By longsizhuo
Run a self-hosted AI investment committee for multi-asset portfolios: view live prices, P&L, and strategy for any yfinance symbol, and get buy/sell verdicts from a 4-role LLM committee with decision accounting and execution recording.
Back up / restore openInvest's local state — memory/ (holdings, strategy, user profile, committee records, dream logs) + db/ (trade ledger, job run history, market-data cache) + .env (SMTP/API credentials) + user_profile.json. All of this data is .gitignore'd with no historical versions in git, so a single accidental overwrite (e.g. slipping and running some one-off migration/init script) means real data loss — no git revert available. **Proactive trigger scenarios** — "backup invest data / 备份一下 openInvest 的数据", "my holdings/strategy look wiped / 我的持仓/策略好像被清空了", "invest data is lost / invest 数据丢了", "restore invest backup / 恢复一下 invest 的备份", before any reinstall/migration of the openInvest deployment on this machine, or right before running an unfamiliar migration/init script (back up first, then act).
First-time openInvest installation and onboarding. **ONLY use when** user explicitly says "set up invest" / "init invest" / "帮我初始化 invest", OR when `invest` skill's `doctor` returns `status="needs_setup"`. **NOT for daily usage** — once onboarding is done, the `invest` skill takes over (portfolio viewing, committee analysis, buy/sell tracking). Wraps `run.sh init --from-stdin` with the canonical 5-question flow.
openInvest multi-asset AI investment committee — **daily use**. Read portfolio / live prices / strategy / decision history / adjust positions / run a 4-role LLM committee for an investment verdict. Supports any yfinance symbol (A-share / HK / US / ETF / crypto / commodities) and any currency. **Two paths** — (1) Coordinator, Claude Code spawns 4 subagents, saves DeepSeek tokens; (2) Direct, any agent (Codex / Hermes / OpenClaw / Cursor / Cline / plain script) runs `run.sh run_committee <SYM>` for a one-shot verdict. **Trigger scenarios** — "show portfolio / 看看我的持仓", "how is my P&L / 我现在涨了多少", "should I buy/sell X / 该不该买卖X", "analyze X / 分析一下X", "run committee on X / 跑委员会", "track AAPL / 跟踪苹果", "add/trim a position, log a trade / 加仓减仓记一笔". **First-time install uses a separate skill `invest-setup`** (switch to it when `doctor` returns `needs_setup`). Backend — longsizhuo/openInvest.
Admin access level
Server config contains admin-level keywords
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A self-hosted investment decision engine built for modern AI agents. Multi-agent information isolation and cross-challenge protocol, providing an auditable decision trail (Audit Trail).
OpenInvest is a self-hosted investment decision engine built for modern AI agents.
It provides a verifiable investment committee, evidence-based reasoning, long-horizon backtesting, and auditable decision records. Instead of replacing Claude Code, Codex, Hermes, or OpenClaw, OpenInvest is designed to power them.
System Self-Disclosure: This system is an auditing tool to eliminate human investment cognitive biases and enforce reasoning transparency, not a return-amplifying black box. Latest automated audit (docs/verdict_accuracy.md): Directional verdicts (excluding HOLD) have a true hit rate of 42.2% (n=56, below random); HOLD accounts for 56% of all decisions. The system's value lies in transparency and discipline (mostly staying inactive, low turnover), not directional prediction. Detailed log stream can be found in docs/verdict_accuracy.md.
This project systematically attempts to falsify its own edge and publishes negative results as-is. The deterministic features the committee reads, and the timing signals around them, were tested against pre-registered statistical gates — none survived as tradable alpha.
| Test | Result | Verdict |
|---|---|---|
| Q1 cross-sectional stock picking | 6 features, mean-IC 0.025–0.067, Holm-corrected p=0.397 | No significant stock-picking signal |
| M1 multivariate GBM (out-of-sample) | mean OOS IC +0.003, p=0.925 | Feature combination doesn't help either — no signal |
| Q2 gold MA200 trend | p_holm=0.016, significant — but trend_dca shows it is beta, not tradable alpha: timing terminal value 3.07 vs 15.10 buy-and-hold, Sharpe +0.36 vs +0.68, max drawdown deeper (−57% vs −44%) | Statistically significant, economically untradable |
| Per-asset multi-signal families | 3 assets × 4 signal families × parameter grid = 24 variants per asset; after costs + DSR deflation, none passes DSR > 0.95 | No tradable signal in any family |
| Positive control | A cheating perfect-foresight timing signal scores DSR = 1.00 | The harness can detect a real signal |
Methodology: Newey-West HAC t-statistics, Deflated Sharpe Ratio (Bailey & López de Prado 2014, re-derived equation by equation), Holm correction, zero lookahead, and LLM training-cutoff probes.
npx claudepluginhub longsizhuo/openinvest --plugin investMaintain repo docs under the Open Knowledge Format (OKF) + fast doc/schema lookup (find_docs.py). Grep-first, script-fallback.
Give the agent eyes: capture a photo from the local webcam with ffmpeg and let it view and analyze it. Cross-platform (Linux/macOS/Windows). Adds an 'i-see-you' skill that triggers on '看看我', 'take a photo', 'selfie', or '拍照'.
Investment knowledge for personal and institutional wealth management. Covers risk measurement, asset classes, valuation, portfolio construction, policy and planning, personal finance, behavioral finance, and reporting.
Multi-agent cryptocurrency intelligence system with 7 specialized AI agents, 9 MCP servers (95 tools), cognitive learning, and self-evolving capabilities for comprehensive market analysis and paper trading.
Finance research, trading, risk, and portfolio Agent Skills grounded in LLMQuant Data. Bundles every llmquant-* category skill under skills/.
Longbridge securities skill family: 17 skills covering market quotes, account read-only, watchlist mutations, and analysis-tier composites (valuation / fundamentals / peer comparison / portfolio / news). Multilingual triggers (Simplified Chinese, Traditional Chinese, English).
Use Alva Agent for investing workflows: ask market questions with live financial context, set alerts, build or remix Playbooks, connect accounts, and backtest strategies on Alva Cloud.
Monitors and reports on investment portfolios with real-time valuations, performance metrics, and asset allocation analysis.