# QuantaAlpha/QuantaAlpha

QuantaAlpha transforms how you discover quantitative alpha factors by combining LLM intelligence with evolutionary strategies. Just describe your research direction, and watch as factors are automatically mined, evolved, and validated through self-evolving trajectories.

Repository: https://github.com/QuantaAlpha/QuantaAlpha
Canonical: https://ross.abutalabs.com/products/quantaalpha
Language: Python
License Family: other
Topics: code, codeagent, factor-mining, self-evolving, quantaalpha
Last push: 2026-06-29T16:55:22+00:00

## Health v2 (maintenance only)
Score: 56/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 90, release rhythm 35, longevity 15
- inputs: {"age_days": 217, "days_push": 65, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1466, forks 286 (observed 2026-08-28T04:04:48.679211+00:00)

## What it is
QuantaAlpha is an LLM-driven framework for mining quantitative alpha factors using a trajectory-based self-evolving paradigm. Users describe a research direction in natural language, and the system automatically generates, evolves, and validates factors through evolutionary strategies with structured hypothesis-code constraints.

## Use cases
- mine quantitative alpha factors with LLMs
- automate factor discovery for trading strategies
- evolve and validate quant factors using evolutionary search
- describe a research idea and get candidate factors generated
- run walk-forward validation on mined factors
- apply LLM agents to quantitative research workflows

## When to choose
- you want to automate quantitative factor mining with LLM intelligence
- you need evolutionary, trajectory-based factor generation and validation
- you prefer describing research goals in natural language rather than coding factor formulas by hand

## When to avoid
- you need a battle-tested production trading system rather than a research framework
- you require a permissively licensed dependency and cannot accept unclear licensing
- you need a no-LLM, purely statistical factor research pipeline

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, llm-inference, machine-learning, data-science, workflow-automation
- domain: fintech, large-language-models, machine-learning, data-science
- platform: python, cli, cross-platform
- tags: quantitative-finance, factor-mining, alpha-research, evolutionary-algorithms, llm-driven, self-evolving, trading, ai-agents

## Member repositories
- QuantaAlpha/QuantaAlpha (main) score 56

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:48.679211+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 2026-08-30T04:35:02.480241+00:00, confidence not recorded.
  - readme: https://github.com/QuantaAlpha/QuantaAlpha (fetched 2026-08-28T04:04:48.679211+00:00, sha 2627b7228fac)
- Data as of 2026-08-30T08:39:29.467469+00:00.