A simple, unified NPM-based interface for interacting with multiple Large Language Model (LLM) APIs, including OpenAI, AI21 Studio, Anthropic, Cloudflare AI, Cohere, Fireworks AI, Google Gemini, Goose AI, Groq, Hugging Face, Mistral AI, Perplexity, Reka A

LLM interface for Agenite

Unified LLM interface (in-memory).

Lightweight CLI LLM Interface

Core package for unified LLM interface

llm interface 库

ResilientLLM is a resilient, unified LLM interface with in-built circuit breaker, token bucket rate limiting, caching, and adaptive retry with dynamic backoff support.

LLM interface and providers for PRsense

ULIS - Unified LLM Interface Specification CLI. Generate agent/skill/mcp/rules configs for Claude Code, Codex, Cursor, OpenCode, and ForgeCode from a single source of truth.

A DIY LLM interface

A single-tool LLM interface framework with hierarchical command routing

Universal LLM interface with predictable behavior and zero dependency core

Core logic for flakewatch: failure grouping, context packaging, LLM interface

Typescript bindings for langchain

This package provides bindings that enable using the Spin LLM interface in apps built using the `@spinframework/build-tools`.

Superfast runtime validators with only one line

A universal LLM client - provides adapters for various LLM providers to adhere to a universal interface - the openai sdk - allows you to use providers like anthropic using the same openai interface and transforms the responses in the same way - this allow

Mastra is a framework for building AI-powered applications and agents with a modern TypeScript stack.

Provider-routed LLM request retry policy for the DeepSeek Harness

HTTP daemon and CLI for agent-driven browser extension testing with Playwright