Repolode
Submit
ginlix-ai

ginlix-ai/LangAlpha

Open-source AI agent harness for market research and trading, with research workspaces, scheduled watches, and governed brokerage orders.

Open-source alternative to:Bloomberg TerminalPerplexity Finance

View on GitHubWebsite
Stars
2,245
Forks
378
Open issues
39
Last commit
20 hours ago

Repolode describes open-source projects and does not give investment advice. Trading and investing can lose money: assess the risk yourself and follow the laws where you live before using this project.

What is it?

LangAlpha is an open-source harness for AI agents that work on financial markets. It keeps an investment thesis in a persistent workspace, so research, files, notes and chat history carry over from one session to the next instead of starting from scratch each time. Agents can split a question across parallel subagents that read SEC filings, pull market data and options, and run calculations in a sandboxed Python environment, then produce deliverables such as Excel models, PDF and HTML reports, and interactive dashboards.

The project also covers monitoring and execution. Automations can run scheduled briefs or wake an agent when a stock crosses a price threshold or moves a set percentage, with results sent to the web app or chat channels such as Slack and Discord. For brokerage accounts, it supports Robinhood, Interactive Brokers, moomoo and Webull, where each connection's permissions are chosen by the user and every order passes through one governed path that requires approval.

Self-hosting uses Docker Compose with Postgres, Redis, a FastAPI backend and a web app. The model layer works with multiple providers, including Claude, ChatGPT, OpenAI-compatible APIs and local models through Ollama, LM Studio or vLLM.

Key features

  • 01Persistent research workspaces that keep files, notes and threads across sessions.
  • 02Parallel subagents for research, with a workflow mode for large multi-company studies.
  • 03Python sandbox for market data analysis, valuation models and charts.
  • 04Scheduled automations and price or percentage move triggers delivered to chat channels.
  • 05Brokerage connections with per-capability permissions and approval before live orders.
  • 06Sources panel that records the data, filings and web pages behind each answer.

Use cases

  • Building and maintaining an investment thesis over weeks or months.
  • Producing equity research deliverables such as initiation reports and DCF models.
  • Setting up price alerts and scheduled morning briefs for a watchlist.
  • Self-hosting an AI research assistant with your own model keys and data sources.

Quick start

  1. 1

    Clone the repository

  2. 2

    Follow the README setup instructions to configure and start the app

Things to know

  • Trading features place real orders on brokerage accounts, so careful permission setup matters.
  • Brokerage support is limited to four providers, and some features vary by broker.

In collections

Open-source AI agent frameworks & appsMCP serversOpen-source personal AI agents

Topics

#ai-agent#finance#trading#llm#langchain#langgraph#mcp#personal-agent#agent#investment

FAQ

What is LangAlpha?
Open-source AI agent harness for market research and trading, with research workspaces, scheduled watches, and governed brokerage orders. LangAlpha is an open-source harness for AI agents that work on financial markets. It keeps an investment thesis in a persistent workspace, so research, files, notes and chat history carry over from one session to the next instead of starting from scratch each time. Agents can split a question across parallel subagents that read SEC filings, pull market data and options, and run calculations in a sandboxed Python environment, then produce deliverables such as Excel models, PDF and HTML reports, and interactive dashboards.
Is LangAlpha free to use? What license does it have?
LangAlpha is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
Is LangAlpha still maintained?
Actively maintained. The last commit to LangAlpha was on Nov 6, 2026.
What can I use LangAlpha for?
Building and maintaining an investment thesis over weeks or months. Producing equity research deliverables such as initiation reports and DCF models. Setting up price alerts and scheduled morning briefs for a watchlist. Self-hosting an AI research assistant with your own model keys and data sources.
How do I install LangAlpha?
Clone the repository Follow the README setup instructions to configure and start the app
Where can I get LangAlpha?
The source code and installation instructions are on GitHub: https://github.com/ginlix-ai/LangAlpha

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects