{"full_name":"ZhuLinsen/daily_stock_analysis","owner":"ZhuLinsen","name":"daily_stock_analysis","url":"https://github.com/ZhuLinsen/daily_stock_analysis","description":"LLM 驱动的多市场股票智能分析系统：多源行情、实时新闻、决策看板与自动推送，支持零成本定时运行。  LLM-powered multi-market stock analysis system with multi-source market data, real-time news, decision dashboard, automated notifications, and cost-free scheduled runs.","homepage":"https://dsa.zhulinsen.tech","topics":[],"language":"Python","license":"MIT","avatar":"https://avatars.githubusercontent.com/u/42829555?u=d8c2535ab7d7b9b8524f8e50dd41aae5d84793c7&v=4","created_at":"2026-01-10T06:43:20Z","pushed_at":"2026-11-09T14:14:52Z","metrics":{"stars":69396,"forks":56558,"watchers":273,"issues":864,"prs":1551,"releases":37,"issues_open":null,"issues_closed":null,"prs_open":null,"prs_closed":null,"prs_merged":null,"discussions":0},"growth":{"day":{"stars":995,"forks":272,"base_day":"2026-11-09"},"week":{"stars":1944,"forks":701,"base_day":"2026-11-03"},"month":{"stars":3475,"forks":1578,"base_day":"2026-10-11"}},"history":{"dates":["2026-09-17","2026-09-18","2026-09-19","2026-09-20","2026-09-21","2026-09-22","2026-09-23","2026-09-24","2026-09-25","2026-09-26","2026-09-27","2026-09-28","2026-09-29","2026-09-30","2026-10-01","2026-10-02","2026-10-03","2026-10-04","2026-10-05","2026-10-06","2026-10-07","2026-10-08","2026-10-09","2026-10-10","2026-10-11","2026-10-12","2026-10-13","2026-10-14","2026-10-15","2026-10-16","2026-10-17","2026-10-18","2026-10-19","2026-10-20","2026-10-21","2026-10-22","2026-10-23","2026-10-24","2026-10-25","2026-10-26","2026-10-27","2026-10-28","2026-10-29","2026-10-30","2026-10-31","2026-11-01","2026-11-02","2026-11-03","2026-11-04","2026-11-09","2026-11-10"],"stars":[64667,64744,64797,64843,64899,64941,64969,65050,65111,65145,65202,65250,65297,65436,65502,65533,65598,65645,65682,65760,65792,65830,65837,65868,65921,65970,66001,66044,66096,66147,66241,66294,66352,66413,66473,66594,66745,66787,66831,66886,66943,66990,67104,67166,67217,67262,67296,67452,67502,68401,69396],"forks":[54202,54272,54304,54342,54377,54401,54421,54489,54521,54538,54569,54591,54631,54716,54749,54777,54802,54830,54846,54891,54908,54943,54931,54950,54980,55002,55011,55027,55052,55087,55144,55193,55235,55278,55302,55360,55448,55479,55523,55552,55572,55603,55660,55687,55711,55743,55756,55857,55882,56286,56558],"watchers":[257,258,258,258,259,260,260,260,260,260,260,260,261,263,264,264,264,264,264,265,265,264,264,264,263,263,263,263,264,264,266,267,267,267,268,268,268,268,268,272,272,267,267,267,268,269,269,269,270,273,273],"issues_open":[null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null],"prs_open":[null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null]},"boards":{"daily":29,"weekly":71,"monthly":153,"daily_rate":88,"weekly_rate":143},"same_owner":[],"issues":[{"number":1903,"title":"feat: 增强 DecisionSignal 后验复盘并反馈到 Agent 记忆","comments":9,"created_at":"2026-07-03T13:21:45Z"},{"number":1743,"title":"roadmap: Codex / Claude Code / OpenCode / Hermes 本地生成与 Agent Backend","comments":9,"created_at":"2026-06-21T19:08:21Z"},{"number":1595,"title":"perf: 提高 LLM 分析输入的 prompt cache 利用率","comments":9,"created_at":"2026-06-04T04:00:57Z"},{"number":1733,"title":"长期开发规划：AI 投研系统、AlphaSift 深度融合、本地 Agent 能力复用与跨资产分析","comments":6,"created_at":"2026-06-20T13:47:26Z"},{"number":2411,"title":"feat(llm): 官方账号授权与模型接入（先调研与规划，待审查）","comments":4,"created_at":"2026-10-14T16:17:35Z"},{"number":1584,"title":"[Feature] 完善大盘复盘报告的分化与催化消化分析","comments":4,"created_at":"2026-06-03T14:22:52Z"},{"number":2137,"title":"[Feature] Android 移动端交付方案：先落地 PWA，再评估 TWA/Capacitor","comments":3,"created_at":"2026-07-31T14:51:37Z"},{"number":1942,"title":"[Feature] 是否能加入同花顺数据源","comments":3,"created_at":"2026-07-06T05:54:27Z"}],"discussions":[],"latest_release":{"name":"v3.33.0","tag":"v3.33.0","published_at":"2026-10-15T11:46:29Z","body":"## v3.33.0\n\n## 发布亮点\n\n- feat: 问股讨论对象由服务端保存，刷新、重开及 Bot/Web 交替使用可恢复；修复“长电科技”等完整股票名称被内部短别名误判的问题。\n- feat: 新增无需 LLM 的规则化 ETF 双动量轮动，提供最新调仓信号、扣成本回测、年度对比、参数平原检验及数据质量告警。\n- feat: Web 新增只读数据中心、持仓风险与暴露看板，以及自选股“变化 / 状态 / 下一步”提示；设置页保护未保存草稿并改善首次配置引导。\n- improve: 选股补齐带来源与质量状态的入选理由及新闻事件证据，修复日线新鲜度、交易日期、缓存降级和检索时间一致性。\n- feat: 简化 Modelflare 单 Key 配置，补充 Requesty 渠道、妙想筹码与资金流数据、FXMacroData 宏观工具，以及单票决策复盘记忆和 Multi-Agent 阶段评估。\n- fix: 修复基本面和资金流解析、科创板成交量单位、重复定时派发及桌面 MiniRacer 打包；调度超时后默认推送已完成的部分结果，可通过 `DSA_TIMEOUT_PARTIAL_NOTIFY=false` 关闭。\n\n## What's Changed\n\n- Persisted the confirmed chat discussion target on the server so it survives refreshes, reopened sessions, and Bot/Web handoffs. Preserved stock/index and cross-market identities, and fixed full stock names being rejected because of embedded aliases or ticker fragments, by @massif-01 and @ZhuLinsen.\n- Added rule-based ETF dual-momentum rotation with current allocation signals, transaction-cost-aware backtests, annual comparisons, parameter sensitivity checks, and data-quality warnings. The strategy uses the actual A-share trading calendar, handles missing quotes without fabricating trades, and does not call an LLM, by @VanishedDust.\n- Added a read-only data capability center, a portfolio risk and exposure dashboard, and watchlist next-action signals. Protected unsaved settings drafts and made the initial watchlist setup action scroll to and focus the correct field, by @ZhuLinsen and @ciphersaw.\n- Added provenance-aware Why Selected / Why Now explanations and per-condition checks for supplied screening snapshots. Improved news/event evidence before LLM reranking, isolated untrusted source material, and corrected trading-date validation, stale-source fallback, cache freshness, and retrieval timestamps, by @ZhuLinsen.\n- Simplified Modelflare configuration to a single key while preserving explicit routing priorities. Added the Requesty preset, optional Miaoxiang chip-distribution and capital-flow fallback, and read-only FXMacroData macroeconomic tools, by @ZhuLinsen, @Thibaultjaigu, and @roberttidball.\n- Added decision-signal review summaries to optional Agent memory and expanded Multi-Agent trajectory evaluation with stage-local tool metrics and cumulative step accounting, by @kebaptx4869 and @yanzhiliaoliao.\n- Deduplicated scheduled occurrences across CLI and Web/API processes sharing one SQLite database. Added timeout diagnostics and partial-result notifications, enabled by default and configurable with `DSA_TIMEOUT_PARTIAL_NOTIFY=false`; manual reruns remain available, by @ZhuLinsen and @MengMa-dev.\n- Corrected financial reporting periods and metric parsing, yfinance prior-year-quarter matching, Tencent STAR Market volume units, and bounded AkShare market-statistics calls. Added complete English analysis prompts, fixed UTF-8 BOM stock imports and alert-filter refresh behavior, and bundled MiniRacer native files and macOS screening resources with runtime checks, by @ZhuLinsen, @co2water, @SynapShift, @gaurav0107, @Iams4kura, and @AsaZhou923.\n\n## Full Changelog\n\nhttps://github.com/ZhuLinsen/daily_stock_analysis/compare/v3.32.0...v3.33.0\n\n@AsaZhou923 @Iams4kura @MengMa-dev @Serenity @Serennity007 @SynapShift @Thibaultjaigu @VanishedDust @ZhuLinsen @ciphersaw @co2water @gaurav0107 @kebaptx4869 @massif-01 @roberttidball @s4kura @summer-meng @yanzhiliaoliao\n"},"readme":true,"readme_zh":false,"news":[{"title":"Daily_stock_analysis: LLM-powered multi-market stock analysis system","url":"https://github.com/ZhuLinsen/daily_stock_analysis","hn":"https://news.ycombinator.com/item?id=48619147","source":"Hacker News","lang":"en","date":"2026-06-21","points":9,"comments":0},{"title":"Daily Stock Analysis","url":"https://github.com/ZhuLinsen/daily_stock_analysis","hn":"https://news.ycombinator.com/item?id=48682687","source":"Hacker News","lang":"en","date":"2026-06-26","points":2,"comments":0},{"title":"GitHub Actions定时运行教程：让daily_stock_analysis自动生成股票分析报告","url":"https://blog.csdn.net/gitblog_00180/article/details/153090682","source":"blog.csdn","lang":"zh","date":"2026-07-23"},{"title":"AI股票分析师daily_stock_analysis与GitHub Actions自动化工作流","url":"https://blog.csdn.net/weixin_29997223/article/details/158312104","source":"blog.csdn","lang":"zh","date":"2026-02-22"},{"title":"Github上开源的AI股票分析神器，已经突破5.5K+ Star!","url":"https://www.sohu.com/a/980206149_121124359","source":"搜狐","lang":"zh","date":"2026-01-26"},{"title":"LLM驱动的股票分析架构与风险","url":"https://news.google.com/rss/articles/CBMiZ0FVX3lxTFBidWxJa1J3YXBwb0pBSmo2aEpIQnFtOS1yZ01OeUZFNjFCSVN0REFTZExhN2d5a2RQTU1ZU2ZSSjdST25XcS0tY3NJeXZzSWRkYm00TFp6RzhxMmh1bGZpY2tzd183WW8?oc=5","source":"80aj.com","lang":"zh","date":"2026-01-19"}],"stale":false,"snapshot_at":"2026-11-10T09:35:25Z","history_start":"2026-09-06"}