Inception Labs Integrations

Mercury Edit 2 is part of Inception Labs’ Mercury family of AI models, designed to perform high-speed reasoning, coding, and editing tasks using a fundamentally different architecture from traditional large language models. It builds on Mercury 2, a diffusion-based reasoning model that generates and refines entire outputs in parallel rather than producing text token by token, enabling significantly faster performance and more responsive editing workflows. Instead of acting like a sequential “typewriter,” the system behaves more like an editor, starting with a rough draft and iteratively improving it across multiple tokens at once, which allows for real-time interaction and rapid iteration in tasks such as code editing, content generation, and agent-based workflows. This architecture delivers throughput of up to around 1,000 tokens per second, making it several times faster than conventional models while maintaining competitive reasoning quality across benchmarks.

Ejentum is a reasoning harness for agentic AI, built as a structured reasoning layer that makes LLM agents more reliable, auditable, and disciplined during long or complex tasks. It works as a tool that an agent can call mid-task, returning the exact cognitive operation matched to the problem in front of it, so the agent can correct reasoning at inference time instead of relying only on static prompts. Ejentum is designed to stop AI agents from drifting, flattering, fabricating, locking into false hypotheses, stopping at shallow answers, or losing important context after several steps. It provides 679 abilities across four cognitive harnesses: reasoning, code, anti-deception, and memory. The reasoning harness channels analytical power across causality, time, space, simulation, abstraction, and metacognition, helping agents avoid surface-level pattern matching.

Mercury, the latest innovation from Inception Labs, is the first commercial-scale diffusion large language model (dLLM), offering a 10x speed increase and significantly lower costs compared to traditional autoregressive models. Built for high-performance reasoning, coding, and structured text generation, Mercury processes over 1000 tokens per second on NVIDIA H100 GPUs, making it one of the fastest LLMs available. Unlike conventional models that generate text one token at a time, Mercury refines responses using a coarse-to-fine diffusion approach, improving accuracy and reducing hallucinations. With Mercury Coder, a specialized coding model, developers can experience cutting-edge AI-driven code generation with superior speed and efficiency.

NLWeb is an open project developed by Microsoft that aims to make it simple to create a rich, natural language interface for websites using the model of their choice and their own data. Our goal is for NLWeb, short for Natural Language Web, to be the fastest and easiest way to effectively turn your website into an AI app, allowing users to query the contents of the site by directly using natural language, just like with an AI assistant or Copilot. Every NLWeb instance is also a Model Context Protocol (MCP) server, allowing websites to make their content discoverable and accessible to agents and other participants in the MCP ecosystem if they choose. NLWeb leverages semi-structured formats like Schema.org, RSS, and other data that websites already publish, combining them with LLM-powered tools to create natural language interfaces usable by both humans and AI agents.