Enables screening LLM input and output through cost-tiered safety checks with per-tenant budgets, returning allow, block, or review decisions. It exposes a JSON-RPC screen tool that isolates tenant spend and falls back to a configurable policy on provider failure or budget exhaustion.
Enables fully air-gapped multimodal document processing by fusing layout parsing with text extraction to produce ordered, labelled reading blocks and reconstructed text via an MCP stdio server.
Enables incremental model scoring over an append-only event log, with a tamper-evident, hash-chained audit trail so every decision can be reviewed and independently re-verified.
Enables retail merchandising recommendations via an MCP server that ranks candidates with a Thompson-sampling bandit, tracks per-tenant monthly spend caps, and exposes recommend, record_feedback, and budget_status tools over JSON-RPC stdio.
Provides MCP tools for edge-based pharmaceutical shipment disposition decisions, returning release, review, or quarantine outcomes while recording every decision in a tamper-evident, hash-chained audit trail.
Enables data-quality workflows by applying named, deterministic transformations to records and generating replayable lineage with content hashes, so users can verify that cleaned results follow exactly from raw inputs.
MCP server for search ranking evaluation and drift monitoring, enabling ranking of documents, scoring against editorial judgments, and detecting ranking regressions with a tamper-evident audit trail.
Reconstructs the reading order of laid-out document blocks from their bounding boxes and exposes it over the Model Context Protocol, with deterministic offline operation and optional model-based refinement.