ModelCompare
Compare

AI coding agent usage

What was the most used AI coding agent on ?

Cline from Cline, with a usage score of 41 out of 100 across 3 of 3 sources. Claude Code was next at 39.

Usage score over time, week by week

Usage ranking

AI coding agents by usage on March 3, 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
    Cline
    Cline · open source
    Usage score 41
    • npm 19 · 31k
    • GitHub 100 · 33k
    • VS Code 3 · 851k
    • npm: 1930,887 downloads of cline in the 7 days to Mar 3, 2025. The leader here is Claude Code with 166k, so Cline scores 31k ÷ 166k × 100 = 19. Source
    • GitHub: 10032,750 stars on github.com/cline/cline on Mar 4, 2025. That's the most of any agent in this source, so it scores 100. Source
    • VS Code: 3850,715 installs of the saoudrizwan.claude-dev extension on Mar 4, 2025. The leader here is GitHub Copilot with 24M, so Cline scores 851k ÷ 24M × 100 = 3. Source

    Usage score: (19 + 100 + 3) ÷ 3 = 41. Cline website

  2. 2
    Claude Code
    Anthropic · closed source
    Usage score 39
    • npm 100 · 166k
    • GitHub 16 · 5.1k
    • npm: 100165,742 downloads of @anthropic-ai/claude-code in the 7 days to Mar 3, 2025. That's the most of any agent in this source, so it scores 100. Source
    • GitHub: 165,110 stars on github.com/anthropics/claude-code on Mar 1, 2025. The leader here is Cline with 33k, so Claude Code scores 5.1k ÷ 33k × 100 = 16. Source

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

    Usage score: (100 + 16) ÷ 3 = 39, divided by 3 rather than 2 because every agent's average counts at least 3 sources. Claude Code website

  3. 3
    GitHub Copilot
    GitHub · closed source
    Usage score 33
    • npm 0 · 0
    • VS Code 100 · 24M
    • npm: 00 downloads of @github/copilot in the 7 days to Mar 3, 2025. The leader here is Claude Code with 166k, so GitHub Copilot scores 0 ÷ 166k × 100 = 0. Source
    • VS Code: 10024,483,284 installs of the GitHub.copilot-chat extension on Mar 3, 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
    Auggie
    Augment Code · closed source
    Usage score 0
    • npm 0 · 0
    • VS Code 0 · 11k
    • npm: 00 downloads of @augmentcode/auggie in the 7 days to Mar 3, 2025. The leader here is Claude Code with 166k, so Auggie scores 0 ÷ 166k × 100 = 0. Source
    • VS Code: 010,764 installs of the augment.vscode-augment extension on Feb 20, 2025. The leader here is GitHub Copilot with 24M, so Auggie scores 11k ÷ 24M × 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, 27k), Roo Code (VS Code, 96k).

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 Mar 3, 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 Mar 4, 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 Mar 4, 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.