An open-source, pip-installable Python library that quantitatively evaluates RAG pipelines using LLM-as-a-Judge methodology.
A minimal generic agent-loop framework on top of LangGraph: build_agent_graph assembles a standard ReAct loop (ai / tool / history / compaction / finish) with dependency-injected llm, checkpointer, tools, and runtime_context.
Point-in-time crypto market sentiment API. As-of buckets, a reconstructed flag and a public hash log, so backtests have no lookahead. Free tier included.
An autonomous, iterative task runner for AI coding agents.
Scan Jupyter notebooks, Python scripts, and ML repos before review, sharing, or production — catches reproducibility gaps, data leakage, PII & secret leaks, missing dependencies, GenAI/LLM risks, and handoff blockers.
