Fast State-of-the-Art Static Embeddings
-
Updated
Nov 11, 2026 - Python
GeezerVisonThe World Wide Web, restored to 800 pixels of glory. |
| Home|About|Gaming cabinet|Archives|How it works|Starter sites |
GeezerVison is showing github.com — Build software better, together
#
model2vecHere are 35 public repositories matching this topic...Language: All
Filter by language
Sort: Most stars
Sort options
Fast State-of-the-Art Static Embeddings
Fast Multimodal Semantic Deduplication & Filtering
datasets preprocessing deduplication vicinity image-dataset-cleaning semantic-deduplication model2vec text-dataset-cleaning
Official Rust Implementation of Model2Vec
Pre-train Static Word Embeddings
A unified web extraction and stateful automation engine for AI. Replaces heavy testing frameworks with token-optimized browser control, deep research, and HITL.
rust proxy mcp vscode self-hosted knowledge-graph web-scraping stealth semantic-search automated-testing ai-agents dev-tools searchengine playwright searxng llm-tools anti-bot-bypass model2vec model-context-protocol
Turn speech into semantic paragraphs in real time, on a CPU (no GPU) — single-pass streaming chunker + Moonshine STT + a live mic demo. Plus a transcribe/chunk/summarize API.
python nlp streaming real-time podcast embeddings openai summarization speech-to-text transcription gradio whisper moonshine fastapi semantic-chunking model2vec
Fast hybrid code search for agents. Pure Go, drop-in MCP-compatible with semble.
CLI for semantic search on your computer. Searches text files and identifies the most relevant chunks to your query.
Fast hybrid (BM25 + semantic) local code search for AI agents - pure Rust, persistent index, MCP/gRPC servers, tree-sitter symbols
rust cli tree-sitter mcp grpc embeddings code-search semantic-search bm25 ai-agents rag hybrid-search model2vec model-context-protocol
Drag and drop your Excel or CSV file with a text column for batch calculating semantic similarity for your queries.
Local-first cross-corpus retrieval MCP server — model2vec embeddings + LanceDB (Tantivy BM25) + SQLite. One binary; hybrid (dense + BM25) search across markdown, code, and Claude Code sessions.
rust retrieval mcp embeddings semantic-search bm25 rag vector-search local-first vector-database hybrid-search lancedb model2vec mcp-server claude-code
벼리 — headless hybrid (lexical + semantic) search for a Markdown vault. No app, no GPU, no cloud. Korean/cross-lingual. Apache-2.0.
Blazingly fast word embeddings with Tokenlearn
Model2Vec inference in pure Zig.
Fast, local semantic search over web content for AI agents. Hybrid BM25 + potion-retrieval-32M embeddings, cross-page dedup, token-budget mode, MCP server, SearXNG bridge. ~90% fewer tokens than raw web_fetch.
python cli mcp embeddings semantic-search bm25 ai-agents claude rag searxng llm-tools retrieval-augmented-generation model2vec model-context-protocol web-research openclaw
Fact evidence-first brain with property graph + hybrid RAG. Search is deduction. ETL included.
go email mcp crm self-hosted knowledge-graph cypher brain fulltext bm25 onlyoffice deduction hnsw vector-search hybrid-search model2vec ladybugdb
Eternal memory, alive and lightning fast, for AI coding agents. One Rust binary, one SQLite file, automatic recall. Stable since 1.0.
An effort to build a holistic matching engine that supports regex, cucumber expressions, semantic phrases, and combinations of that. Could be useful for Guardrails, Caching systems etc. Can eventually be a symbolic AI engine
Local-first persistent memory engine for AI coding agents.
Describe a concept and instantly find the perfect word. A free reverse dictionary powered by AI that runs entirely in your browser — no sign-up, no tracking.
Add this topic to your repoTo associate your repository with the model2vec topic, visit your repo's landing page and select "manage topics." |
| You are visitor 01402503 — GeezerVison does not store the pages you look up. Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required. |