Features
Autonomous spreadsheet analysis via natural language queries
Multi-agent parallel simulation runs with traceability
Agentic reasoning for domain-specific modeling
Raw data to accurate model building
Complex spreadsheet question answering
Collaborative multi-agent systems for workflows
Full traceability of agent reasoning steps
Research-backed agent architecture from computational neuroscience
Knowledge graph extraction from raw text
Hierarchical community clustering (Leiden)
Community summary generation (bottom-up)
Global search using community summaries
Local search by entity neighborhood fan-out
DRIFT search blending local and community context
Basic search (vector similarity fallback)
Prompt auto-tuning for better out-of-box results
Indexing pipeline with TextUnits
Entity, relationship, and claim extraction
Configuration file management (YAML)
Versioning and migration support
Initial public release under MIT License
