TurboQuant: Extreme compression for AI models with GGUF and SafeTensors export

Self-learning LLM runtime — TurboQuant KV-cache (6-8x compression), SONA adaptive learning, FlashAttention, speculative decoding, GGUF inference

TurboQuant WASM SIMD vector compression — 3 bits/dim with fast dot product. Requires relaxed SIMD (Chrome 114+, Firefox 128+, Safari 18+, Node 20+)

TypeScript implementation of Google's TurboQuant algorithm for near-optimal vector quantization

Fast, calibrated tool selection and schema pruning for AI agents using TypeSafe System One and TurboQuant vector search.

Persistent browser-local TurboQuant vector search backed by IndexedDB

TurboQuant vector quantization for the browser — compress embeddings 8x, search client-side

Self-learning LLM runtime — TurboQuant KV-cache (6-8x compression), SONA adaptive learning, FlashAttention, speculative decoding, GGUF inference

Self-learning LLM runtime — TurboQuant KV-cache (6-8x compression), SONA adaptive learning, FlashAttention, speculative decoding, GGUF inference

AINative ZeroDB MCP Server - 77 operations for vector search, TurboQuant vector compression (PolarQuant + QJL), NoSQL, dedicated PostgreSQL management, files, events, RLHF, and persistent memory for AI agents with enterprise security. All tools annotated

Compressed vector search for DuckDB — Google TurboQuant quantization, IVF indexing, incremental CRUD, cosine/L2/dot

Vector search for JSON datasets. Build quantized indexes and search with WASM SIMD.

Fully local semantic code search for your AI assistant. Powered by Google TurboQuant vector quantization and jina-v2-base-code embeddings (768-dim, 8K context, 30+ languages). One-command install, zero config, zero cloud. npm install -g turboindex

Isomorphic text embeddings with Harrier ONNX int8 plus exact and TurboQuant-style vector search.

Data-oblivious, zero-training vector quantization and nearest-neighbor search for TypeScript — a clean-room implementation of Google Research's TurboQuant. Runs in Node, browsers, Bun, and edge/serverless runtimes.

Backend-free semantic search for any site. Index content into a tiny TurboQuant-compressed pack and search it locally in the browser — no server, no per-query cost.

Semantic code knowledge graph for Kiro: fewer tool calls, instant symbol lookups, 100% local.

Browser UI for the pi coding agent — self-hosted React workbench with chat, file browser, terminal, git panel, and session tree.

CLI per setup automatico GSD + Qdrant in qualsiasi progetto Node.js

LeafEngines MCP Server — Patent-protected agricultural intelligence for AI agents. 1,092+ downloads. Free tier with test key leaf-test-370df0a2e62e. Soil analysis, crop recommendations, environmental intelligence from USDA, EPA, NOAA data. Works with Clau