Popular repositories Loading
-
contamination-detector
contamination-detector PublicToolkit for detecting benchmark/eval-data contamination in LLM training corpora
Python
-
quant-analyst-agent
quant-analyst-agent PublicAutonomous equity-research agent: a ticker in, a sourced investment memo out. Claude tool-use loop over SEC EDGAR + market data, schema-constrained synthesis, every claim cited.
Python
-
market-pulse
market-pulse PublicWatchlist market-event monitor: deterministic dedupe before any model call, materiality scoring against a cached rubric, ranked digest. Claude prompt caching + structured outputs.
Python
-
compsheet
compsheet PublicTrading comps from SEC XBRL filings. The model picks peers and writes commentary; every number in a cell is computed in Python. n/a and nm are different answers.
Python
-
rag-eval-harness
rag-eval-harness PublicRAG evaluation harness: deterministic retrieval metrics, an LLM judge that is itself scored against human labels, and a regression gate that tells a real drop from noise.
Python
-
promptfort
promptfort PublicPrompt-injection red-teaming harness for your own LLM app: canary-based deterministic breach detection, switchable guardrail layers, and a per-category before/after scorecard.
Python
If the problem persists, check the GitHub status page or contact support.