Back to browse
Shivvr – Ephemeral semantic embedding and cognitive agent service

Shivvr – Ephemeral semantic embedding and cognitive agent service

by kordlessagain·Jun 16, 2026·2 points·0 comments

AI Analysis

●●SolidBig BrainNiche Gem

Orthogonal matrix encryption preserves cosine similarity while keeping embeddings private.

Strengths
  • FST-BM25 hybrid search blends dense vectors with sparse lexical indices for guardrails.
  • Native MCP server enables zero-config Claude Code and Antigravity integration.
  • Ephemeral RwLock<HashMap> storage means pure in-memory compute with no persistence.
Weaknesses
  • Ephemeral storage limits practical production use cases significantly.
  • Cognitive agent service space already has many established competitors.
Category
Target Audience

AI engineers building agent systems with privacy requirements

Similar To

LangChain · LlamaIndex · Continue

Similar Projects

AI/ML●●●Banger

YantrikDB – persistent memory for AI agents

Bundled 7MB embedder means zero network calls or model downloads for agent memory.

Zero to OneWizardrySolve My Problem
pranabsarkar
111mo ago