# ginlix-ai/LangAlpha

Claude Code for Financial Market

Repository: https://github.com/ginlix-ai/LangAlpha
Canonical: https://ross.abutalabs.com/products/langalpha
Homepage: https://langalpha.ai
Language: Python
License: Apache-2.0
License Family: permissive
Topics: agent, investment, langchain, langraph, llm, mcp, skills, trading
Last push: 2026-08-26T19:56:00+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 96, longevity 16
- inputs: {"age_days": 228, "days_push": 7, "days_rel": 28, "gap_med": 5.5, "n_releases_24m": 13}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1696, forks 284 (observed 2026-08-28T04:05:23.825412+00:00)

## What it is
LangAlpha is an open-source agentic AI harness for financial market research and investment decision support, inspired by code-agent harnesses like Claude Code. It provides persistent workspaces, parallel research subagents, MCP tool integration, and access to market data such as prices, SEC filings, options chains, macro series, and news.

## Use cases
- generate long/short pair-trade ideas from market screening
- build and iteratively refine an investment thesis with an AI agent
- analyze SEC filings and earnings call transcripts with citations
- run deep research on a sector rotation or macro theme
- track and update positions as new market data arrives
- automate scheduled market research workflows
- chat with an agent about stock fundamentals and options chains

## When to choose
- you want an open-source, self-hostable AI analyst for equity research
- you need persistent, compounding research workspaces rather than one-shot Q&A
- you want agents grounded in primary sources like SEC EDGAR filings and earnings transcripts
- you want to extend an agent with custom MCP tools and skills for finance

## When to avoid
- you need guaranteed-accurate financial advice or regulatory compliance
- you want a simple charting or portfolio tracker without LLM agents
- you need real-time HFT execution rather than research support
- you cannot work with an early-stage project requiring Python 3.13+

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, mcp, rag, web-scraping, chat-interface, data-visualization, analytics, trading, llm-inference
- domain: artificial-intelligence, fintech, large-language-models, data-science
- platform: python, self-hosted, cross-platform
- tags: financial-research, investment-agent, vibe-investing, langchain, langgraph, subagents, market-analysis, sec-filings, equity-research, trading-ideas, ai-agents, finance, web-server

## Member repositories
- ginlix-ai/LangAlpha (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:23.825412+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:37:53.789292+00:00, confidence not recorded.
  - readme: https://github.com/ginlix-ai/LangAlpha (fetched 2026-08-28T04:05:23.825412+00:00, sha ae6f41b2faf4)
  - homepage: https://langalpha.ai (fetched 2026-08-29T11:12:44.395209+00:00, sha 44812dc898fe)
  - site_page: https://langalpha.ai/pricing (fetched 2026-08-29T11:12:44.404362+00:00, sha 6584d6a6d63b)
- Data as of 2026-08-30T08:39:29.467469+00:00.