Clean-room LLM protocol translation core: Anthropic Messages <-> OpenAI Chat

Vendor-neutral LLM protocol for auto-hwp chat-editing: EditRequest/EditResponse types, buildDocContext (R5 fence), buildSystemPrompt (INTENT-SCHEMA excerpt, allowed-intent subset), validateRequest/validateResponse (whitelist + structure). Pure, isomorphic

LLM Protocol layer for NaN•Web — Sessions, Drivers, Models, Streaming. One Logic — Many UI.

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

DeepSeek chat-completions adapter for the DeepSeek Harness LLM seam

Shared wire protocol for the DeepSeek Harness SDK runtime: the newline-delimited JSON-RPC stdio transport and the named request, result, and notification types spoken between the runtime server and SDK clients

The Chrome DevTools Protocol JSON

The postgres client/server binary protocol, implemented in TypeScript

Agent runtime — facade + LLM protocol + task loop + tool framework + safety policy + skill loader + prompt assembler + persistence. Embeddable in any host process.

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

Provider-neutral LLM service interface for the DeepSeek Harness

A library for working with LLMs in Grafana plugins

VSCode Language Server Protocol implementation

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

Stdio JSON-RPC server plugin for out-of-process DeepSeek Harness SDK clients

Simple to use, blazing fast and thoroughly tested websocket client and server for Node.js

Protocol Buffers for JavaScript

Transform OpenTelemetry SDK data into OTLP

Model Context Protocol implementation for TypeScript

AI-powered chat and tool execution for Open Mercato, using MCP (Model Context Protocol) for tool discovery and execution.