Vibe-Research: An investment research workbench for China A-shares, US stocks, and HK stocks.
What problem it solves
The project brings market monitoring, watchlists, portfolio records, research, news, backtesting, and report management into one workbench across China A-shares, US stocks, and HK stocks. It also keeps research records and imported materials on the user's computer while allowing research to be conducted with local AI subscriptions or compatible model APIs.
Key features
Unified Market Research Workspace — The workbench combines indices, watchlists, portfolio performance, daily reviews, industry research, company analysis, backtesting, and a report library across three equity markets.
Source: README
Structured Company Research — Company research follows six stages, preserving source materials, calculation details, conflicts, and data gaps alongside the generated report.
Source: README
Local Research Materials and Records — Users can import PDF, DOCX, TXT, MD, or CSV materials, ask questions with traceable citations, and retain research, debate, and backtest reports locally.
Source: README
Backtesting and Portfolio Review — Natural-language rules can be tested against historical data and benchmarked against market indices, while transaction-ledger records support portfolio diagnostics and historical scenario review.
Source: README
Flexible AI Access — The workbench supports locally authenticated Claude Code, Codex, and WorkBuddy subscriptions as well as model APIs that implement Chat Completions and function calling.
Source: README
Quick start
Copied verbatim from the project's README.
git clone https://github.com/simonlin1212/Vibe-Research.git vibe-research-agent
cd vibe-research-agent
scripts/setup
scripts/startclaude mcp add vibe-research -- node "$(pwd)/orchestrator/src/mcp.ts"Who it may suit
This may suit individual investors and equity researchers who want a self-hosted workbench spanning China A-shares, US stocks, and HK stocks. It may also suit users who keep research materials and records locally and work with local AI subscriptions or compatible model APIs.
Topics to discuss
Which data sources and evidence conventions should the community prioritize for each market?
How should locally stored research records and imported documents evolve while keeping their provenance transparent?
Which AI workflows offer the most useful balance between source verification, reproducibility, and privacy?
Written by ReadmeX AI from the project's README, source and public GitHub data; it may contain mistakes.
Read the original README https://github.com/simonlin1212/Vibe-Research#readme
ReadmeX opened this community for a trending project; it is not run by the project. Maintainers can claim it from the community page.
Comments
…