AgentVerse OS turns a single Ubuntu server into a personal cloud with a real desktop in the browser, built for a developer and their AI agents. You work in a windowed desktop with a taskbar, start menu, and widgets for system monitoring, clock, news, weather, and projects, and the same desktop opens from a laptop, tablet, or phone while everything stays on the server. Each project gets an isolated Incus container with Docker inside, its own network and gate, plus VS Code, a terminal, files, and git in the browser. The Agents app runs Claude Code, Codex, Gemini CLI, pi, and Antigravity inside the workspace, with permission prompts you approve from any device, scheduled routines, model menus, conversation search and export, and a ledger of what each session spent. When you close your laptop the agents keep working, and you pick the conversation up later exactly where it stopped. A built-in store merges the Runtipi, Coolify, and Umbrel catalogs into about 945 installable apps with guided setup, credentials shown in the app card, snapshots, and rollback. Projects request capabilities such as storage.s3, llm, or notify instead of hardcoding addresses, scheduled ZFS snapshots feed a restic backup repository, and access arrives only through your Tailscale network with real certificates. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

EveryOS gives the Linux server you already own a desktop it never had: open a browser and your machine greets you with windows you can move, snap, and stack, a dock, virtual desktops, widgets, and a launcher, all remembering exactly how you left them. Your files live in a private home with the usual folders, previews, a text editor, and a trash you can restore from, and plugging in a USB disk makes it appear on the desktop ready to mount. An app store installs self-hosted applications from catalogs and follows each deployment, later offering updates that keep your settings, rollbacks when one goes wrong, and backups of app data. The same workspace watches the machine itself: CPU, memory, disk, and network at a glance, systemd services and logs, available package updates, and a Docker view for containers and Compose projects. A real terminal opens in the browser under your own Linux account, Home Assistant arrives as a panel and desktop widgets with its tokens kept on the server, and an AI assistants app can find or install a local model server such as Ollama and chat with it privately. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Puter delivers a complete cloud operating system that runs entirely in the browser — turning any device with internet access into a full-featured personal computer with desktop environment, file management, application hosting, and developer platform. The familiar desktop interface presents windows, taskbar, right-click menus, drag-and-drop, and multi-window management indistinguishable from native operating systems. The hierarchical filesystem supports file creation, uploads, sharing, permissions, and trash recovery with storage backends ranging from local SQLite for self-hosting to S3 and DynamoDB for production scale. Built-in AI integration provides access to GPT-4, Claude, and other models directly from the desktop for text generation, code assistance, and image creation. The developer platform offers a JavaScript SDK, REST APIs, cloud storage, key-value database, and serverless workers for building and hosting web applications without managing infrastructure. Sandboxed applications run in iframes with IPC communication and permission-based access to filesystem, AI, and system services. The app store enables publishing, discovering, and monetizing applications built on the Puter platform. Website hosting publishes static sites with custom domains directly from the file manager. Multi-user support provides individual accounts with authentication, resource isolation, and sharing capabilities. Deploy via Docker with a single command, Docker Compose for production, or npm for development — the one-line install script handles everything automatically on Linux, macOS, and Windows. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3.0 licensed.

Homeio turns a Linux box into a desktop you open in a browser tab, with draggable windows, a dock, a lock screen, and a command palette sitting on top of your Docker apps, files, and disks. The App Store installs Docker Compose stacks from the CasaOS catalog or your own store sources, and each app's ports, volumes, environment variables, and compose file stay editable before and after install. Containers you started elsewhere still appear with live CPU and memory stats, streaming logs with keyword filters, and one-click restarts. The file manager uploads with progress, previews images, audio, video, and PDFs, edits text in a built-in code editor, mounts USB drives and SMB shares, and shares folders over Samba. A real login shell lives in the Terminal window, with exec access into any container, so routine fixes never need a separate SSH client. Cron-style scheduled tasks restart apps, pull images, or run backups on a timer, and scheduled archives of the database, files, and compose stacks restore from the same interface. Tailscale puts the whole desktop on your private network, while Cloudflare Tunnel can publish a single app on a public hostname with its DNS record created for you. Live metrics stream to widgets and the status bar, and notifications flag crashed containers, filling disks, and failed tasks. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3.0 licensed.

taOS is a self-hosted operating system for AI agents that lives on hardware you already own, offline by default and cloud only when you invite it. Open one URL and a full web desktop appears: floating windows, a dock, launchpad, widgets, notifications, and 43 bundled apps, from mail and kanban projects to an app store with over a hundred one-click installs. Agents deploy through a guided wizard into isolated containers (LXC on bare metal, Docker on a VPS), each with its own memory store, files, secrets, and network identity. taOS owns the agent lifecycle outside the framework, so you can swap SmolAgents for LangChain or OpenClaw and the agent keeps its history, channels, trained adapters, and API keys untouched. Long-term memory is a temporal knowledge graph with hybrid search on your disk, not a row in a vendor database, and the messages app works like a private Discord that also installs as a phone PWA. Local inference spans Apple Silicon, NVIDIA, AMD, Rockchip NPUs, Raspberry Pi boards, and salvaged Android phones, with auto-clustering that pools idle machines into one compute fabric. Messaging connectors cover Telegram, Discord, Slack, Matrix, email, and webhooks, and a rollback command returns the system to a known-good state when an experiment misbehaves. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3.0 licensed.

Host your own email, files, calendars, and passwords on a single server with YunoHost, a server operating system that puts every app behind one web admin and one shared login. Browse a catalog of more than 500 apps, such as Nextcloud, WordPress, and Vaultwarden, filter by quality level, and install in a few clicks, or paste a Git URL for a custom app. Each person signs in once at a portal that shows a tile for every app they may open, and apps with single sign-on skip their own login screen. Groups and per-app permissions control access, including public access for visitors, and the Admins group adds web admin, SSH, and sudo. A full mail stack handles incoming and outgoing email per domain with DKIM signing, and Let's Encrypt certificates renew automatically. The domain screen suggests the DNS records you need and can push them to a supported registrar's API, while free .nohost.me, .noho.st, and .ynh.fr subdomains configure themselves. Backups bundle system settings, mail data, and chosen apps into downloadable archives that can be restored selectively from the admin or the command line. Twice a day a built-in diagnosis checks DNS records, mail setup, and system resources, then emails the admins if anything needs attention, with a firewall editor and fail2ban protection alongside. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3.0 licensed.

Google Workspace and Microsoft 365, replaced by a platform you actually control: Nextcloud is the self-hosted digital workspace. Files is the core: file storage and sync across desktop, mobile, and web clients, with sharing, versioning, and collaboration built in. Around it, Talk provides private text chat, audio/video conferencing with screen sharing, SIP integration, and persistent voice rooms; Groupware bundles calendar, contacts, and mail with delegation support; and Office offers two collaborative suites - the Collabora-based option with deep ODF support, and Euro-Office, whose local-processing architecture delivers strong Microsoft Office compatibility and fast browser rendering with reduced server load. The Nextcloud Assistant threads AI through the platform via a context-aware sidebar, Whiteboard covers visual collaboration, Flow handles automation, and an app ecosystem of hundreds of extensions adds everything from Kanban boards to end-to-end encryption. Hub 26 brings a lighter UI with a unified app switcher and Nextcloud Governance for organizations under strict regulatory requirements. This is the flagship of data sovereignty: your files, chats, calendars, and documents live on your server, under your jurisdiction, with GDPR compliance by architecture rather than by contract.

With over 1,200 GitHub stars, 12,000+ commits, and more than a decade of active development distributed under the AGPL-3.0 license, Cozy Cloud operates as a comprehensive personal data hub that goes far beyond file storage by connecting your documents, contacts, calendars, banking transactions, energy bills, and productivity tools into a single self-hosted platform where no third party profiles you. The cozy-stack Go binary handles file storage, CouchDB document management, job scheduling, app serving, and the REST API in a single process consuming approximately 150MB of RAM idle. Sandboxed konnectors import data from 50+ external services — banks, utility providers, telecom operators, cloud drives — running as isolated jobs via nsjail to prevent untrusted code from accessing other user data. The built-in app store serves web applications in subdomain-isolated environments with Content Security Policy headers, each app communicating exclusively through the documented REST API. Real-time synchronization via PouchDB replication and WebSocket keeps files, contacts, and documents consistent across desktop clients, mobile apps for iOS and Android with automatic photo backup, and the web interface. Security features include automatic Let's Encrypt TLS certificates, Argon2id password hashing, optional TOTP two-factor authentication, and GDPR-compliant data export via the CLI. Each user receives their own isolated instance with independent storage, database, and application configuration. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3.0 licensed.

A personal cloud does not need the weight of a small enterprise suite, and bewCloud proves it by keeping files, photos, notes, contacts, and calendars in one compact service a single person can run for a whole household. The Files app stores uploads in a plain folder tree on disk, offers public sharing links, optional whole-folder downloads as zip archives, and a WebDAV endpoint that desktop tools can mount. Photos turns that same storage into a browsable gallery, while Notes keeps quick text within reach of every login. Contacts and Calendar speak CardDAV and CalDAV through a bundled Radicale server, so the calendar and address book on a phone or laptop stay in sync without another account anywhere. News collects feeds to read in the browser, and Expenses tracks spending in a small ledger beside everything else. The header shows only the apps you enable, in the order you choose, and companion desktop and mobile apps connect to the same server for people who prefer native sync. Accounts can be protected with multi-factor authentication using TOTP, passkeys, or email codes, and optional single sign-on lets a household sign in through an existing identity provider. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3.0 licensed.

Large language models get a polished front end that can run fully offline: Open WebUI is the self-hosted front end of choice. It talks to local model runners, primarily Ollama, and to any OpenAI-compatible API, so LM Studio, vLLM, Groq, Mistral, OpenRouter, and cloud providers all plug into the same chat interface and can be mixed per conversation. RAG is built in: upload files to knowledge bases or reference them in chat with the # command, backed by a choice of nine vector databases (ChromaDB and PGVector officially maintained) and multiple extraction engines including Tika and Docling, with hybrid BM25-plus-vector search and cross-encoder reranking. Web search results from providers like SearXNG, Brave, and Tavily inject directly into conversations. Extensibility comes from Python tools and functions that run inside the chat, a Pipelines plugin framework, and native MCP support. Multi-user features include RBAC, SSO, and group permissions, and the instance itself exposes an OpenAI-compatible API your own apps can call.

With over 48,000 GitHub stars and monthly releases since March 2023, LocalAI is the self-hosted AI engine that replaces every OpenAI endpoint with a single Docker container running on your own infrastructure — serving chat completions, image generation, text-to-speech, speech-to-text, embeddings, vision, video generation, and function calling through identical API schemas that require zero application code changes. The composable backend architecture isolates each inference engine as a separate gRPC service running in its own OCI container, so llama.cpp, vLLM, SGLang, transformers, whisper.cpp, diffusers, MLX, Stable Diffusion, and Flux install on demand without touching the core, can run on separate machines, and a fault in one never affects others. Hardware acceleration spans NVIDIA CUDA 12 and 13, AMD ROCm, Intel oneAPI/SYCL, Apple Silicon Metal, Vulkan, and NVIDIA Jetson L4T — or runs entirely on CPU without any GPU. Built-in AI agents support autonomous tool use, retrieval-augmented generation, Model Context Protocol integration, and skill-based workflows directly in the web interface. The model gallery provides curated YAML configuration files for hundreds of models that install with a single command, while P2P federated inference distributes model shards across multiple machines for running models larger than any single node's memory. Multi-user API key authentication with quotas and role-based access enables team deployments. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

ODS turns a GPU machine or server you already own into a complete private AI stack with a single install command, replacing a shelf of separate tools with one system that serves models, chat, agents, automation, and search from your own hardware. The installer reads your GPU, VRAM, memory, and disk, then downloads a GGUF model matched to that hardware tier, and a compact bootstrap model starts answering within minutes while the full model finishes downloading. From the web dashboard you watch every service's health, ports, and resource use, restart what misbehaves, and check storage and updates without touching a terminal. You chat with local models in Open WebUI, hand background work to the Hermes and Portal agents, and build automations in n8n that connect the stack to more than 400 other apps. Documents you add become searchable knowledge through Qdrant vector storage, so answers cite your files instead of the model's memory. SearXNG and Perplexica answer web questions without trackers or accounts, Whisper transcribes speech, Kokoro reads text aloud, and ComfyUI generates images, all on the same box. Every bundled service is an extension you can enable, disable, or replace, and a Privacy Shield scrubs personal data before anything reaches an optional cloud model through the LiteLLM gateway. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

OpenLLM serves any large language model as an OpenAI-compatible API endpoint from a single CLI command, handling model download, backend selection, quantization, and port binding automatically. It supports the full spectrum of popular models including Llama 3.3, Qwen2.5, DeepSeek, Mistral, and Phi3, choosing between vLLM and PyTorch inference backends based on hardware capabilities. When vLLM is available, continuous batching with PagedAttention achieves up to 23x throughput improvement over naive serving, while GPTQ and bitsandbytes quantization reduces memory requirements for GPU-constrained deployments. The server exposes a RESTful API on port 3000 with full OpenAI client library compatibility, enabling drop-in replacement for commercial providers in any application using the standard chat completions format. A built-in web chat UI at the /chat endpoint provides immediate interactive testing without external clients. Custom model repositories allow teams to maintain private catalogs of fine-tuned models alongside the default repository that tracks the latest releases. Deployment workflows generate production-ready Docker images automatically, with Kubernetes manifest support for orchestrated scaling. Native integration with LangChain and LlamaIndex supports RAG pipelines, Transformers Agents enables tool-calling workflows, and HuggingFace Hub handles model discovery. Server-Sent Events enable real-time token streaming across all API endpoints. Backed by BentoML's production ML infrastructure. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache 2.0 licensed.

Your prompts never have to leave the building: TextGen runs open large language models on your own hardware behind a chat interface and an API that speak fluent OpenAI. Load GGUF or Hugging Face weights through llama.cpp, ik_llama.cpp, Transformers, ExLlamaV3, or TensorRT-LLM, and switch models or backends from the interface without restarting the server. Chat mode gives you conversations with characters and system prompts, notebook mode behaves like a familiar completion editor, and both accept image attachments for vision models and documents for context. Models that support tool calling can search the web, fetch pages, and do math through single-file Python tools, and MCP servers plug in for larger tool catalogs. Start it with the API flag and the same model answers at chat, completions, and messages endpoints that mirror OpenAI and Anthropic, complete with streaming, logprobs, embeddings, and optional API key authentication. Portable builds for Linux, Windows, and macOS bundle every dependency, so the distance from download to a running model is an unzip and one shell command. Because everything is local, prompts, documents, and outputs stay on machines you control, and parallel request handling lets a single loaded model serve a whole team's tools at once. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3.0 licensed.

Backed by over 36,000 GitHub stars and 120 contributors with 123 releases since 2022, 1Panel has rapidly become the go-to open-source alternative to cPanel and Plesk for modern Linux server management. The platform delivers a clean Vue.js dashboard powered by a Go backend using the Gin framework, providing visual management of Docker containers, images, networks, and volumes without touching the command line. Its curated app marketplace offers one-click installation of 165+ trusted open-source applications including Nextcloud, Bitwarden, Umami analytics, WordPress, and NocoBase, each running in isolated containers for maximum security. Native AI capabilities set 1Panel apart from every competing panel: deploy Ollama LLMs directly from the dashboard, spin up OpenClaw personal agents, monitor GPU utilization, and manage AI models through a unified interface. Website management includes automatic domain binding, Let's Encrypt SSL certificate provisioning, and Nginx configuration with zero manual setup. Security runs deep with built-in firewall rules, fail2ban integration, container isolation, WAF protection, and comprehensive audit logging enabled from day one. Automated backups support AWS S3, Cloudflare R2, and local storage with one-click restore from any snapshot. The panel supports Debian, Ubuntu, CentOS, and Rocky Linux across x86_64, aarch64, armv7l, ppc64le, and s390x architectures. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. GPL-3.0 licensed.