#7878th of 80 in Agent platformsFor finance and business, trading, stocks and crypto, finance and accounting

aiagents-stock

Streamlit app where AI analyst agents research A-share, HK and US stocks

Stars
2.1k
License
no license
Last commit
Oct 2026
Last release
Oct 2025
Language
Python
Stars, last 29 weeks+877
21 Apr 2026: 1,206 stars28 Apr 2026: 1,243 stars5 May 2026: 1,265 stars12 May 2026: 1,309 stars19 May 2026: 1,348 stars26 May 2026: 1,393 stars2 Jun 2026: 1,423 stars9 Jun 2026: 1,455 stars16 Jun 2026: 1,482 stars23 Jun 2026: 1,520 stars30 Jun 2026: 1,566 stars7 Jul 2026: 1,601 stars14 Jul 2026: 1,667 stars21 Jul 2026: 1,701 stars28 Jul 2026: 1,737 stars4 Aug 2026: 1,769 stars11 Aug 2026: 1,805 stars18 Aug 2026: 1,827 stars25 Aug 2026: 1,849 stars1 Sept 2026: 1,875 stars8 Sept 2026: 1,890 stars15 Sept 2026: 1,907 stars22 Sept 2026: 1,927 stars29 Sept 2026: 1,962 stars6 Oct 2026: 1,980 stars13 Oct 2026: 1,998 stars20 Oct 2026: 2,018 stars27 Oct 2026: 2,039 stars3 Nov 2026: 2,061 stars10 Nov 2026: 2,083 stars

1,206 on 21 Apr 20262,083 on 10 Nov 2026

From GitHub's daily star counts.

Checked on GitHub.

Overview

Streamlit app that runs six LLM analyst roles (technical, fundamental, fund flow, risk, sentiment, news) on a stock, then produces a team discussion, a rating and a PDF report. It adds iwencai-based screeners, price alerts via email, DingTalk or Feishu, and optional MiniQMT order placement. Works with any OpenAI-compatible model, defaulting to DeepSeek.

Who it is for: Chinese-speaking retail investors self-hosting LLM-assisted stock research

Strengths

  • Covers analysis, screening, monitoring, portfolio schedules and notifications in a single app
  • Any OpenAI-compatible model via DEFAULT_MODEL_NAME; optional OrcaRouter gateway
  • Data source fallback chain TDX, Tushare, AKShare; Compose file included
  • API keys and notifications configurable from a web settings page

Weaknesses

  • Screeners need an iwencai login cookie and Playwright Chromium
  • README and UI are Chinese only; targets Chinese market data and brokers
  • No license file detected by tooling, though the README says MIT
  • Auto trading needs a locally running MiniQMT client; not investment advice per its disclaimer

What it needs

  • no GPU
  • Docker + Compose
  • Needs DeepSeek or OpenAI-compatible API key, Node.js 16+ (pywencai), Playwright Chromium, SQLite, Tushare token (optional), MiniQMT (optional)
  • Models: DeepSeek, Qwen, GPT-4o, OpenAI-compatible APIs, OrcaRouter
  • port 8503

Quick answers

Is aiagents-stock open source?

Its code is public on GitHub, but the repository has no license, so by default nobody may reuse it.

Can you run aiagents-stock with Docker?

Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.

Does aiagents-stock need a GPU?

No, it runs without one.

Also in Agent platforms

See all 80
Also in Agent platforms
RankProjectScore
1AutoGPTRole-based AI agents coordinated by one lead agent, plus a visual workflow builder Live demo ↗ (opens in a new tab)188k stars+853 (+0.5%) in 30 dayscustom license95 out of 100
2daily_stock_analysisLLM-driven daily analysis of watchlist stocks across six markets, pushed to chat apps69.9k stars+3,683 (+5.6%) in 30 daysMIT95 out of 100
3LangflowVisual builder for AI agents and workflows, exposed as API or MCP server156.5k stars+1,251 (+0.8%) in 30 daysMIT94 out of 100
#4deer-flowAgent harness running sub-agents, memory and sandboxes with pluggable skills85.2k stars+1,752 (+2.1%) in 30 daysMIT93 out of 100
#5DifyVisual builder for LLM workflows, RAG pipelines and agents, with APIs Live demo ↗ (opens in a new tab)161k stars+3,111 (+2.0%) in 30 dayscustom license92 out of 100