Stateless, high-concurrency AI Agent framework with onion-model middleware and dynamic LLM switching

Typescript bindings for langchain

Glob matching for javascript/node.js. A replacement and faster alternative to minimatch and multimatch.

Hardware accelerated language model chats on browsers

BrowserStack's Official MCP Server

Provider-neutral LLM service interface for the DeepSeek Harness

Provider-routed LLM request retry policy for the DeepSeek Harness

Additive request-field registry for the official DeepSeek LLM API adapter

Superfast runtime validators with only one line

Streaming colorization for Shiki, useful for highlighting LLM outputs and other text streams

Superfast runtime validators with only one line

pi-ai-backed DeepSeek adapter for the DeepSeek Harness LLM seam (design-verification twin of dsh-llm-deepseek)

<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>

Display language model outputs in your React project.

DeepSeek chat-completions adapter for the DeepSeek Harness LLM seam

Self-learning LLM runtime — TurboQuant KV-cache (6-8x compression), SONA adaptive learning, FlashAttention, speculative decoding, GGUF inference

LLM eval & testing toolkit

Popular AI / LLM Model Brand SVG Logo and Icon Collection

General-purpose agent with transport abstraction, state management, and attachment support

Token-Oriented Object Notation (TOON) – compact, human-readable serialization of JSON data for LLM prompts