# LLMQuant/quant-mind

QuantMind is an agent-native knowledge extraction and retrieval framework for quantitative finance.

Repository: https://github.com/LLMQuant/quant-mind
Canonical: https://ross.abutalabs.com/products/quant-mind
Homepage: http://llmquantdata.com/
Language: Python
License: MIT
License Family: permissive
Topics: quantitative-finance, quantitative-research, data, knowledge, llm, pipeline, workflow, agent, context-engineering, harness-engineering
Last push: 2026-08-15T07:49:16+00:00

## Health v2 (maintenance only)
Score: 64/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 97, release rhythm 35, longevity 38
- inputs: {"age_days": 537, "days_push": 18, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2630, forks 450 (observed 2026-08-28T04:07:05.526796+00:00)

## What it is
QuantMind is an agent-native Python framework that refines raw financial information such as papers, news, and SEC filings into typed, timestamped, citation-preserving structured knowledge for retrieval and reasoning. It is designed so coding agents can build and verify knowledge pipelines inside the checkout, and it complements the LLMQuant Data platform with its MCP server and financial data APIs.

## Use cases
- extract structured knowledge from financial research papers
- build a pipeline to parse SEC filings into typed knowledge
- collect and structure financial news for LLM agents
- give trading agents retrieval-ready financial context
- run deterministic preprocessing of financial documents with provenance
- connect financial data to Claude or Cursor via MCP
- build time-queryable knowledge bases of market information

## When to choose
- you need reproducible, citation-preserving knowledge extraction from financial sources
- you want an agent-oriented repo where coding agents build pipelines against contracts and skills
- you are building LLM trading or quant research agents that need structured financial context
- you want an importable Python library plus MCP integration for financial data

## When to avoid
- you need a general-purpose RAG framework outside finance
- you want a turnkey backtesting or live-trading engine rather than knowledge extraction
- you need a no-code tool for non-technical users
- you require guaranteed long-term support from a vendor rather than an MIT-licensed open-source project

## Facets
- artifact type: framework
- maturity: active
- function: rag, etl, nlp, agent-framework, mcp, search-engine, parser, data-science
- domain: fintech, large-language-models
- platform: python, cli, cross-platform
- tags: quantitative-finance, knowledge-extraction, financial-data, agent-native, context-engineering, sec-filings, research-papers, trading, mcp-server, llm-pipeline, ai-agents, retrieval-augmented-generation, data-engineering, natural-language-processing

## Member repositories
- LLMQuant/quant-mind (main) score 64

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:05.526796+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 2026-08-30T02:19:37.817820+00:00, confidence not recorded.
  - readme: https://github.com/LLMQuant/quant-mind (fetched 2026-08-28T04:07:05.526796+00:00, sha a99a80943b8d)
  - homepage: http://llmquantdata.com/ (fetched 2026-08-29T10:02:41.925603+00:00, sha 3485a5b85ca0)
  - site_page: https://docs.llmquantdata.com/ (fetched 2026-08-29T10:02:41.954815+00:00, sha d1f86a007b0f)
  - site_page: https://llmquantdata.com/pricing (fetched 2026-08-29T10:02:41.956680+00:00, sha 7716c6b35041)
  - site_page: https://llmquantdata.com/changelog (fetched 2026-08-29T10:02:41.958433+00:00, sha cd43cdfaf393)
- Data as of 2026-08-30T08:39:29.467469+00:00.