Evaluation

Evaluation, tracing, prompt testing, and monitoring tools for LLM applications.

Tools for documentation, code search, testing, review, observability, and engineering workflow acceleration.

Open-source and developer-focused resources for finance data, backtesting, analytics, and trading research.

Agent frameworks and projects for building autonomous or semi-autonomous software workflows.

Retrieval-augmented generation frameworks, vector databases, and data tooling for knowledge-connected LLM apps.

Open-source and locally controllable AI tools for builders who need privacy, portability, or reduced vendor lock-in.

Open-source observability and evaluation tool for LLM and ML applications.

Evaluation framework for RAG and LLM application quality checks.