A lightweight framework for benchmarking multimodal AI agents with parallel execution, prompt variation, and automated evaluation.
DB-native knowledge graph: a typed graph of Markdown-content nodes and typed edges in one SQLite file, with an append-only event log, node versions, undo, and wikilink materialization — behind a deterministic, LLM-free service layer and a JSON-emitting CLI.
Second Opinion Labs Python SDK — tracing (spans, PHI redaction, Anthropic wrapper) + custom evaluators (Form A) for medical AI agents
Query-aware, meaning-first LLM context compression. Local, zero-dependency core, transparent decisions, drop-in compatible API for hosted compression services.
Query-aware, meaning-first LLM context compression. Local, zero-dependency core, transparent decisions, drop-in compatible API for hosted compression services.
