Blazing-fast, zero-cost local LLM router. Classify and route prompts to specialized AI models (OpenAI, Claude, Gemini, Llama) with <1ms latency using heuristic rules.
A Typescript client to interact with Switchboard On-Demand.
common type definitions and utils for interacting with switchboard
A lightweight library to decode and parse aggregator accounts
No description provided.
Session-aware routing layer for AI-assisted software delivery workflows
Local model-routing CLI for Codex and Claude Code.
Enforce real-time token budgets and spending limits for OpenAI, Anthropic Claude, and Google Gemini API calls in Node.js
Display language model outputs in your React project.
Typescript bindings for langchain
Hardware accelerated language model chats on browsers
command line tool to interact with switchboard
[llm-ui](https://llm-ui.com) markdown block.
LLM eval & testing toolkit
Operator project contains switchboard interfaces and orchestration code
[llm-ui](https://llm-ui.com) code block.
Contains switchboard interfaces
[llm-ui](https://llm-ui.com) JSON blocks for building custom components.
Local Development Support NS8 Switchboard Projects
Unified MCP server manager for AI coding agents
General-purpose agent with transport abstraction, state management, and attachment support
micromark extension to support math (`$C_L$`, `\(C_L\)`)
Detox driver for Wix Pilot usage
Supervised inter-agent messaging relay for Claude Code (and any MCP client). Named identities, channel-based pub/sub, single-pane supervision UI with manual-approval mode.