Search

Wrapper to call different LLMs and includes prompt management

An LLM Proxy that allows the user to interact with different language models from different providers using unified request and response formats.

extra-small AI SDK.

Load and use an LLM model directly in Electron. Experimental.

A Stencil web component library for LLM test runner functionality

Intelligent AI model router — route every LLM call to the cheapest model that can handle it

A simple and lightweight proxy for seamless integration with multiple LLM providers including OpenAI, Ollama, and Cloudflare AI

Regex-based prompt injection firewall for TypeScript. Zero dependencies, sub-millisecond, with neutralization mode.

Deterministic testing for NodeLLM powered AI systems

Bootstrap and run LLM-driven projects with structured workflows, specs, and task management

A lightweight TypeScript/JavaScript code indexer that generates comprehensive project maps for LLMs

Proxy to convert Anthropic API requests to OpenAI format for Claude Code

Industrial-grade testing framework for LLM prompts

Vercel AI SDK middleware for prompt-identifiers. Efficient ID compression for token optimization.

CLI tool to manage Claude Code configurations across multiple LLM providers

n8n nodes to interact with Google Gemini API for search and content generation

Token tracking, cost management, caching, and budget enforcement for LLM API calls (Node.js + TypeScript).

n8n community node for routing LLM requests through Pay-i proxy with cost tracking and budget enforcement

SmartGent custom nodes for n8n - AI-powered automation and intelligent workflow integrations including LiteLLM chat completions, SharePoint file monitoring, and enterprise search

Structured observability for LLM requests — OpenTelemetry metrics + Pino logging.