daily_stock_analysis vs deer-flow
Two of the top projects in Agent platforms, side by side: who leads on each score part and who each one suits, then setup, license, activity and what each review found.
daily_stock_analysis
Daily LLM stock analysis for A-share, HK, US and other markets, pushed to chat apps
deer-flow
Agent harness that runs sub-agents, memory and sandboxed skills for long tasks
Verdict
daily_stock_analysis ranks higher, 77 to 75. Of the 5 score parts we measure for both, daily_stock_analysis leads on 2, deer-flow on 1 and 2 are even.
- Adoptiondeer-flow leads by 14 points, 82 to 68.
- FreshnessEven at 100.
- Maintenancedaily_stock_analysis leads by 20 points, 96 to 76: a wide gap.
- Easy to runEven at 50.
- Agent-readydaily_stock_analysis leads by 15 points, 85 to 70: a wide gap.
Pick daily_stock_analysis if you are
Retail investors and self-hosters wanting scheduled LLM watchlist reports
- Runs on a GitHub Actions fork with no server; default schedule is weekdays 18:00 Beijing time
- Free data sources (AkShare, Baostock, YFinance) work with zero configuration
Pick deer-flow if you are
Engineers self-hosting a multi-agent harness for research and long-running tasks
- Interactive `make setup` wizard generates config.yaml and .env in about 2 minutes
- Web UI model registration for OpenAI, Anthropic, DeepSeek, Qwen, Doubao, Kimi, Zhipu, MiniMax
| What we compare | daily_stock_analysis | deer-flow |
|---|---|---|
| Score parts, out of 100 | ||
| Adoption | 68, popular | 82, widely used |
| Freshness | 100, active | 100, active |
| Maintenance | 96, healthy | 76, fair |
| Easy to run | 50, easy | 50, easy |
| Agent-ready | 85, ready | 70, partly |
| Facts from GitHub and the README | ||
| Stars | 66.4k | 83.9k |
| License | MIT (permissive) | MIT (permissive) |
| Last commit | Oct 2026 | Oct 2026 |
| Last release | Sep 2026 | Sep 2026 |
| Language | Python | Python |
| Docker | Yes | Yes |
| GPU | Not needed | Not needed |
| arm64 or Apple Silicon | Mentioned | Mentioned |
daily_stock_analysis
Python app that pulls quotes, K-lines, news and fundamentals for a watchlist across A-share, HK, US, Japan, Korea and Taiwan markets. It has an LLM write a decision report with score, trend, buy/sell levels and risks, then pushes it to WeCom, Feishu, Telegram, Discord, Slack or email. It runs on GitHub Actions, Docker or locally, with a FastAPI web workbench for history, backtests and strategy chat.
Who it is for: Retail investors and self-hosters wanting scheduled LLM watchlist reports
Strengths
- Runs on a GitHub Actions fork with no server; default schedule is weekdays 18:00 Beijing time
- Free data sources (AkShare, Baostock, YFinance) work with zero configuration
- Supports Gemini, Claude, OpenAI-compatible APIs, DeepSeek, Qwen and local Ollama models
- Six push channels plus a web UI with history, backtest, portfolio and 15 built-in chat strategies
Weaknesses
- README is mainly Chinese; English docs are in a separate file
- Free data sources are subject to rate limits and upstream changes; stability not guaranteed
- Report quality depends on a paid news-search API key; a search service is recommended
- Output is for study only; the disclaimer excludes investment advice and liability
- no GPU
- Docker + Compose
- Needs LLM API key or Ollama, News search API (Anspire, SerpAPI, Tavily, Bocha, Brave, MiniMax or SearXNG), Market data sources (AkShare, Baostock, YFinance; optional TickFlow, Tushare, Longbridge), Notification channel
- Models: Gemini, OpenAI-compatible, DeepSeek, Qwen, Claude
- port 8000
deer-flow
DeerFlow 2.0 is a ByteDance agent harness where a lead agent delegates to sub-agents, backed by long-term memory, a sandboxed file system and extensible skills. It includes a web UI, a Gateway, MCP support, IM channels, scheduled tasks, a terminal UI and an embedded Python client. It is a ground-up rewrite that shares no code with v1.
Who it is for: Engineers self-hosting a multi-agent harness for research and long-running tasks
Strengths
- Interactive `make setup` wizard generates config.yaml and .env in about 2 minutes
- Web UI model registration for OpenAI, Anthropic, DeepSeek, Qwen, Doubao, Kimi, Zhipu, MiniMax
- Tracing via LangSmith, Langfuse and Monocle, plus `make doctor` and `make support-bundle`
- Many search and fetch backends: Brave, Tavily, Jina, Firecrawl, Crawl4AI, InfoQuest
Weaknesses
- README warns improper deployment carries security risks; Gateway admin equals code execution
- Local development needs Python 3.12+ and Node.js 22+
- README is dense with config detail; RAM and hardware needs are not stated
- v2 shares no code with v1; v1 users must stay on the 1.x branch
- no GPU
- Docker + Compose
- Needs LLM provider API key, Python 3.12+, Node.js 22+
- Models: OpenAI, Anthropic, DeepSeek, Qwen, Doubao
More in Agent platforms
Building with these?
We help teams pick an open-source AI stack and run it in production. Client work never changes a rank.