Fund Dashboard

Personal investment portfolio analysis platform: fund / stock position management, net value tracking, XIRR annualized return, maximum drawdown, look-through analysis, DCA dollar-cost averaging backtesting, Monte Carlo simulation, and an MCP server for AI agents.

Pure Go backend + React frontend, single-container deployment, SQLite persistence (optional PostgreSQL).

Features

• Position management: unified management of funds + stocks (A-shares / HK stocks / US stocks), transaction CRUD, automatic snapshot recalculation

• Quantitative analysis: XIRR annualized return, maximum drawdown, portfolio NAV trends, profit & loss distribution, Monte Carlo simulation, correlation heatmap, fund comparison radar, DCA backtesting

• Look-through analysis: drills through fund holdings to the underlying stocks, aggregated by industry

• MCP server: AI agent tools (portfolio / transactions / admin / market / analysis / report), Streamable HTTP transport, Bearer key authentication

• Dual themes: light / dark theme, red for gains, green for losses

Related MCP server: Wealth Management MCP

Tech stack

Quick start

# 测试
go test ./... -count=1
npm ci && npm test

# 构建
go build -o bin/fund-dashboard ./cmd/fund-dashboard
npm run build --workspace packages/web

# 容器
docker build -f deploy/Dockerfile -t fund-dashboard:local .

Documentation

Releases

This project follows Semantic Versioning. Releases are triggered by Git tags:

./scripts/release.sh 2.0.0   # 归并 CHANGELOG + 打 tag v2.0.0 + 推送

Once a tag is pushed, GitHub Actions automatically builds multi-architecture images (GHCR) and creates a Release, with release notes taken from CHANGELOG.md. To pull an image:

docker pull ghcr.io/deliciousbuding/fund-dashboard:latest

Contributing

Issues and PRs are welcome. Development workflow: create a feature/* branch from main, and open a PR back to main. See CONTRIBUTING.md.

License: Apache-2.0