NOMIFUN DESKTOP · Your own personal AI companion

Let AI live
by your side.

Build your Agent. Meet your companion.
From inspiration to action,
bring the power of AI into your everyday life.

Windows / macOSOpen sourceLocal first

The same companion, on your screen and at your side.

Move your pointer and let ideas meetChoose a mode to explore
OPEN SOURCE. OPEN POSSIBILITIES.Scroll into the possibilities
COMPOSE THE POSSIBILITIES

Every capability has a place to shine.

Knowledge & memory01
Remember what mattersNOMIFUN
Code & files02
Bring ideas to lifeNOMIFUN
Web & browser03
Explore real websitesNOMIFUN
Multi-agent04
Work toward one goalNOMIFUN
Image creation05
Picture your ideasNOMIFUN
Video creation06
Bring frames to lifeNOMIFUN
Audio & music07
Give stories a voiceNOMIFUN
Continuous work08
Keep work movingNOMIFUN
Physical devices09
Connect to the worldNOMIFUN
Plugins & mini-apps10
Add new capabilitiesNOMIFUN
YOUR PERSONAL AI COMPANIONS

Personal. Always growing.
Ready to work together.

A personality and memories of its own, with a complete Agent's capabilities.
Keep the same companion close, across your desktop, phone, and physical device.

Independent Agents · Distinct personalities
YOUR PERSONAL AGENT01 / 03
I'll keep today's inspiration for you.

MochiEveryday companion

Personality · Conversation · Long-term memory

Keep learning. Build reusable Skills.Your personality choices · Your capability mix
01 03
A companion. A lasting connection.

Own memories.
Shared knowledge.

Only for Mochi

“You like making complex things a little easier to understand.”

Each companion remembers and learns at its own pace

Designed for lasting, "unbounded memory": archiving, compression and retrieval on demand keep the connection going. Repeated work can become reusable Skills.

Meet NomiFun Desktop
TelegramFeishu / LarkDingTalkWeChatWeComDiscordMatrixMattermostSlackTwitchNostrQQ Bot
Permissions in your handsDemo settings

Only users you approve can message your companion directly.

This website demo does not create companions or connect devices. Additional desktop windows use more WebView resources. Each chat platform requires its own setup.

PERSONAL AI / BEYOND THE SCREEN

The same AI companion.
Now by your side.

A companion that remembers you, helps you get things done, and keeps the conversation going on your phone. Connect Xiaozhi Yuntai so it can hear you and respond with voice, expressions, and movement in your everyday space.

NOMIFUN × XIAOZHIREAL DEVICE
A familiar companion. A physical presence.

Existing Xiaozhi Yuntai project demo. The same identity and memory, with a new way to respond.

Physical device integration currently uses Xiaozhi Yuntai. It requires compatible hardware, configured firmware, pairing on a trusted local network, and a running Desktop. Voice, expressions, and movement depend on the board, firmware, and model configuration.

LOOK CLOSER. GO FURTHER.

Turn capabilities
into tangible work.

Your models, knowledge and tools.
A workspace that belongs to you.

Actual workspace component · Preview with test data · Click to explore

01 / AN AGENT, AS YOU IMAGINE IT

Only what you need.
An Agent that fits you.

From simple chat to a full working partner. Visually combine capabilities, models, and execution policies,
so every Agent can work its own way.

Compose it. Try it.Interactive capability demo
Read projects, edit files, and use local processes and version control.
4 capabilities selected

From project insight to delivery

Understand the code, research options, divide the work, and deliver results you can review.

Compose the modules. You authorize the actions.
ONE CONVERSATION. DIFFERENT CAPABILITIES.

One conversation.
Let capabilities take turns.

Your context and drafts stay here. Next turn,
switch to the Agent that fits the task.

My product plan

Help me turn this idea into a working tool.

Research Agent

First, research the use cases and map out sourced options and implementation boundaries.

Messages and drafts stay · Applies next turn

Agent switching is available while a regular local conversation is idle. Companion and channel conversations follow their bound Agent settings. This preview describes the current development source; check release notes for available features.

KEEP THE WORK MOVING

You set the direction.
Keep the work moving.

Requirements + AutoWork + IDMM
From one goal to a continuous work loop.

Scroll to take the next step
THE WORK CONTINUES.Website workflow demo · No real tasks run
01 / REQUIREMENT

Give your goal a place to begin.

Keep the goal, resources and acceptance criteria in one requirement. You set the direction. Work starts here.

REQUIREMENT #001

Turn an idea
into a useful tool.

A clear goalThe right resourcesA verifiable result
Product designLocal projectQueued
Your work queue01
Queued

Organize with tags. Keep the next task in sight.

02 / CLAIM

A task is claimed. Work begins.

The assigned Agent session claims the next requirement in order. Persisted execution records keep the queue moving.

YOUR AGENT
CLAIMEDInteractive prototypeAssigned session · Work continues
01 → 02 → 03
Claim recorded and persisted
Claimed

When the queue is empty, it waits quietly.

03 / EXECUTE

Keep moving. Make it deliverable.

Understand the task, use tools and run checks in the original session. IDMM handles recoverable failures and safe decision pauses alongside it.

NomiFun / Agent workspace
Understand the goalReview context, resources and scope
Build itTools, code and your local workspace
Check and deliverMake the result verifiable
→ moving the work forward
IDMMSidecar decisions
Running

Work stays in the main Agent session, with traceable results.

04 / RECEIPT

Every step. A result, a receipt.

Record deliverables, check results and an execution receipt before advancing. Your acceptance criteria stay with the task.

WORK RECEIPT / #001

Done. Ready to verify.

PrototypeDelivered
Local checksRecorded
Execution recordArchived
CHECK. RECORD. CONTINUE.
Completed

Verifiable delivery makes the next step reliable.

05 / CONTINUE

Let each result start something new.

With permission to write requirements, the Agent can submit follow-up work as instructed. Turn results into new goals in a controlled loop.

THE NEXT POSSIBILITY
This delivery
Awaiting your permission
New requirement

Continuous work, always within your authorization.

INTELLIGENCE, IN THE RIGHT PLACE.

Work moves forward.
Not every decision needs a model.

IDMM handles execution strategy alongside the main task.
Use rules for clear choices. Call for judgment when needed.

INTELLIGENT DECISION

IDMM decisions

0Model tokens / rule decision

Deterministic rules handle recoverable failures and clear, safe options first. Model calls for the main task are still billed by usage.

Permissions, credentials, payments and destructive decisions wait for a person.
7×24
Designed for continuous work.

Idle queues wait. Enabled work loops resume when the backend starts.

Keep the computer and app running, with model services available.
Approvals, errors or configured limits may pause tasks.

A SPACE FOR EVERY IDEA / MULTIMODAL CREATION

Ideas have no limits.
Neither should your workspace.

Chat, images, video, and audio.
From one conversation to a canvas you can make your own.

Chat / CHAT

One conversation. Every idea.

KnowledgeToolsImagesAudioContextONE CONVERSATION. EVERY POSSIBILITY.

Understand goals, use tools, and search knowledge. Bring your work into one Agent workspace.

Conversation demo

Help me turn this idea into a complete creative plan.

Let’s take it from idea to creation.

Start with the story, then gather image, video, and audio references. For domain details, I can search the knowledge base you attach.

Selected: knowledge search
Bring your ideas into the workspace…

Website demo only. No messages are sent or models called.

Image / IMAGE

From inspiration to images.

Prompts, references, models, and settings in one place. Generate, edit, and organize as your ideas take shape.

NomiFun Desktop / Product interface
NomiFun Desktop image creation workspace screenshot
Historical product screenshot: v0.7.2 / Aug 2026. Current features may differ; sample prompts retain their original language.
Video / VIDEO

Give your images a sense of time.

Set up prompts, references, and generation options. Bring images and video onto a timeline to keep creating.

NomiFun Desktop / Product interface
NomiFun Desktop video creation workspace screenshot
Historical product screenshot: v0.7.2 / Aug 2026. Current features may differ; sample prompts retain their original language.
Audio / AUDIO

Give your story a voice.

YOUR IDEAS, YOUR VOICENomiFun / Audio

Choose a speech model and voice settings to turn text into audio. Add audio nodes to the same creative canvas.

Audio creation demo

Give every word its own voice.

Speech synthesis · Audio nodes · Your choice of model

Visual waveform demo only. No sound is played or generated.

Canvas / INFINITE CANVAS

Make room for your ideas.

Arrange images, video, text, audio, and timelines on a canvas you can freely zoom. Build a workspace around your process.

City & nature / Canvas demo
Image node: generate & edit
An interactive illustration of nodes and connections. Select a node to explore your workspace.
Keep media, models, and creative context in one space.Explore creative capabilities

MAKE IT YOURS MINI APPS & HEADLESS PLUGINS

Your ideas,
made into capabilities.

Create in natural language and preview visually. Semi-managed mini apps and headless services let your tools, background capabilities, and automation grow with your needs.

INTERACTIVE DEMO

02 / PREVIEW

See your idea take shape.

Interfaces and background services share one extension package. Preview it before deciding how to use it.

This demo does not create or run real plugins.

ONE PACKAGE. MANY POSSIBILITIES.
My focus workspace
Make a little room for ideas today.
25MIN FOCUS
Find the next good idea for your project
Set aside time to create
UIServiceActionBinding
7

entry points into real work.

From chat to desktop, tools to automation. Choose an entry point to see where your extension can contribute.

agent.tool

Agent tools

Give your Agent custom actions. It can choose when to use them and call your extensions in a conversation.

BUILT TO BE OPEN For developers. For every creator.

Powerful by nature.
Open by design.

From a single conversation to an agent team. See how NomiFun connects models, capabilities and real action.

THE RIGHT MODEL FOR THE RIGHT TASK

Let every model do its best work.

Configure tasks, models and protocols separately. Connect chat, images, video, audio and retrieval to the right providers, with room to add new protocols.

Explore the source
Available capabilities depend on the connected protocols, models and provider settings.
Interactive architecture demo

Chat model

Understand · Reason · Collaborate
PROTOCOL ADAPTEROpenAI / Responses / Anthropic / Gemini
Task → Model → Protocol

A design demonstration; no live models or tasks are running.

Your computer.
Your data. Your work.

Local first. Open source. No product telemetry. Models, IM channels and online tools connect to external services according to your settings.

Open code. Come explore it with us.

A PERSONAL IDEA. AN OPEN FUTURE.

One person's idea.
A future we can all shape.

In October 2025, NomiFun began as one developer's robot brain and coding enhancement system.
From helping machines understand to giving Agents memory, capabilities, and action, the exploration continues.

Read the origin story
2025.10

Starting with a robot brain

Solo development begins, connecting coding tools and intelligent conversation to the physical world.

2025 Q4 — 2026 Q1

Bringing ideas into the product

IDMM sidecar decisions, requests and autonomous work loops, remote robots, companion Agents, and knowledge bases arrive in the product.

NOW & BEYOND

An open system of capabilities

Composable Agents, a unified plugin core, and a multimodal workspace open up possibilities for users and developers to build together.

ONE ECOSYSTEM. MANY WAYS IN.

Your computer at the center.
More possibilities within reach.

Desktop, mobile, robots and cross-network connections. Four open-source projects, each with a purpose.

01 / OPEN SOURCETHE LOCAL BRAIN
LOCAL AI WORKSTATION

NomiFun Desktop

Composable agents, desktop companions, autonomous work, and multimodal creation—powered by one local runtime.

Meet Desktop
01 / 04

Drag left or right to bring the next possibility into view.

1 / 4: NomiFun Desktop

Your computer is the service. Phones and robots connect directly on a trusted LAN, without deploying an additional application server.
For access across networks, self-host Net Infra and use your own transport channels.

Explore the ecosystem

A FEW THINGS TO KNOW

Before you begin,
a few things to know.

The choices are yours.
The boundaries should be clear.

Explore NomiFun0%