agentskillexchange Run persistent finance research workspaces with LangAlpha
Create persistent investment-research workspaces where agents process market data, filings, models, charts, and thesis updates over time.
Prerequisites
Python 3.12+, LangAlpha backend and web or CLI/TUI, configured model credentials, optional financial data provider keys and MCP servers
Installation
Use the upstream install or setup path that matches your environment:
- All tiers are enabled by default. To run with free data only (Yahoo Finance), run make config with prompted selection. You can also edit agent_config.yaml manually.
- git clone https://github.com/ginlix-ai/langalpha.git
- make config # interactive wizard — creates .env, configures LLM, data sources, sandbox, and search
- make up # starts PostgreSQL, Redis, backend, and frontend
Requirements and caveats from upstream:
- Programmatic Tool Calling (PTC) — The agent writes and executes Python to process financial data from mcp servers instead of pouring raw data into the LLM context window, enabling complex multi-step analysis while...
- LLM["LLM"] -- "1 — Writes Python" --> EC["ExecuteCode Tool"]
Basic usage or getting-started notes:
Getting Started •
EC -- "2 — Sends to sandbox" --> Run["Code Runner"]
Run -- "3 — import tools.*" --> Wrappers["Generated WrappersOne module per MCP server"]
Extracted from upstream docs: https://raw.githubusercontent.com/ginlix-ai/LangAlpha/HEAD/README.md