Search results
369 packages found
Sort by: Default
- Default
- Most downloaded this week
- Most downloaded this month
- Most dependents
- Recently published
Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level
- llama
- llama-cpp
- llama.cpp
- bindings
- ai
- cmake
- cmake-js
- prebuilt-binaries
- llm
- gguf
- metal
- cuda
- vulkan
- grammar
- View more
A JavaScript interface for chroma
<p align="center"> <img height="100" width="100" alt="LlamaIndex logo" src="https://ts.llamaindex.ai/square.svg" /> </p> <h1 align="center">LlamaIndex.TS</h1> <h3 align="center"> Data framework for your LLM application. </h3>
- llm
- llama
- openai
- gpt
- data science
- prompt
- prompt engineering
- chatgpt
- machine learning
- ml
- embedding
- vectorstore
- data framework
- llamaindex
The Retrieval-Augmented Generation (RAG) module contains document processing and embedding utilities.
- rag
- retrieval-augmented-generation
- vector-search
- vectorstore
- embeddings
- embedding
- document-processing
- semantic-search
- text-splitting
- chunking
- ai
- llm
- llms
- typescript
This library provides a high-performance Node.js client for Baseten.co endpoints including embeddings, reranking, and classification. It was built for massive concurrent POST requests to any URL, also outside of baseten.co. The PerformanceClient is built
Vercel AI SDK Provider for Ollama using official ollama-js library
- ai
- vercel-ai
- ollama
- ai-sdk
- llm
- language-model
- embedding
- chat
- local-ai
- provider
- typescript
- embeddings
- tool-calling
Scraper for oEmbed, Twitter Cards and Open Graph metadata - fast and Promise-based
- oembed
- twitter-cards
- open-graph-protocol
- open-graph
- ogp
- scraper
- scraping
- embedding
- embed
- iframe
- metadata
- node.js
- fast
A node package to retrieve fetch local or remote files in base64 encoding.
t-SNE implementation in JavaScript
Four-layer local memory system plugin for OpenClaw — auto-captures, structures, and profiles conversational knowledge using local LLM + SQLite vector search (L0→L1→L2→L3 pipeline)
- openclaw
- openclaw-plugin
- memory
- ai-memory
- long-term-memory
- vector-search
- sqlite-vec
- llm
- conversation
- persona
- scene-extraction
- embedding
Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level
- llama
- llama-cpp
- llama.cpp
- bindings
- ai
- cmake
- cmake-js
- prebuilt-binaries
- llm
- gguf
- metal
- cuda
- vulkan
- grammar
- View more
A lightweight, lightning-fast, in-process vector database
Proxy renderer for Vue.js based on @remote-ui
Components for interactive embedding visualization
The TypeScript library for building AI applications.
Rust + N-API: HTML sanitization, extraction, and boilerstrip.
SQLite vector search extension for Node.js - Cross-platform vector embeddings and similarity search
- sqlite
- vector
- embedding
- ai
- machine-learning
- similarity-search
- semantic-search
- vector-database
- sqlite-extension
An Eleventy plugin that allows you to quickly add common web embeds to markdown posts, using only their URLs
- 11ty
- eleventy
- eleventy-plugin
- embeds
- embedding
- mastodon
- media
- openstreetmap
- soundcloud
- spotify
- tiktok
- twitch
- View more
Complete local model SDK for EASBot - Transformers.js + ONNX implementation supporting both Language Model (text generation) and Embedding (text embedding) with full AI SDK v2 compatibility
- easbot
- local-model
- language-model
- embedding
- transformers
- onnx
- qwen
- bge
- ai-sdk
- text-generation
- text-embedding
- chinese-nlp
- offline-ai
- privacy-first
跨项目知识库 MCP 服务,支持三层搜索(文本/TF-IDF/语义向量),提供 Web UI 管理界面