LOCAL AI WORKSPACE

Local LLM, Orchestrated.

Run local models through Gateway, use them in focused workspaces, and hand multi-step execution to the Mate agent system. ExtendedLM brings the model, knowledge, workflow, and tools into one desktop experience.

Start Building

LOCAL + CLOUD MODELS

KimiMoonshot AI DeepSeekDeepSeek GLMZ.ai QwenAlibaba GPTOpenAI ClaudeAnthropic GeminiGoogle LlamaMeta

Models under your control

Use Gateway to discover, load, serve, and observe local models, while keeping cloud adapters available for workloads that need them.

Focused AI workspaces

Move between chat, translation, speech, knowledge search, documents, slides, reports, and research without rebuilding each experience from scratch.

An agent system that executes

Use the Mate agent system when a task needs planned browser, shell, file, search, or configured MCP actions—with approvals and execution evidence.

Focused workspaces

Choose the workspace for the job.

ExtendedLM presents different working modes for different outcomes: everyday chat and media, translation and transcription, knowledge retrieval, document and presentation creation, deep research, and executable work through an agent system.

One desktop, multiple modes

Select Standard, Image, Speech, Translation, Transcribe, Notebook, Global RAG, Agentic RAG, Document, Slide, Report, Deep Research, Fusion, or Mate according to the work in front of you. Availability can depend on configuration.

EXTENDEDLM / WORKSPACE MAP WORKSPACE MAP

ExtendedLM DESKTOP

01 Translation

02 Notebook / RAG

03 Documents

04 Image / Speech

05 Agent System

06 Deep Research

Workspace selection overview

VISUAL WORKFLOW EXECUTABLE GRAPH

Workflow graph

RUNNING

文 Input schema

R RAG Tool collection

↗ MCP Tool configured server

LLM model node

ACTIVE WORKFLOW Input → RAG → LLM → MCP

04 NODES

Visual workflow execution

Visual workflows

Design the steps, not just the prompt.

Build an executable graph from LLM, code, generated-tool, RAG, and MCP nodes. Connect inputs and outputs visually instead of hiding the whole process inside one prompt.

Control flow you can inspect

Add conditions, iteration, while loops, parallel branches, Try/Catch, delays, and merge nodes. Configure variables and ports, then inspect execution results from the same workflow.

CAPABILITIES

Run locally. Automate the work.

Manage models, connect repeatable steps, and bring the tools your work already depends on.

GATEWAY / MODEL CONTROL ONLINE

01 Find a local model List models available to Gateway FOUND

02 Check compatibility Confirm the runtime and requirements COMPATIBLE

03 Load and serve Make the model ready for requests READY

01 / LOCAL MODELS

Download, load, and run local models

Gateway brings model discovery, download, compatibility checks, loading, unloading, and service status into one control surface.

02 / AUTOMATION

Turn repeatable work into a workflow

Start with manual input or a webhook, then connect LLM, RAG, and tool nodes with conditions, loops, parallel branches, retries, delays, and merges.

03 / TOOLS

Connect the tools you already use

Call tools from configured MCP servers, use built-in code tools, or create a visual tool and place it directly in the workflow.

Connected platform

One desktop. Three connected layers.

The desktop app brings model selection, focused AI workspaces, knowledge, and visual workflows together. Gateway supplies inference; the Mate agent system supplies tool execution.

01
Workspace: chat, media, translation, knowledge, documents, research, and workflows.
02
Gateway: model routing, local runtimes, model lifecycle, and inference APIs.
03
Agent System: planned browser, shell, file, search, and MCP execution with approvals and observable output.

01 / MODEL LAYER
Gateway
local models · cloud adapters · inference

02 / WORKSPACE
ExtendedLM
chat · RAG · documents · visual workflows

03 / EXECUTION
Agent System
browser · shell · files · MCP

INTEGRATED COMPONENTS

The desktop connects models to action.

Gateway and the Mate agent system remain distinct systems with clear responsibilities inside the ExtendedLM experience.

Gateway

Run GGUF and Safetensors models on available CPU or GPU hardware, expose them through application-facing APIs, and manage discovery, loading, observation, and release.

Learn More →

Agent System

Mate turns a goal into planned tool work across browser, shell, files, search, and configured MCP services. Review progress, approvals, artifacts, previews, and diffs by session.

Learn More →

A deliberate path from model to result

Select and operate a local model through Gateway, with cloud access remaining an explicit option rather than the premise.

Use that model in chat, translation, knowledge retrieval, document creation, research, or a visual workflow.

When the task requires action, hand it to the Mate agent system with a session, execution policy, approvals, and observable outputs.

STARTING POINTS

Start with the layer you need.

Adopt one capability first, then connect the others when the work requires them.

Model layer 01 Gateway

Begin by serving one local model for a concrete chat, extraction, coding, retrieval, translation, or speech task.

Workspace layer 02 ExtendedLM

Use the model in a focused workspace or connect model, knowledge, tools, and control flow visually.

Execution layer 03 Agent System

Add the Mate agent system when the desired result requires planned work outside a model response.

EXTENDEDLM

Start with one model and one real task.

Choose where the model should run, select the workspace for the outcome, and add a workflow or the Mate agent system only when the task needs execution.

Get Started