Item detail

ZhuLinsen/alphasift

ZhuLinsen/alphasift (AlphaSift) is an Apache-2.0-licensed, open-source agent-native stock discovery and ranking engine that scans a broad market universe, applies auditable YAML strategies, enriches candidates with optional market context, ranks them with deterministic factors plus optional LLM judgment, and saves runs for later T+N evaluation, so quant-research engineers, AI-trading-platform buil

Score7.8
Popularity7.6
Riskmedium
TierSilver
Score breakdown
Usefulness7.0
Novelty8.0
Momentum7.0
Maturity5.8
Open-source/build8.4
Evidence7.2
Workflow potential8.6
Setup ease6.4

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for quant-research engineers, AI-trading-platform builders, and finance-LLM application teams who need an Apache-2.0-licensed, open-source agent-native stock discovery and ranking engine that scans a broad market universe, applies auditable YAML strategies, enriches candidates with optional market context, ranks them with deterministic factors plus optional LLM judgment, and saves runs for

Who should use it

quant-research engineers who need an Apache-2.0-licensed, open-source agent-native stock discovery and ranking engine with auditable YAML strategiesAI-trading-platform builders who want deterministic factors plus optional LLM judgment and a T+N evaluation loop on saved runsfinance-LLM application teams who need an agent-native stock-screening stack with an `SKILL.md` interface so AI agents can call itopen-source contributors who want an Apache-2.0-licensed alternative to hand-rolled market-data-plus-LLM screening notebooks

Who should skip it

Skip or sandbox it if you cannot review permissions, data access, and failure modes before use.

Risk explanation

It is an Apache-2.0-licensed agent-native stock discovery and ranking engine that ships research / engineering output and explicitly is not investment advice, so review which market-data sources and LLM keys the engine is allowed to call, scope which strategies are run in production, confirm that the LLM-ranking layer is sandboxed with an isolated API key before any real-money decision, and never treat AlphaSift output as buy / sell instructions.

Evidence links

Closest alternatives / related signals

stock-screeningai-tradingfinancequantyaml-strategiesllm-rankingagent-nativeevaluation