NLP

Calculate confidence scores for OpenAI JSON outputs

Transform natural language into terminal commands with AI. Supports OpenAI, OpenRouter, and Ollama.

Typescript SDK for using CONVA AI Copilots

A complete Retrieval-Augmented Generation system using pgvector, LangChain, and LangGraph for Node.js applications with dynamic embedding and model providers, structured data queries, and chat history - supports OpenAI, Anthropic, HuggingFace, Azure, Goog

OpenClaw CloudPhone plugin that gives AI agents cloud device management and UI automation capabilities through natural language, including device queries, power actions, screenshots, taps, swipes, and text input.

One API, every AI model, instant switching. Change from GPT-4 to Gemini to local models with a single config update. LLMForge is the lightweight, TypeScript-first solution for multi-provider AI applications with zero vendor lock-in.

Blazing-fast, zero-cost local LLM router. Classify and route prompts to specialized AI models (OpenAI, Claude, Gemini, Llama) with <1ms latency using heuristic rules.

A lightweight, multi-provider Node.js library for text tokenization, embedding, and context management

Parse partial JSON generated by LLM

Natural language shell command generator and executor powered by AI

A simple, type-safe OpenAI TypeScript client for creating chatbots and AI-powered applications, providing a convenient interface to the OpenAI API and supporting the GPT-3.5 Turbo model.

TypeScript bridge for recursive-llm: Recursive Language Models for unbounded context processing with structured outputs

LU (Layer Understanding) is a lightweight framework for controlled chatbot interactions with LLMs, action orchestration, and retrieval-augmented generation (RAG).

Semantic Cache is a library for caching natural text based on semantic similarity using LanceDB with multiple embedding provider support (OpenAI, Google Gemini, VoyageAI)

CLI AI Assistant v3 - Natural language to shell commands with persistent REPL session

AI-powered CLI for managing Cosmic CMS through natural language and direct commands

Javascript BPE Encoder Decoder for GPT-2 / GPT-3. The "gpt-3-encoder" module provides functions for encoding and decoding text using the Byte Pair Encoding (BPE) algorithm. It can be used to process text data for input into machine learning models, or to

A Convex component for adding natural language database queries to your app.