Agentar-Scale-SQL is a novel framework that leverages scalable computation to significantly improve Text-to-SQL performance.
active 2025-09-29 → 2026-07-03 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 278 days from 2025-09-29 to 2026-07-03. Pushes: 6 total, peak 2 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 15 total, peak 3 in a day. Comments: 22 total, peak 3 in a day. Stars: 128 total, peak 14 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
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| Peng-fei-Wang | 19 | 3 | 0 | 15 |
| caseware66 | 3 | 0 | 0 | 2 |
| xiaoer2498 | 3 | 0 | 0 | 1 |
| czHero | 2 | 0 | 0 | 0 |
| dabao0903 | 2 | 2 | 0 | 0 |
| bajie688 | 1 | 0 | 0 | 0 |
| erbanku | 1 | 0 | 0 | 1 |
| nwy2010 | 1 | 0 | 0 | 1 |
| XM-Dong | 1 | 1 | 0 | 0 |
| wanjianwei | 1 | 0 | 0 | 0 |
| kinokopro | 1 | 0 | 0 | 0 |
| skytiansky | 1 | 0 | 0 | 0 |
| wanteatfruit | 1 | 0 | 0 | 1 |
| ChinaJeng | 1 | 0 | 0 | 0 |
| mmarianneliu | 1 | 0 | 0 | 0 |
| Muggle666 | 1 | 0 | 0 | 0 |
| noob-ctrl | 1 | 0 | 0 | 1 |
| k4nyeEaaast | 1 | 0 | 0 | 0 |
| xiaohui-hiwintech | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#27Peng-fei-Wang2026-04-09 13:08Code release for internal experimentation
- Issue comment#26wanteatfruit2026-02-05 09:09Request for Evaluation Results for Academic Research
- Issue comment#26Peng-fei-Wang2026-02-05 07:48Request for Evaluation Results for Academic Research
- Issue#26kinokopro2026-01-29 07:59Request for Evaluation Results for Academic Research
- Issue comment#11Peng-fei-Wang2026-01-21 06:44请问这个框架代码是需要用自己的sql生成训练集自己训练吗？不能直接用在生成sql上？发布的32B模型是怎么用呢？
- Issue comment#24Peng-fei-Wang2026-01-15 02:26vllm API prompt 调用方式示例吗？
- Issue#23xiaoer24982026-01-14 02:15About Iterative Refinement module.
- Issue#22bajie6882026-01-12 06:29是否可以将开源模型更换为闭源大模型调用
- Issue comment#21xiaoer24982026-01-07 07:38About the upper bound accuracy of the generator
- Issue comment#21Peng-fei-Wang2026-01-07 05:39About the upper bound accuracy of the generator
- Issue comment#20Peng-fei-Wang2025-12-26 05:35Why only value linking in your solution?
- Issue comment#20Peng-fei-Wang2025-12-25 09:09Why only value linking in your solution?
- Issue#20Muggle6662025-12-25 08:16Why only value linking in your solution?
- Issue comment#18nwy20102025-12-23 13:15Why use BM25 instead of just vector matching?
- Issue comment#17Peng-fei-Wang2025-12-18 07:05请问下载完32B模型 具体的调用步骤是什么呢？
- Issue#18xiaoer24982025-12-18 02:52Why use BM25 instead of just vector matching?
- Issue comment#14Peng-fei-Wang2025-12-15 06:51Will there be smaller models, such as 7B or 14B, open-sourced in the future?
- Issue#14k4nyeEaaast2025-12-15 06:41Will there be smaller models, such as 7B or 14B, open-sourced in the future?
- Issue comment#12caseware662025-12-10 02:34第一步和第二步如何关联运行
- Issue comment#12Peng-fei-Wang2025-12-10 02:25第一步和第二步如何关联运行
- Issue comment#12caseware662025-12-10 01:35第一步和第二步如何关联运行
- Issue comment#12Peng-fei-Wang2025-12-09 10:48第一步和第二步如何关联运行
- Issue#12caseware662025-12-09 10:46第一步和第二步如何关联运行
- Issue comment#10Peng-fei-Wang2025-12-07 08:24What is the performance on the MiniDev?
- Issue#8czHero2025-12-05 08:00how to get the data?
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 128 stars here means stars gained during the window, not the repo's star count.