Search

Up-to-date models.dev data as typed packages

Multi-LLM Provider System for Claude Flow V3

Capacitor plugin for on-device llama.cpp model loading over GGUF files.

llama.cpp LLM Provider

> LlamaCloud is a new generation of managed parsing, ingestion, and retrieval services, designed to bring production-grade context-augmentation to your LLM and RAG applications.

The repo is for one of the backend: [llm-rs](https://github.com/rustformers/llm)

Real-time API traffic inspector for OpenClaw — intercepts LLM provider requests, shows token usage, costs, and message flow in a live web dashboard.

PromptKit Arena - Multi-turn conversation simulation and testing tool for LLM applications

Middleware guardrails to reduce PII/secrets/SQL/schema/prompt leakage in LLM apps

Svelte 5 component library with Skeleton UI and Tailwind CSS

Run eslint with watch mode

LLM provider abstraction layer with unified streaming interface

Hanseol - OpenAI-Compatible Coding Agent

LLM-Augmented Declarative Execution

Lingo.dev CLI

React Native binding of llama.cpp

Helpers to simplify LLM tool calls for popular APIs

ANTLR 4 command line tool for TypeScript

LLM-powered deployment troubleshooting assistant for Orca

Raises the popularity score on your package through nefarious means.