Skip to content

量化交易Qlib is an AI-oriented quantitative investment platform that aims to realize the potential, empower research, and create value using AI technologies in quantitative investment, from exploring ideas to implementing productions. Qlib supports diverse machine learning modeling paradigms. including supervised learning, market dynamics

Python · active 2025-01-102026-08-10 (UTC)

Partial coverage12,219 / 13,872 hourly files (88%) · 2 absent upstream · 1,650 failed, retryable2025-01-102026-08-11 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
14.3K
Pushes
89
Pull requests
87
Issues
94
Stars
12.1K
Forks
1.6K

Activity over time

Daily event counts in the loaded window

Line chart, 578 days from 2025-01-10 to 2026-08-10. Pushes: 89 total, peak 9 in a day. Pull requests: 87 total, peak 5 in a day. Issues: 94 total, peak 4 in a day. Comments: 224 total, peak 9 in a day. Stars: 12,088 total, peak 489 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#2249freenowill2026-06-07 05:13
    宣传一下:我自用的对qlib模型推理结果做的多agent策略分析
  • Issue#2229Olcmyk2026-05-23 12:41
    DDG-DA: TypeError: unhashable type: 'list' in InternalData.setup()
  • Issue#2226Olcmyk2026-05-23 10:14
    LightGBM 4.0+ Compatibility: TypeError when early_stopping_rounds=None
  • Issue#2226Olcmyk2026-05-23 10:14
    LightGBM 4.0+ Compatibility: TypeError when early_stopping_rounds=None
  • Pull request#2200zhaochaofeng2026-05-02 10:34
  • Issue#2198masmc052026-04-29 19:15
    Incorrect topic label. This isn't a minecraft server
  • Issue#2197bkauto32026-04-28 18:16
    Add SwarmScore — Portable Trust Rating for AI Agents
  • Issue comment#1922unliftedq2026-04-24 10:01
    csi300成份股csi300.txt部分数据有冲突
  • Issue comment#2150SunsetWolf2026-04-22 07:07
    docs: replace broken RD-Agent demo links in README
  • Issue comment#2192Srujanrana072026-04-19 12:09
    FileCalendarStorage.index() 方法存在严重缺陷
  • Pull request#2194AHS00032026-04-18 19:52
  • Issue comment#2149SunsetWolf2026-04-13 05:18
    demo video of RD Agent part link are invalid | RD Agent 部分的 示例视频 链接已失效
  • Issue comment#2109JKDasondee2026-04-10 03:38
    fix: correct WMA calculation to use nansum instead of nanmean
  • Issue comment#2188microsoft-github-policy-service[bot]2026-04-10 03:21
    fix(ops): WMA divides by window length twice
  • Issue comment#2179microsoft-github-policy-service[bot]2026-04-01 10:13
    feat: add optional US retail sentiment dataset support
  • Pull request#2179alexander-schneider2026-04-01 10:12
  • Issue comment#2162Bortlesboat2026-03-29 15:03
    feat: options/derivatives data collector module
  • Issue comment#2164warren6182026-03-23 03:01
    fix(model): use `in` instead of `==` for metric comparison in HIST and IGMTF
  • Pull request#2156kaish1142026-03-14 16:58
  • Issue comment#1629Peakara2026-03-08 12:10
    生成csi100股池文件,出错
  • Pull request#2151monkeyjack1232026-03-05 06:06
  • Pull request#2150monkeyjack1232026-03-05 04:39
  • Issue comment#2145Bortlesboat2026-03-03 22:35
    fix: upgrade deprecated LightGBM API in docs and version constraints
  • Issue comment#2144microsoft-github-policy-service[bot]2026-03-03 18:17
    Fix lint issues in qlib/utils/ (W1309, W0612)
  • Pull request#2141universeplayer2026-03-01 17:26

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 12,088 stars here means stars gained during the window, not the repo's star count.