Skip to content

AgentCPM-GUI: An on-device GUI agent for operating Android apps, enhancing reasoning ability with reinforcement fine-tuning for efficient task execution.

active 2025-05-132026-05-11 (UTC)

Partial coverage11,785 / 13,135 hourly files (90%) · 2 absent upstream · 1,346 failed, retryable2025-02-092026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
875
Pushes
24
Pull requests
1
Issues
91
Stars
587
Forks
59

Activity over time

Daily event counts in the loaded window

Line chart, 364 days from 2025-05-13 to 2026-05-11. Pushes: 24 total, peak 4 in a day. Pull requests: 1 total, peak 1 in a day. Issues: 91 total, peak 13 in a day. Comments: 105 total, peak 8 in a day. Stars: 587 total, peak 89 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

Recent activity

Latest issues, pull requests and releases

  • Issue comment#100github-actions[bot]2026-03-16 04:23
    都支持哪些app,有清单吗?
  • Issue#100zcgit0012026-02-14 02:18
    都支持哪些app,有清单吗?
  • Issue#99zcr20242026-01-12 03:50
    关于gpt-4o在AITZ和AC上的测评
  • Issue#98github-actions[bot]2026-01-12 03:25
    screenspot-v2评测分数很低
  • Issue comment#98github-actions[bot]2026-01-12 03:25
    screenspot-v2评测分数很低
  • Issue#97github-actions[bot]2026-01-11 03:27
    GUIMTRFTDataset 的 step_index 计算是不是有问题啊
  • Issue comment#97github-actions[bot]2026-01-11 03:27
    GUIMTRFTDataset 的 step_index 计算是不是有问题啊
  • Issue#97github-actions[bot]2025-12-28 03:25
    GUIMTRFTDataset 的 step_index 计算是不是有问题啊
  • Issue comment#97github-actions[bot]2025-12-28 03:25
    GUIMTRFTDataset 的 step_index 计算是不是有问题啊
  • Issue#95github-actions[bot]2025-12-16 03:12
    rft训练过程中卡死
  • Issue comment#92github-actions[bot]2025-12-05 03:08
    坐标范围和图片缩放
  • Issue#91github-actions[bot]2025-11-29 02:57
    考虑升级底层模型吗
  • Issue#97shuqingjinse2025-11-27 10:33
    GUIMTRFTDataset 的 step_index 计算是不是有问题啊
  • Issue#93github-actions[bot]2025-11-27 02:59
    run_predict_qwen2_5VL.py效果有点差
  • Issue comment#93github-actions[bot]2025-11-27 02:59
    run_predict_qwen2_5VL.py效果有点差
  • Issue#91github-actions[bot]2025-11-15 02:53
    考虑升级底层模型吗
  • Issue comment#91github-actions[bot]2025-11-15 02:53
    考虑升级底层模型吗
  • Issue#94Zhong-Zhang2025-10-28 07:37
    询问AgentCPM-GUI评测数据相关问题
  • Issue comment#66icey-zhang2025-10-23 08:42
    微调数据集
  • Issue comment#92Zhong-Zhang2025-10-21 07:22
    坐标范围和图片缩放
  • Issue#91lywqq2025-10-15 02:13
    考虑升级底层模型吗
  • Issue#88Zhong-Zhang2025-09-15 06:39
    大佬求解答!!!~~~
  • Issue comment#89Zhong-Zhang2025-09-15 06:30
    low SR on AndroidControl High Test
  • Issue#89Zhong-Zhang2025-09-15 06:30
    low SR on AndroidControl High Test
  • Issue#86Zhong-Zhang2025-09-15 05:24
    Why doesn't the benchmark report SR?

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 587 stars here means stars gained during the window, not the repo's star count.