Community usage

Which AI coding agents and models developers actually use

Every agent launched from AgentsRoom by users who share their usage, counted by CLI and by model. No survey, no vendor benchmark: what people start when they have work to do.

Updated Sep 21, 2026, 7:51 PM

Agent launches

63

newvs previous period

Users

5

CLIs used

4

Models used

12

Most launched coding CLIs

Share of all agent launches over the period, with the users who launched each one at least once.

  1. 1
    Claude69.8%
    44 launches5 usersnew
  2. 2
    Codex23.8%
    15 launches2 usersnew
  3. 3
    Antigravity4.8%
    3 launches2 usersnew
  4. 4
    Grok1.6%
    1 launches1 usersnew

Most launched models

The model pinned on the agent at launch. Launches that leave the model to the CLI's default are counted in the CLI totals only.

  1. 1
    OpusClaude44.4%
    28 launches3 users63.6% of Claude launchesnew
  2. 2
    GPT-5.6 LunaCodex15.9%
    10 launches2 users66.7% of Codex launchesnew
  3. 3
    Opus 5Claude12.7%
    8 launches2 users18.2% of Claude launchesnew
  4. 4
    SonnetClaude6.3%
    4 launches3 users9.1% of Claude launchesnew
  5. 5
    GPT-5.6 SolCodex4.8%
    3 launches1 users20% of Codex launchesnew
  6. 6
    defaultClaude3.2%
    2 launches2 users4.5% of Claude launchesnew
  7. 7
    Gemini 3.8 Flash (High)Antigravity3.2%
    2 launches1 users66.7% of Antigravity launchesnew
  8. 8
    GPT-6 AstraCodex3.2%
    2 launches1 users13.3% of Codex launchesnew
  9. 9
    Claude Sonnet 4.6Antigravity1.6%
    1 launches1 users33.3% of Antigravity launchesnew
  10. 10
    Grok 4.6Grok1.6%
    1 launches1 users100% of Grok launchesnew
  11. 11
    HaikuClaude1.6%
    1 launches1 users2.3% of Claude launchesnew
  12. 12
    Opus 4.8Claude1.6%
    1 launches1 users2.3% of Claude launchesnew

How agents are started

  • New agent33%
  • Backlog ticket25%
  • Quick agent14%
  • Team run11%
  • Trigger11%
  • Resumed3%

Reasoning effort

  • Medium43%
  • High27%
  • Low16%
  • Xhigh14%

Agent roles

  • Custom35%
  • Fullstack17%
  • Frontend13%
  • Architect6%
  • Bot6%
  • Mobile5%

Where the numbers come from

AgentsRoom is a desktop command center for AI coding agents. Every time a user starts an agent, the desktop records the CLI, the model, the reasoning effort, the agent role and how it was started, and nothing else: no prompt, no project, no file, no name. Only users who keep "Share usage data" on contribute, anonymous launches count as launches but never as users, and the page refreshes every ten minutes.

The same numbers rank the Providers and Models boards of the in-app leaderboard.

Download AgentsRoom