SQLBot
AGENTS.md7k starsChanged 15 months agoLicence not identifiedView on GitHub
SQLBot 让业务用户用自然语言提问,基于已配置的数据源生成并安全执行 SQL,返回数据、图表、分析和后续问题建议。领域词汇表见 CONTEXT.md。 本文及按需文档是开发约定,不是现有实现已满足所有约束的证明。文档与实现冲突时先核实并报告差异,不要为迎合旧实现削弱安全要求;易漂移的实现细节注明源码入口或适用版本,避免多处复制。领域词汇约定不要求重命名现有 API、数据库字段或翻译键。 商业扩展源码维护在独立仓库 dataease/sqlbot-xpack。它不是 submodule,也不是本仓库的固定子目录。本地 sqlbot-xpack/ checkout 会被主仓库忽略,永远不应出现在本仓库 PR 中。 默认使用开源版 SQLBot 工作流:把 sqlbot-xpack 视为版本范围由 backend/pyproject.toml 约束的已发布 wheel(精确版本冻结在不入库的 uv.lock)。不读取、不修改本地 xpack checkout。 只有任务确实需要修改或调试闭源 xpack 代码,或需要两个仓库联动验证时,才按 docs/agents/xpack.md 检查本地关联开关(AGENTS.local.env)并协调两个仓库的变更。
- Reads credentials
Trending
Quiet since March.thin dataabout the whole repository
Who's talking about dataease/SQLBot
- LEEKIYOON-SEC/Argus-DEV“[Argus] CVE-2026-32949: SQLBot: SSRF를 통한 임의 파일 읽기 (AFR) 취약점 (가짜 MySQL 사용)”GitHub · Mar 20, 2026
- LEEKIYOON-SEC/Argus-DEV“[Argus] CVE-2026-32950: SQLBot: Excel 업로드 엔드포인트의 SQL Injection을 통한 RCE”GitHub · Mar 20, 2026
- LEEKIYOON-SEC/Argus-DEV“[Argus] CVE-2026-32622: SQLBot: 용어 주입을 통한 원격 코드 실행 취약점”GitHub · Mar 19, 2026
- sasha-the-architect/SQLBot“Fix SQL Injection Vulnerability in preview() function”GitHub · Jan 31, 2026
- DaoCloud/public-image-mirror“dataease/sqlbot:v1.5.0”GitHub · Jan 9, 2026
The biggest 5 of 12 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 12
Talked about on GitHub (12 times).
On GitHub · 12
- Mar 20, 2026[Argus] CVE-2026-32949: SQLBot: SSRF를 통한 임의 파일 읽기 (AFR) 취약점 (가짜 MySQL 사용) — LEEKIYOON-SEC/Argus-DEV0 reactions
- Mar 20, 2026[Argus] CVE-2026-32950: SQLBot: Excel 업로드 엔드포인트의 SQL Injection을 통한 RCE — LEEKIYOON-SEC/Argus-DEV0 reactions
- Mar 19, 2026[Argus] CVE-2026-32622: SQLBot: 용어 주입을 통한 원격 코드 실행 취약점 — LEEKIYOON-SEC/Argus-DEV0 reactions
- Jan 31, 2026Fix SQL Injection Vulnerability in preview() function — sasha-the-architect/SQLBot0 reactions
- Jan 9, 2026dataease/sqlbot:v1.5.0 — DaoCloud/public-image-mirror0 reactions · 1 comment
7 more on GitHub
- Nov 7, 2025学习一下text2sql提示词 — niumoo/JavaNotes0 reactions
- Nov 4, 2025【开源自荐】SQLBot - 基于大模型的智能问数系统 — ruanyf/weekly0 reactions
- Sep 29, 2025SQLBot智能问数系统部署 — chenWULUQI/wjc.github.io0 reactions
- Sep 17, 2025**SQLBot version** — MVB388/psychic-guide0 reactions
- Sep 17, 2025**SQLBot version** — MVB388/LIMITED-0 reactions
- Sep 17, 2025**SQLBot version** — MVB388/LIMITED-0 reactions · 1 comment
- Aug 28, 2025[公告] DataEase 发布 SQLBot 智能问数开源项目 — dataease/dataease0 reactions
In this repository2 other files it gives its agents.
- g2-ssr/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

