RAG Memory Configuration
Memory benchmarks (full N=500, gpt-4o reader) round Top-5 65.7%, session Top-5 71.4%, round Top-10 72.0%). Benchmarks · Run JSONs · SOTA writeup
HyDE Retrieval
HyDE improves RAG and memory retrieval by generating a hypothetical answer before
Deep Research & Query Classification
Ask an agent "what's 2+2" and it should answer instantly. Ask it "what are the latest treatment options for drug-resistant tuberculosis" and it should go dig through medical literature, cross-reference sources, identify gaps, and come back with citations.
Citation Verification
Per-claim citation verification for AI agents: decompose answers into atomic claims, embed against retrieved sources, verdict ladder (supported/weak/unverifiable/contradicted) with optional NLI contradiction check and web-search fallback.
Reranker Chain
Configurable multi-stage reranking pipeline for search results and RAG retrieval.
Multimodal RAG (Image + Audio)
Memory benchmarks (full N=500, gpt-4o reader): 85.6% on LongMemEval-S at $0.0090 per correct, +1.4 points above Mastra Observational Memory (84.23%). 70.2% on LongMemEval-M on the 1.5M-token / 500-session haystack variant — the only open-source library on the public record above 65% on M with publicly reproducible methodology. The same text-first retrieval pipeline that produced these numbers is what the multimodal pattern below indexes against (derived captions, transcripts, OCR, document text) once you have a text representation. Benchmarks · Run JSONs · SOTA writeup
Document Ingestion
Ingest PDFs, DOCX, HTML, Markdown, CSV, JSON, YAML, text, and URLs into the agent memory system with configurable chunking and multimodal image extraction.