[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"pack-detail-personal-investing-ai-en":3,"seo:pack:personal-investing-ai:en":98},{"code":4,"message":5,"data":6},200,"操作成功",{"pack":7},{"slug":8,"icon":9,"tone":10,"status":11,"status_label":12,"title":13,"description":14,"items":15,"install_cmd":97},"personal-investing-ai","📈","#10B981","new","New · this week","Personal Investing AI — AI Stack for Self-Directed Investors","Ten picks for the self-directed investor running stocks, ETFs, crypto, and options out of their own dashboard: market data + research, AI for reading 10-Ks and earnings, portfolio monitoring, strategy backtesting, and a plain-text trading ledger for tax season. Editorial, not financial advice.",[16,28,38,46,53,61,69,76,83,90],{"id":17,"uuid":18,"slug":19,"title":20,"description":21,"author_name":22,"view_count":23,"vote_count":24,"lang_type":25,"type":26,"type_label":27},2599,"40612086-4771-11f1-9bc6-00163e2b0d79","openbb-open-source-investment-research-platform-40612086","OpenBB — Open-Source Investment Research Platform","OpenBB provides a unified Python SDK and CLI for accessing financial market data from dozens of providers, enabling quant researchers and analysts to build custom investment workflows without expensive terminal subscriptions.","Script Depot",54,0,"en","skill","Skill",{"id":29,"uuid":30,"slug":31,"title":32,"description":33,"author_name":34,"view_count":35,"vote_count":24,"lang_type":25,"type":36,"type_label":37},3642,"1b4ee2c7-6143-5e42-aaa8-32d7a4eea207","twstockmcpserver-taiwan-stock-data-mcp-server","TWStockMCPServer — Taiwan Stock Data MCP Server","TWStockMCPServer is an MCP server for Taiwan market data; verified 85★ and the README cites 143 TWSE OpenAPI tools plus Docker\u002FHTTP modes.","MCP Hub",64,"mcp","MCP",{"id":39,"uuid":40,"slug":41,"title":42,"description":43,"author_name":44,"view_count":45,"vote_count":24,"lang_type":25,"type":26,"type_label":27},4338,"94144188-39a7-4495-b4a1-562536ab0242","claude-code-agent-quant-analyst-94144188","Claude Code Agent: Quant Analyst","Quantitative finance and algorithmic trading specialist. Use PROACTIVELY for financial modeling, trading strategy development, backtesting, risk analysis, and portfolio...","TokRepo精选",26,{"id":47,"uuid":48,"slug":49,"title":50,"description":51,"author_name":22,"view_count":52,"vote_count":24,"lang_type":25,"type":26,"type_label":27},3657,"488cac73-4f09-11f1-9bc6-00163e2b0d79","tradingagents-multi-agent-llm-financial-trading-framework-488cac73","TradingAgents — Multi-Agent LLM Financial Trading Framework","An open-source multi-agent framework that simulates a trading firm with specialized LLM agents for market analysis, risk management, and trade execution.",69,{"id":54,"uuid":55,"slug":56,"title":57,"description":58,"author_name":59,"view_count":60,"vote_count":24,"lang_type":25,"type":26,"type_label":27},3945,"9c461d13-7676-5580-8bf4-e1fb00660a9d","awesome-trading-agents-trading-agents-mcp-list","awesome-trading-agents — Trading Agents + MCP List","Curated list of trading agents, market-data MCPs, and skills, with “If you only read three” starters and bilingual docs. Verified 114★; pushed 2026-05-11.","Agent Toolkit",100,{"id":62,"uuid":63,"slug":64,"title":65,"description":66,"author_name":67,"view_count":68,"vote_count":24,"lang_type":25,"type":26,"type_label":27},2918,"5d04b403-4c28-11f1-9bc6-00163e2b0d79","wealthfolio-private-local-first-portfolio-tracker-5d04b403","Wealthfolio — Private Local-First Portfolio Tracker","Beautiful desktop app for tracking investments, net worth, and spending with all data stored locally on your machine.","AI Open Source",45,{"id":70,"uuid":71,"slug":72,"title":73,"description":74,"author_name":67,"view_count":75,"vote_count":24,"lang_type":25,"type":26,"type_label":27},886,"d4e2f573-349d-11f1-9bc6-00163e2b0d79","ghostfolio-open-source-wealth-management-portfolio-tracker-d4e2f573","Ghostfolio — Open Source Wealth Management & Portfolio Tracker","Ghostfolio is an open-source personal finance dashboard for tracking stocks, ETFs, crypto, and other investments with real-time market data and performance analytics.",149,{"id":77,"uuid":78,"slug":79,"title":80,"description":81,"author_name":67,"view_count":82,"vote_count":24,"lang_type":25,"type":26,"type_label":27},4583,"c91240a2-5425-11f1-9bc6-00163e2b0d79","backtrader-python-algorithmic-trading-framework-c91240a2","Backtrader — Python Algorithmic Trading Framework","A feature-rich Python framework for backtesting and live trading strategies with support for multiple data feeds, brokers, and advanced analytics.",20,{"id":84,"uuid":85,"slug":86,"title":87,"description":88,"author_name":22,"view_count":89,"vote_count":24,"lang_type":25,"type":26,"type_label":27},4580,"9add158b-5425-11f1-9bc6-00163e2b0d79","ccxt-universal-cryptocurrency-exchange-trading-library-9add158b","CCXT — Universal Cryptocurrency Exchange Trading Library","A unified API for connecting to over 100 cryptocurrency exchanges in Python, JavaScript, and PHP, enabling automated trading, market data retrieval, and portfolio management across platforms.",15,{"id":91,"uuid":92,"slug":93,"title":94,"description":95,"author_name":67,"view_count":96,"vote_count":24,"lang_type":25,"type":26,"type_label":27},4587,"0413334e-5426-11f1-9bc6-00163e2b0d79","ledger-double-entry-accounting-via-command-line-0413334e","Ledger — Double-Entry Accounting via the Command Line","A powerful plain-text accounting system that uses a simple text file format for double-entry bookkeeping, budgeting, and financial reporting from the terminal.",25,"tokrepo install pack\u002Fpersonal-investing-ai",{"pageType":99,"pageKey":8,"locale":25,"title":100,"metaDescription":101,"h1":102,"tldr":103,"bodyMarkdown":104,"faq":105,"schema":121,"internalLinks":127,"citations":140,"wordCount":153,"generatedAt":154},"pack","Personal Investing AI — 10-Tool Stack for the Self-Directed Investor","OpenBB, TWStockMCPServer, Quant Analyst agent, TradingAgents, awesome-trading-agents, Wealthfolio, Ghostfolio, Backtrader, CCXT, Ledger — the ten-asset stack a self-directed investor uses to pull market data, read 10-Ks with AI, monitor positions, backtest strategies, and keep a tax-ready trade log. Editorial. Not financial advice.","Personal Investing AI — From Market Data to Tax-Ready Ledger","Ten picks in deliberate order: build a market-data pipeline first (OpenBB + a stock MCP), then aim AI agents at filings and earnings, then track positions in a local-first portfolio app, then backtest before you trade, then keep a plain-text trade ledger for tax season. Editorial guidance, not financial advice — every signal in here gets human review before it touches an order ticket.","## What's in this pack\n\nThis is the stack for the **self-directed investor** — the person who runs their own brokerage account in stocks, ETFs, crypto, and the occasional options trade, and is tired of pasting earnings releases into a chat window one paragraph at a time. Not a Twitter list of 30 'AI alpha' bots. Every pick here does one specific job in the personal investing loop: pull market data, read filings with AI, monitor what you actually own, backtest before you trade, and keep enough of a paper trail that tax season is one afternoon.\n\nThe pack is built around one principle: **AI accelerates the research; the trade and the tax record stay yours**. That's why the data layer is `OpenBB` (open-source, you own the keys) instead of a paid terminal. That's why the portfolio layer is local-first (`Wealthfolio`, `Ghostfolio`) instead of a SaaS that sees every position you hold. And it's why the ledger is plain-text (`Ledger`) so you can hand a single file to your accountant in April.\n\n### The five layers\n\n- **Data sources** — `OpenBB`, `TWStockMCPServer` — pull prices, fundamentals, filings, with API keys you control.\n- **Research \u002F AI reading** — `Quant Analyst`, `TradingAgents`, `awesome-trading-agents` — point agents at 10-Ks, earnings transcripts, and industry comps.\n- **Portfolio monitoring** — `Wealthfolio`, `Ghostfolio` — track holdings, P&L, and allocation locally without uploading your book.\n- **Strategy & backtest** — `Backtrader`, `CCXT` — write a strategy, replay it on historical data, then paper-trade on real exchanges before risking a dollar.\n- **Tax \u002F ledger** — `Ledger` — one plain-text file of every fill, ready for cost-basis math at year end.\n\n## Install in this order (data pipeline → filings AI → portfolio dashboard → strategy → tax ledger)\n\n1. **OpenBB — Open-Source Investment Research Platform** — start here. OpenBB is a unified Python SDK and CLI that pulls market data, fundamentals, macro series, news, and filings from dozens of providers. Bring your own keys (free tiers exist for several). This is the data spine the rest of the pack reads from.\n2. **TWStockMCPServer — Taiwan Stock Data MCP Server** — example of the MCP shape: an LLM-callable server that hands market data straight to your agent. If you trade non-US markets, this is the pattern to copy; if you don't, skim it once and move on. The point is that data layers are pluggable.\n3. **Claude Code Agent: Quant Analyst** — once data is reachable, this is the agent you point at it. Valuation, DCF, scenario analysis, ratio screens, sensitivity tables. Feed it a fresh 10-K plus the last four quarters and ask 'what changed in the numbers'. Good at modeling, mediocre at judgment — the human still picks the assumption set.\n4. **TradingAgents — Multi-Agent LLM Financial Trading Framework** — a research-grade multi-agent setup that simulates an analyst desk (fundamentals, sentiment, news, technicals, risk). Use it the way you'd use a junior team: it produces a memo, you decide. Do not wire it to a live order ticket on day one.\n5. **awesome-trading-agents — Trading Agents + MCP List** — the index. Curated list of trading agent frameworks and MCP servers worth tracking — useful when picking 4 and 5's actual configuration, and for finding domain-specific MCPs (options chains, on-chain, alt-data) as new ones land.\n6. **Wealthfolio — Private Local-First Portfolio Tracker** — your positions, on your machine, no cloud. Multi-account, multi-currency, manual entry or import. The right answer when you don't want a vendor to see your book.\n7. **Ghostfolio — Open Source Wealth Management & Portfolio Tracker** — the self-hosted-server counterpart to Wealthfolio. Pick this if you want a web UI shared across devices (phone + laptop) and you're willing to run a Docker container. The two are alternatives — pick one based on the deploy story.\n8. **Backtrader — Python Algorithmic Trading Framework** — the workhorse for strategy backtesting in Python. Write a strategy, replay on historical bars, get metrics (Sharpe, drawdown, win rate) before you risk capital. Pairs with OpenBB for the data feed.\n9. **CCXT — Universal Cryptocurrency Exchange Trading Library** — if any part of your book is crypto, this is the integration layer. Unified API across 100+ exchanges for reading prices and placing orders. Start in read-only mode for monitoring; only enable trading keys after a long paper-trade window.\n10. **Ledger — Double-Entry Accounting via the Command Line** — the tax\u002Faudit backbone. Every fill (buy, sell, dividend, fee, FX conversion, crypto trade) lands as a double-entry posting in a plain-text journal. At tax time you have one file your accountant can read in any decade, no proprietary export needed.\n\n## How they fit together\n\n```\n     Market data APIs\n     (Yahoo, FMP, AV,\n      exchange feeds)\n            │\n            ▼\n      ┌─────────────┐         ┌──────────────────┐\n      │   OpenBB    │ ←─MCP─→ │ TWStockMCPServer │\n      │  (Python    │         │  (or other       │\n      │   SDK\u002FCLI)  │         │   regional MCP)  │\n      └─────┬───────┘         └────────┬─────────┘\n            │                          │\n            └──────────┬───────────────┘\n                       ▼\n             ┌─────────────────────┐\n             │  AI research layer  │\n             │  Quant Analyst      │ ← 10-Ks, earnings, comps\n             │  TradingAgents      │ ← multi-agent memos\n             │  awesome-trading-   │ ← index of more MCPs\u002Fagents\n             │   agents (catalog)  │\n             └──────────┬──────────┘\n                        │\n           memos \u002F models \u002F signals\n                        │\n     ┌──────────────────┴──────────────────┐\n     ▼                                     ▼\nPortfolio dashboards               Strategy \u002F execution\n(Wealthfolio  ◇  Ghostfolio)       (Backtrader for backtest,\n positions, P&L, allocation         CCXT for crypto venues)\n     │                                     │\n     └──────────────┬──────────────────────┘\n                    ▼\n             every fill \u002F dividend\n                    ▼\n             ┌─────────────┐\n             │   Ledger    │ ← plain-text journal,\n             │ (plain-text)│   cost basis, tax export\n             └─────────────┘\n```\n\nThe critical join is the **read-only AI on top of your own data**: the agents (Quant Analyst, TradingAgents) read the OpenBB-fetched data and your Ledger journal; they propose memos and signals; **you place the trade**, and the trade is logged back into Ledger. The agents never own the order ticket or the tax file. Read-only AI on auditable data is the safe shape for personal investing.\n\n## Tradeoffs you'll hit\n\n- **Real-time vs end-of-day data** — real-time stock and options feeds cost money (broker API or paid vendor). End-of-day is free or near-free. For research and backtesting, end-of-day is more than enough. For active intraday trading, you'll pay. Don't pay before you've proven you actually trade intraday.\n- **Data cost vs coverage** — OpenBB free providers cover US equities and crypto well, international equities and options chains less so. Plan to layer paid keys (FMP, Polygon, etc.) only for the slices you actually use. Subscribing to everything 'in case' is a $200\u002Fmonth tax on nothing.\n- **Model bias on financial text** — an LLM summarizing an earnings call will mirror the management tone. Adverse signals (rising churn, deferred capex) get smoothed into 'continued investment in growth'. Mitigation: ask for the *numbers that moved*, not the narrative, and cross-check against the 10-K body.\n- **Backtest overfitting** — Backtrader will happily show a 60% annualized return on a strategy that's curve-fit to one regime. Out-of-sample testing, walk-forward analysis, and paper-trading on live data for at least one quarter are not optional. A backtest is a hypothesis, not a license.\n\n## Common pitfalls\n\n- **AI-written strategies with look-ahead bias** — the single most common failure mode for LLM-generated backtests. The model writes a strategy that, on close inspection, uses tomorrow's data to make today's decision (e.g. referencing `close[t]` when only `close[t-1]` was available at decision time). Always inspect the time index in the strategy logic; reject any 'too good' Sharpe without staring at the entry condition for ten minutes.\n- **24\u002F7 crypto monitoring cost** — CCXT can poll exchanges as fast as their rate limits allow, and running that on a $10 VPS will rack up API errors, ban risks, and occasional missed fills. For personal accounts, 1-minute polling is plenty for almost everything below intraday scalping. Don't engineer for HFT you'll never do.\n- **Tax jurisdiction differences** — Ledger is a generic accounting tool; it doesn't know your country's wash-sale rules, holding-period brackets, or crypto-as-property treatment. The pack gives you the data; your accountant (or local tax software) applies the rules. Don't ship a tax return out of an LLM. Talk to a human.\n- **FMP \u002F data provider rate limits** — free tiers cap requests per minute and per day. Hit the cap during a Sunday-night research session and your dashboard goes blank. Cache aggressively (a local Parquet of daily bars is one line of code), and treat the provider as the slow side of your pipeline.\n- **Treating the AI output as a recommendation** — none of this pack constitutes financial advice. The agents produce memos, models, and backtests; you make the investment decision and you carry the loss. If a position would make you panic at -20%, don't take it because an LLM said the DCF was attractive.\n\n## Disclaimer\n\nThis pack is editorial guidance about an AI-assisted personal-investing workflow. It is **not** investment, tax, or legal advice. Tools mentioned have their own terms of service, data licenses, and regional restrictions — review them before use. Backtest results are not predictive of future performance. Past performance is not a guarantee of future returns. Talk to a licensed advisor before any material investment decision.",[106,109,112,115,118],{"q":107,"a":108},"Can AI actually pick stocks for me?","Not reliably, no. What AI is genuinely good at is **compressing the reading work**: summarizing a 200-page 10-K, comparing this quarter's segment results against the last four, extracting management's guidance changes, flagging unusual line items. That accelerates *your* research by 5-10x. What AI is still bad at: judgment under regime change, knowing when a thesis breaks, understanding why the market is wrong about a name (or whether you are). The pack is built around 'agent reads, you decide' for that reason. Use it to do better research, not to delegate the decision. The Quant Analyst agent + TradingAgents framework are research desks, not portfolio managers.",{"q":110,"a":111},"FMP vs Alpha Vantage vs Polygon — how do I pick a data provider?","Three rough buckets. **Free + casual**: Yahoo Finance via OpenBB's `yfinance` integration covers most US equity research, intraday + daily, with no key. Good enough to start. **Mid-tier paid**: Financial Modeling Prep (FMP) and Alpha Vantage both have generous free tiers and cheap paid plans ($15-30\u002Fmo), with fundamentals, ratios, and historical statements that Yahoo skips. FMP is stronger on fundamentals; Alpha Vantage stronger on FX and global indices. **Pro**: Polygon for institutional-grade real-time and tick data, but it starts at $30\u002Fmo and goes up fast. Practical sequence: start free, add FMP when you find yourself wanting 10-year statements, only consider Polygon when you can name the specific intraday strategy that needs it. OpenBB makes all three swappable behind the same SDK.",{"q":113,"a":114},"What are the most common backtest mistakes I'll make with Backtrader?","Four classics. **Look-ahead bias** — your strategy accidentally uses information from the future (e.g. tomorrow's open price to decide today's entry). **Survivorship bias** — your universe contains only stocks that exist today; the ones that went to zero are silently excluded and your returns look great. **Overfitting** — you tune parameters until the curve looks beautiful on the in-sample period; out of sample, it dies. **Transaction-cost denial** — your backtest assumes zero commission, zero slippage, infinite liquidity. Add realistic costs (10-20 bps per trade for retail equities, more for small caps) and many 'profitable' strategies flip to negative. Backtrader supports realistic execution modeling; use it, don't shortcut it.",{"q":116,"a":117},"How do I handle crypto for tax purposes?","Two-part problem. **Tracking**: CCXT can pull your trade history from every exchange you use; pipe each fill into Ledger as a posting with the timestamp, asset, quantity, fiat value at execution, and fees. This gives you a complete, queryable trade log. **Tax math**: this is jurisdiction-specific. In the US, crypto is property (FIFO or specific-identification cost basis, short-vs-long capital gains, every trade is a taxable event including crypto-to-crypto). In the UK, there's section 104 pooling. In Germany, >1 year held is tax-free. Don't guess — use a dedicated tool (Koinly, CoinTracker, TokenTax) or a CPA who handles crypto. Ledger gives you the clean data; the tax-rules layer is *not* in this pack on purpose, because getting it wrong is expensive.",{"q":119,"a":120},"Is AI-generated commentary on earnings reports actually trustworthy?","Trustworthy for compression, suspicious for conclusion. An LLM reading an earnings transcript will accurately extract: revenue, segments, margins, guidance changes, capex direction, named one-time items. That part is reliable, and it's 80% of the work. The unreliable part is the *interpretation* — 'this is a buy because margins expanded' is the kind of sentence the model produces fluently and confidently regardless of whether it's true. Treat the AI output as a clean executive summary, not a recommendation. Always check the actual numbers against the 10-Q exhibits before acting. The pack pairs Quant Analyst (extraction) with human judgment (decision) for exactly this reason.",{"@context":122,"@type":123,"name":124,"description":125,"numberOfItems":126,"inLanguage":25},"https:\u002F\u002Fschema.org","ItemList","Personal Investing AI","Ten AI-era picks for self-directed investors: market data and research, AI readers for filings and earnings, portfolio monitoring, strategy backtesting, and a plain-text trading ledger for tax season.",10,[128,132,136],{"url":129,"anchor":130,"reason":131},"\u002Fen\u002Fai-tools-for\u002Fdata-analysis","AI tools for data analysis","Investment research and quantitative work live inside the broader data-analysis catalog on TokRepo",{"url":133,"anchor":134,"reason":135},"\u002Fen\u002Fpacks\u002Ffinance-accountant-ai-pack","Finance + Accountant AI Pack","Sister pack for the bookkeeping side of money — pairs naturally with the investing flow at tax time",{"url":137,"anchor":138,"reason":139},"\u002Fen\u002Ffeatured","Featured assets on TokRepo","These ten picks are part of the broader curated catalog of agent-ready assets",[141,145,149],{"claim":142,"source_name":143,"source_url":144},"OpenBB is an open-source investment research platform with a unified Python SDK and CLI","OpenBB official site","https:\u002F\u002Fopenbb.co\u002F",{"claim":146,"source_name":147,"source_url":148},"Backtrader is a Python backtesting and live trading framework","Backtrader documentation","https:\u002F\u002Fwww.backtrader.com\u002F",{"claim":150,"source_name":151,"source_url":152},"CCXT provides a unified API across 100+ cryptocurrency exchanges","CCXT on GitHub","https:\u002F\u002Fgithub.com\u002Fccxt\u002Fccxt",920,"2026-05-23T00:00:00Z"]