Zeraix: open-source AI desktop
Zeraix is an open-source AI desktop for working with models, files, tools, and agents, with local inference at its core.
Verified
Core facts
Read by a script from the official API, not rewritten by a model.
- Repository
- https://github.com/zeraix/zeraix
- License
- Apache-2.0
- Languages
- TypeScript
- Maintainer
- zeraix
- Homepage
- https://zeraix.com
- Verified
What it is
Zeraix is an open-source AI desktop for working with models, files, tools, and agents, with local inference at its core. It lets you run supported models on your own hardware, work with your files, and carry out multi-step tasks in one workspace. Cloud models and services can be connected when you need them. Zeraix is licensed under Apache 2.0.
Main features
Zeraix downloads and runs supported GGUF models, with hardware-aware recommendations and runtime management.
From the same conversation, it can read, search, and edit project files, inspect diffs, run terminal commands, and use browser tools.
Work can be delegated to specialized sub-agents, whose execution can be inspected and which can be stopped individually.
Zeraix keeps local conversations and memory, tracks task goals, and schedules recurring workflows with run history and notifications.
Zeraix bundles Skills for Word documents, PDFs, presentations, and spreadsheets, with shared formatting guidance and local processing tools.
Zeraix collects uploaded and generated assets in a media library, previews images, video, audio, PDFs, and text, and connects compatible image or video generation services.
Getting started
On macOS, the requirement is macOS 13 or newer on Apple Silicon.
On Windows, the requirement is Windows 10/11 x64.
Open Model Library and let Zeraix detect your hardware.
Choose a recommended model and review its memory and disk requirements.
Download the model and required runtime, then start it.
Select the running model in chat and send your first message.
git clone https://github.com/zeraix/zeraix.git
cd zeraix
corepack enable
pnpm install --frozen-lockfile
pnpm electron:devWho it is for
The local core requires no Zeraix account, subscription, or API key. For memory, at least 16 GB is recommended. Initial setup downloads model and runtime assets.
Local inference and local tools can work offline after setup. Web search, remote MCP servers, generation services, and cloud models need their respective network connections. Selecting a local model does not make external tools offline.
Local-model inference runs on your device, and local conversations are stored locally. Zeraix offers Default, Full trust, Manual approval, or Plan mode to control how tool calls are approved. Plan mode blocks file-changing tool calls and asks before shell commands outside the recognized read-only set.
Approval modes control consent, and they do not replace sandbox isolation. An optional QEMU sandbox provides an isolated environment for supported commands. Zeraix combines a curated model catalogue with compatible community GGUF imports and custom OpenAI-compatible endpoints.
The desktop currently uses llama.cpp-based runtimes for general local inference. Imparo is an open-source LLM inference engine, designed to adapt execution to hardware and workload. Imparo is not yet the bundled default inference engine in Zeraix.
Development uses Node.js 22, Corepack/pnpm, Git, and the stable Rust toolchain with Cargo, with Rust 1.85 or newer. Local files, model management, terminal tools, and other native capabilities require the Electron application. CI runs JavaScript and Rust tests, type checks, and macOS/Windows runtime smoke checks.
Third-party models, runtimes, plugins, and downloaded assets retain their own licenses.
Related tools
Related tools listed on this site.
EveryGen AI
Video generator and creative studio describing scene planning, clips, image editing, voices, music and video assembly.
QwenPaw
Personal AI assistant and agent workstation running in your own environment. Its primary description presents local/cloud deployment, multiple channels and extension through Skills and MCP.
Cursor
A coding agent for understanding repositories, planning features, changing code, and reviewing diffs.
CodeBuddy IDE
AI coding workspace for product, design and development. Its dedicated IDE documentation describes technical conversations, code completion, Figma-to-code, diagnostics and a design-to-deployment workflow.
InfCode
Enterprise AI coding agent from TokensInfinity. Its site describes using enterprise code and knowledge through IDE, extension and CLI forms for completion, cross-file changes and engineering tasks.
阿里云百炼
Alibaba Cloud Bailian is a model-service and application-development platform for model inference, knowledge bases, agents and workflows.
千问云
The discovered Qianwen Cloud entry currently presents the Qianwen AI Platform for model discovery, online trials, API access, Skills/CLI tooling and usage/cost management.
Figma AI
Collection of AI workflows and capabilities within Figma products for design exploration, content editing and connecting prototypes with code.
Pixso AI
AI design capability integrated into the Pixso canvas. Its official page describes generating editable web and mobile interfaces from text, sketches or screenshots and continuing to refine existing designs.
Ardot
AI design and collaboration tool. Its official site describes text/image-to-editable UI, vector editing, dynamic layouts and design systems, plus collaboration, annotations and design-to-development handoff.
纳米AI
Nano AI is an AI search and agent assistant whose site says it can generate videos, reports and slides from one sentence and integrates several large models.
Exa AI
Exa is a web-retrieval service for AI applications and agents, describing search, content retrieval, deep research and structured-output APIs.
Related guides
- skill-creator: Anthropic's skill for writing, editing and evaluating skillsAnthropic's skill-creator skill: draft a skill, run evals, revise it and tune its trigger description. Not tested here; follow the official text and docs.
- webapp-testing Skill: drive local web apps with PlaywrightOfficial Anthropic webapp-testing Skill: Python Playwright scripts for local web apps, not tested
- frontend-design: avoiding templated defaults in UI designAnthropic's frontend-design skill: plan the visual direction, check it against the brief, avoid templated defaults. Not tested; follow the official text.
- gh-address-comments: work through GitHub PR review commentsOfficial OpenAI Codex skill: fetch comments on the current branch's PR with the gh CLI, number them, then fix only the ones you pick; not tested.
- security-best-practices: language- and framework-specific security reviewOfficial OpenAI Codex skill: load security references matching the project's language and framework, then write safer code or a report; not tested.
Sources
This page is written from the official sources below. Open them to check the original text.
- GitHub READMEhttps://github.com/zeraix/zeraixFetched
Verified ·
This page is written by AI from the official sources above and checked automatically. This site has not tested it. Found a mistake? Tell us.