ModelCompare
Compare

AI coding agent usage

What was the most used AI coding agent on ?

Claude Code from Anthropic, with a usage score of 39 out of 100 across 2 of 3 sources. Cline was next at 39.

Usage score over time, week by week

Usage ranking

AI coding agents by usage on May 1, 2025

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 39
    • npm 100 · 268k
    • GitHub 17 · 7k
    • npm: 100268,002 downloads of @anthropic-ai/claude-code in the 7 days to May 1, 2025. That's the most of any agent in this source, so it scores 100. Source
    • GitHub: 177,001 stars on github.com/anthropics/claude-code on Apr 1, 2025. The leader here is Cline with 42k, so Claude Code scores 7k ÷ 42k × 100 = 17. Source

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

    Usage score: (100 + 17) ÷ 3 = 39, divided by 3 rather than 2 because every agent's average counts at least 3 sources. Claude Code website

  2. 2
    Cline
    Cline · open source
    Usage score 39
    • npm 12 · 32k
    • GitHub 100 · 42k
    • VS Code 4 · 1.1M
    • npm: 1231,721 downloads of cline in the 7 days to May 1, 2025. The leader here is Claude Code with 268k, so Cline scores 32k ÷ 268k × 100 = 12. Source
    • GitHub: 10042,308 stars on github.com/cline/cline on May 1, 2025. That's the most of any agent in this source, so it scores 100. Source
    • VS Code: 41,122,287 installs of the saoudrizwan.claude-dev extension on Apr 2, 2025. The leader here is GitHub Copilot with 27M, so Cline scores 1.1M ÷ 27M × 100 = 4. Source

    Usage score: (12 + 100 + 4) ÷ 3 = 39. Cline website

  3. 3
    GitHub Copilot
    GitHub · closed source
    Usage score 33
    • npm 0 · 0
    • VS Code 100 · 27M
    • npm: 00 downloads of @github/copilot in the 7 days to May 1, 2025. The leader here is Claude Code with 268k, so GitHub Copilot scores 0 ÷ 268k × 100 = 0. Source
    • VS Code: 10027,079,711 installs of the GitHub.copilot-chat extension on Apr 1, 2025. 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: (0 + 100) ÷ 3 = 33, 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 19
    • npm 6 · 17k
    • GitHub 50 · 21k
    • VS Code 1 · 176k
    • npm: 616,622 downloads of @openai/codex in the 7 days to May 1, 2025. The leader here is Claude Code with 268k, so Codex CLI scores 17k ÷ 268k × 100 = 6. Source
    • GitHub: 5021,041 stars on github.com/openai/codex on May 1, 2025. The leader here is Cline with 42k, so Codex CLI scores 21k ÷ 42k × 100 = 50. Source
    • VS Code: 1175,563 installs of the openai.chatgpt extension on Apr 7, 2025. The leader here is GitHub Copilot with 27M, so Codex CLI scores 176k ÷ 27M × 100 = 1. Source

    Usage score: (6 + 50 + 1) ÷ 3 = 19. Codex CLI website

  5. 5
    Amp
    Sourcegraph · closed source
    Usage score 0
    • npm 1 · 3.2k
    • VS Code 0 · 311
    • npm: 13,246 downloads of @sourcegraph/amp in the 7 days to May 1, 2025. The leader here is Claude Code with 268k, so Amp scores 3.2k ÷ 268k × 100 = 1. Source
    • VS Code: 0311 installs of the sourcegraph.amp extension on May 1, 2025. The leader here is GitHub Copilot with 27M, so Amp scores 311 ÷ 27M × 100 = 0. Source

    Not counted: 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

  6. 6
    Kilo Code
    Kilo · open source
    Usage score 0
    • npm 0 · 0
    • GitHub 0 · 107
    • VS Code 0 · 889
    • npm: 00 downloads of @kilocode/cli in the 7 days to May 1, 2025. The leader here is Claude Code with 268k, so Kilo Code scores 0 ÷ 268k × 100 = 0. Source
    • GitHub: 0107 stars on github.com/Kilo-Org/kilocode on Apr 3, 2025. The leader here is Cline with 42k, so Kilo Code scores 107 ÷ 42k × 100 = 0. Source
    • VS Code: 0889 installs of the kilocode.Kilo-Code extension on Apr 3, 2025. The leader here is GitHub Copilot with 27M, so Kilo Code scores 889 ÷ 27M × 100 = 0. Source

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

  7. 7
    Auggie
    Augment Code · closed source
    Usage score 0
    • npm 0 · 0
    • VS Code 0 · 44k
    • npm: 00 downloads of @augmentcode/auggie in the 7 days to May 1, 2025. The leader here is Claude Code with 268k, so Auggie scores 0 ÷ 268k × 100 = 0. Source
    • VS Code: 044,428 installs of the augment.vscode-augment extension on Apr 3, 2025. The leader here is GitHub Copilot with 27M, so Auggie scores 44k ÷ 27M × 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. Auggie website

Not ranked that day, only one source has them: Aider (GitHub, 30k), Roo Code (VS Code, 325k).

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, 2025

    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 May 1, 2025

    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 1, 2025

    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.