Home
Market and global indices, watchlist and holdings P&L first, then a conversation with AI.
A research workbench for China A-shares, US and Hong Kong stocks. 168 data endpoints, six-stage company research, backtesting and portfolio checks run on your own computer. Through MCP, Claude Code, Codex or Cursor can fetch data, start research and read reports and evidence directly.
For Independent investors who want their own agent to fetch data and run research, and want the numbers in a report to trace back to their sources.
Runs on Windows 11, macOS and Linux with Node.js 22.18+ (24 LTS recommended), Python 3.11+ (3.12 recommended) and Git. Portable zips for Windows x64, Apple silicon and Intel Macs are also available; they are unsigned and have not been validated on physical machines. Remote cloud mode supports macOS and Linux only. Setup and verification scope in the README ↗



The work
One task through the system
Add the MCP server in Claude Code, Codex or Cursor, or choose a subscription or model API under Connect AI. A setting is saved only after a successful test.
The orchestrator fetches data through controlled scripts, saving raw responses with hashes. Research stages can call only five controlled tools.
Six stages: company profile, financials, earnings expectations, valuation, risks and report. Missing data is recorded as a gap, never as zero.
Numbers in the report carry evidence or calculation IDs, and the evidence appendix traces back to raw data. A number with no traceable source is replaced with an unverified marker and the run is marked incomplete. Records stay on your computer.
The workspace
Market and global indices, watchlist and holdings P&L first, then a conversation with AI.
Breadth, volume, short-term sentiment, index trend position, margin balances and fund flows. Blocks that fail to load say why instead of showing zero.
News radar and industry signals: news, filings and event leads, plus supply-chain signals such as GPU rental rates and monthly industry data.
Twenty sectors, each with step-by-step research prompts. Your AI researches the content; the product does not prefill it.
Company deep dive (six-stage research for A-shares, Hong Kong and US stocks), bull/bear debate (A-shares only for now), backtesting and a candidate screen.
Watchlist and holdings, an event calendar and after-close reminders. Holdings come from a trade ledger; there is no order placement.
Import your own research documents and ask questions with citations back to the source; research, backtest and debate reports are kept by date.
Choose a subscription or model API. Once the test passes, the whole workbench uses it.
MCP
Run this in the repository folder after setup. For Codex use codex mcp add with the same arguments; Cursor setup is in the README.
claude mcp add vibe-research -- node "$(pwd)/orchestrator/src/mcp.ts" Connect AI
Current product
Not done yet
Boundary