0 · 9.9k
    • GitHub 10 · 14k
    • VS Code 1 · 607k
    • npm: 09,910 downloads of @kilocode/cli in the 7 days to Feb 1, 2026. The leader here is Claude Code with 7.5M, so Kilo Code scores 9.9k ÷ 7.5M × 100 = 0. Source
    • GitHub: 1013,662 stars on github.com/Kilo-Org/kilocode on Jan 1, 2026. The leader here is OpenClaw with 135k, so Kilo Code scores 14k ÷ 135k × 100 = 10. Source
    • VS Code: 1606,712 installs of the kilocode.Kilo-Code extension on Jan 6, 2026. The leader here is GitHub Copilot with 59M, so Kilo Code scores 607k ÷ 59M × 100 = 1. Source

    Usage score: (0 + 10 + 1) ÷ 3 = 4. Kilo Code website

  12. 12
    pi
    Mario Zechner · open source
    Usage score 1
    • npm 0 · 7.6k
    • GitHub 3 · 4.5k
    • npm: 07,588 downloads of @mariozechner/pi-coding-agent in the 7 days to Feb 1, 2026. The leader here is Claude Code with 7.5M, so pi scores 7.6k ÷ 7.5M × 100 = 0. Source
    • GitHub: 34,478 stars on github.com/badlogic/pi-mono on Feb 1, 2026. The leader here is OpenClaw with 135k, so pi scores 4.5k ÷ 135k × 100 = 3. Source

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

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

  13. 13
    Auggie
    Augment Code · closed source
    Usage score 0
    • npm 0 · 23k
    • VS Code 1 · 680k
    • npm: 023,236 downloads of @augmentcode/auggie in the 7 days to Feb 1, 2026. The leader here is Claude Code with 7.5M, so Auggie scores 23k ÷ 7.5M × 100 = 0. Source
    • VS Code: 1680,079 installs of the augment.vscode-augment extension on Jan 13, 2026. The leader here is GitHub Copilot with 59M, so Auggie scores 680k ÷ 59M × 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 · 5k
    • GitHub 1 · 832
    • npm: 05,018 downloads of @letta-ai/letta-code in the 7 days to Feb 1, 2026. The leader here is Claude Code with 7.5M, so Letta Code scores 5k ÷ 7.5M × 100 = 0. Source
    • GitHub: 1832 stars on github.com/letta-ai/letta-code on Jan 11, 2026. The leader here is OpenClaw with 135k, so Letta Code scores 832 ÷ 135k × 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 · 34k
    • VS Code 0 · 87k
    • npm: 034,104 downloads of @sourcegraph/amp in the 7 days to Feb 1, 2026. The leader here is Claude Code with 7.5M, so Amp scores 34k ÷ 7.5M × 100 = 0. Source
    • VS Code: 086,674 installs of the sourcegraph.amp extension on Jan 17, 2026. The leader here is GitHub Copilot with 59M, so Amp scores 87k ÷ 59M × 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, 67k), Aider (GitHub, 40k), Droid (npm, 910).

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 Feb 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

  • GitHubStars · data from Feb 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 Feb 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.