Latest Blog
Speaker Diarization: How Voice Boundaries Shape Searchable Home Audio
See how speech boundaries and speaker clusters create searchable audio, where overlap causes errors, and how to audit diarization locally.
OCR Layout Recovery: Why Reading Order Determines Table and Form Accuracy
Learn why OCR text can be correct yet structurally wrong, how reading order is recovered, and how to test tables and forms before indexing.
20 Open-Source Jev Projects You Can Try in 2026: MCP, Coding Agents, Browser Automation & More
Explore 20 open-source Jev projects for MCP, coding agents, browser automation, routing, games and data pipelines, plus what Jev actually decides.
Multilingual Embeddings: How One Vector Space Connects Household Documents Across Languages
See how aligned embeddings connect documents across languages, why retrieval quality varies, and how to test cross-language evidence coverage locally.
Agent Memory Conflicts: Why Recent Corrections Can Lose to Repeated Older Facts
Learn how duplicate old memories overpower corrections, where recency rules fail, and how to test supersession in a private agent memory store.
Private Search Reranking: How a Second Model Changes the Final Evidence Order
See why first-stage similarity and second-stage relevance disagree, when reranking helps private RAG, and how to evaluate reordered evidence.
Local LLM Sampling: Why Decoding Settings Change Repetition and Stability
Learn how temperature, top-p, min-p, seeds, and penalties interactโand how to test decoding settings without confusing randomness with quality.
Vector Index Tombstones: How Deleted Files Remain Searchable Until Compaction
Understand logical deletion, compaction, stale search paths, and the tests needed to prove a removed file no longer influences local RAG.
