#semantic-search

Encrypted, fully offline agentic memory. One click install, GUI w/ memory map, all OS and agents. Logically and mathematically superior storage and retrieval.

Vector Graph RAG for code & docs with Persistent Chat-Session Memory — BM25 (multi-lang), AST chunking. Hybrid, Compute, Scan, Timeline, Absence, Salience. Graph + temporal knowledge. Privacy Stamps. Source Adapters. Chat summarisation + verbatim copy + free scan. Git indexing. CLI, MCP and Claude Code plugin. Ollama or cloud LLMs. Dashboard.

AI-agent friendly CLI for Exa — neural web search, URL crawling, and deep research from the terminal. Clean JSON output.

Convert document collections to verified Markdown, package them encrypted, and expose them to agents over MCP

Local memory + cron scheduling for Cursor agents. Recall past sessions, schedule playbooks, MCP-native.

Upstash Vector Database PHP Client, Upsert, Query and Range vectors

Rust implementation of TurboQuant, PolarQuant, and QJL — zero-overhead vector quantization for semantic search and KV cache compression (ICLR 2026)

Persistent memory layer for Claude Code. Zero API key. Zero config. The only tool that tells compact what to preserve.

A fractal memory plugin and mcp server for opencode.

该仓库未发布描述。

A local knowledge vault for your AI agents — saves tokens, remembers across sessions, and turns every model into a disciplined engineer.

Lightweight QMD alternative: fully local hybrid search engine (BM25 + vector + rerank) and MCP server in a single ~15MB Go binary. No Node.js. Runs on Raspberry Pi.