Open Source App Cloud Marketplace
Deploy, host, and scale with one click, at half the cost. Then customize with AI agents.
n8n
Webhooks, cron schedules, and app events trigger chains of nodes that fetch, transform, and route data: n8n is a workflow automation platform built around a visual, node-based editor. It ships with 400+ built-in integrations covering databases like Postgres, SaaS tools like Slack and HubSpot, and every major AI provider. When a pre-built node does not exist, the HTTP Request node calls any REST API, and the Code node runs JavaScript or Python inline, so you are never blocked by a missing connector. Workflows execute as directed graphs with branching, loops, error handling, and sub-workflows, and every run is logged for inspection and replay during debugging. It also includes LangChain-based nodes for building AI agents with tool calling and memory. Self-hosting on RepoCloud gives you unlimited workflow executions with no per-task pricing, and all data stays on your instance. Runs on Node.js with SQLite by default; add Postgres and Redis queue mode when you need to scale workers horizontally.
OpenClaw VPS
A personal AI assistant that remembers what it learns and reaches you wherever you are — OpenClaw is an open-source agent gateway built by the OpenClaw Foundation with 247,000+ GitHub stars. It connects to 200+ LLM models through providers like Anthropic, OpenRouter, and OpenAI, and meets you on 21+ messaging channels: Telegram, Slack, Discord, WhatsApp, Signal, iMessage, Matrix, and more. Persistent memory with full-text search lets the agent recall context across sessions, and a self-improving skills system means it gets more capable the longer it runs. Voice wake words and talk mode enable hands-free interaction on macOS, iOS, and Android. A live canvas provides an agent-driven visual workspace. Built-in browser automation, cron scheduling for unattended tasks, and subagent spawning for parallel workstreams round out the toolset. The gateway architecture keeps all sessions, credentials, and conversation history on your own server — nothing transits a third-party cloud unless you choose to connect one. The API key you provide for your chosen LLM provider powers the underlying calls; billing goes through your own account. Running on a dedicated VPS with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
Dokploy VPS
Your own Heroku or Vercel on a dedicated server — Dokploy is the open-source PaaS that replaces cloud platform subscriptions with a single dashboard you control. Point it at a Git repository or a Docker image, and it builds and deploys the application using Dockerfiles, Nixpacks, or Heroku/Paketo buildpacks. Traefik handles reverse proxying, routing, load balancing, automatic Let's Encrypt SSL, and HTTP/3. Databases — MySQL, PostgreSQL, MongoDB, MariaDB, libsql, and Redis — provision from the UI with automated backups to any S3-compatible destination. Complex multi-service applications deploy through native Docker Compose support, and multi-node scaling uses Docker Swarm. The web dashboard covers environment variables, volumes, resource limits, real-time CPU/memory/network monitoring, and deployment logs, with a CLI and REST API for automation. Deploy notifications go to Slack, Discord, Telegram, or email. One-click templates install common open-source tools, and a single control plane can manage deployments across multiple remote servers. Because everything is standard Docker, there is no lock-in: Dockerfiles, Compose files, and data volumes work anywhere else Docker runs. The push-to-deploy workflow of a $20/seat cloud PaaS, running on a dedicated VPS with guaranteed CPU, RAM, SSD, and full root access — no per-app, per-environment, or per-seat fees regardless of how many applications you deploy. 26,000+ GitHub stars.
Coolify VPS
The open-source PaaS with 55,000+ GitHub stars and the largest one-click service catalog in its class — Coolify gives you the Vercel push-to-deploy workflow on a dedicated server you control. Connect a GitHub, GitLab, Bitbucket, or Gitea repository and every push builds and deploys automatically via Nixpacks, a Dockerfile, or Docker Compose, with Traefik or Caddy reverse proxying, automatic Let's Encrypt certificates, and per-branch preview deployments with their own URLs. Databases — PostgreSQL, MySQL, MariaDB, MongoDB, Redis — provision in a few clicks, and a catalog of 280+ one-click service templates covers WordPress, n8n, Grafana, MinIO, Plausible, Ollama, and more. One dashboard manages the entire server, with Docker Swarm available for clustering multiple nodes. Backups go to any S3-compatible storage with one-click restore, and a full API supports CI/CD integration. All configuration lives on your own server, so resources keep running even if you stop using Coolify — no vendor lock-in by design. Running on a dedicated VPS with guaranteed CPU, RAM, and SSD, full root access via SSH and browser console. Apache 2.0 licensed.
Supabase
With over 107,000 GitHub stars and adoption by teams at Mozilla, 1Password, Peerlist, and thousands of startups, Supabase has become the most widely deployed open-source Firebase alternative — built entirely on PostgreSQL rather than a proprietary NoSQL store. Every project provisions a dedicated Postgres database with 40+ preinstalled extensions, auto-generating REST APIs via PostgREST, GraphQL via pg_graphql, and real-time change streams via an Elixir-based WebSocket engine that supports database change listeners, user presence tracking, and arbitrary broadcast messaging. Authentication covers email and password, phone OTP, magic links, and 20+ social providers including Google, GitHub, Apple, Azure, and SAML SSO, all enforced through Postgres Row Level Security policies that run inside the database itself. S3-compatible object storage delivers files through a CDN spanning 285+ cities with on-the-fly image transformations powered by imgproxy. Edge Functions run globally distributed TypeScript on the Deno runtime with Node.js compatibility and access to over two million NPM packages. The pgvector extension stores, indexes, and queries vector embeddings for AI-powered semantic search and retrieval-augmented generation workflows. Supabase Studio provides a browser-based dashboard with a table editor, SQL editor, schema visualizer, and log explorer. Official client SDKs ship for JavaScript, Python, Flutter, Swift, Kotlin, C#, Go, and Ruby. The self-hosted Docker Compose stack runs fourteen coordinated services including Kong API gateway, Supavisor connection pooler, and Logflare analytics. 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.
OpenBot
Open source GrokBot, built by the team behind the AG-UI protocol. OpenBot is the open-source enterprise agent platform that gives every AI coworker its own sandboxed computer — a real Chromium browser with its own login sessions, a private filesystem, and only the MCP tools you explicitly grant. The centralized gateway evaluates CEL policy rules against tool name, intent, bot identity, page URL, element attributes, and file paths before any action executes, writing an immutable audit row for every call and outcome. Any agent that speaks AG-UI — LangGraph, Mastra, CrewAI, Pydantic AI, Google ADK, or hand-written endpoints — registers as a Bot and receives its own channel with persistent conversation history. The take-the-wheel system lets humans assume control when an agent encounters login walls or two-factor prompts, recording control transfers as structured audit events. Knowledge documents from Google Drive and OneDrive carry source-based permissions where deny principals always win and ambiguous mappings refuse retrieval entirely. The React and Vite frontend provides live screen viewing of each agent's browser, channel-based chat, admin settings, and component galleries. The Hono API server on port 3001 handles authentication, role-based access, tenant packaging, and credential management backed by PostgreSQL with pgvector. Deploy via Docker Compose with the included supervisor that manages per-bot computer containers. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
Hermes Agent
OpenRouter's most-used application by token volume — over 17 trillion tokens processed — Hermes Agent is an open-source autonomous agent built by Nous Research that lives on your server and gets more capable every day. Define a goal in natural language and Hermes plans sub-tasks, executes them through tool integrations, observes results, handles errors, and refines until the job is done or it genuinely needs your input. Persistent memory with full-text search and LLM summarization lets it recall context across sessions, and an agent-created skills system self-improves after complex tasks. A messaging gateway connects Telegram, Discord, Slack, WhatsApp, Signal, and 16 more platforms with cross-channel conversation continuity. A built-in cron scheduler runs daily reports, nightly backups, and weekly audits unattended. Subagent spawning parallelizes workstreams, and six terminal backends — local, Docker, SSH, Singularity, Modal, and Daytona — fit any infrastructure. Works with any LLM provider: Nous Portal, OpenRouter for 400+ models from 70+ providers, OpenAI, Anthropic, or your own endpoint. The API key you supply powers all LLM calls; billing goes through your own account. Running on a dedicated VPS with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
CashPilot
Idle bandwidth and spare hardware earn nothing sitting unused, so CashPilot deploys passive-income services across your servers and shows every balance in one web dashboard. From the catalog you start Docker earners such as Honeygain, Earn.fm, Traffmonetizer, PacketStream, ProxyRack, MystNodes, Storj, and Sia hostd with one click, no compose files to write, and you can add any service the catalog lacks by image name under the same container restrictions. Providers that run as browser extensions, desktop apps, or GPU nodes, 24 of them, are tracked alongside, while 15 built-in collectors read balances every hour into a single earnings history, so a service that runs without earning shows up as a flat line instead of a surprise. When a balance drops, CashPilot treats it as a probable payout and asks you to confirm rather than counting income by guesswork. One worker runs on each server under a single dashboard, with every figure broken down per server and per service. Extra copies of a service can earn through SOCKS5, HTTP CONNECT, or Tailscale exit-node proxies and stop dead if the proxy dies instead of leaking your real address. Earners are fenced off from your LAN, the host, your tailnet, and cloud metadata by default, and per-service guides flag restrictions such as providers that ban datacenter IPs. 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.
Knowhere
With 2,600+ GitHub stars since its May 2026 open-source launch, Knowhere solves the last-mile problem of document intelligence for AI systems — transforming complex unstructured PDFs, reports, and multi-page documents into structured JSON chunks that LLMs can consume without hallucination. The platform processes documents through an AI-native parsing pipeline that handles 20+ page documents with deep hierarchies, intricate tables, and multimodal content including images with OCR, achieving 95% precision in information extraction while reducing token costs by 50% compared to raw document ingestion. The knowledge tree architecture maintains historical context across multiple documents, enabling cross-document graph navigation for agentic retrieval that goes beyond simple chunk-based RAG. Built on Python 3.11+ with MinerU as the default PDF parser, the backend API runs alongside async workers that process document ingestion, graph construction, and embedding generation. The self-hosted Docker Compose stack packages the API server, processing workers, and Next.js dashboard for managing API keys, webhooks, and document-processing jobs, backed by PostgreSQL and Redis. Both Python and Node.js SDKs provide programmatic access for integration into existing AI pipelines and agent frameworks. LLM providers include DeepSeek and Alibaba Cloud DashScope with configurable key rotation for rate-limit management. Deploy 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.
Gotify
Real-time alerts from your own infrastructure to your phone, with no Firebase, Pushover, or third-party push service in the path: Gotify is a simple, self-hosted notification server written in Go. The model is deliberately minimal: senders push messages with a single HTTP POST to the REST API, receivers subscribe over a WebSocket stream, and a clean React web UI manages the pieces. Senders are namespaced as "applications," each with its own token, so your backup script, Uptime Kuma, CI pipeline, and cron jobs each get an identity, an icon, and independently revocable credentials - centralized alerting from many services with per-source management. Messages carry a title, body, and priority level that maps to notification importance on the client. The official Android app (on both F-Droid and Google Play, notable for working entirely without Google Play Services) shows push notifications for new messages; the web UI itself supports Web Push in the browser; and gotify/cli pushes messages from shell scripts with one command. A server-side plugin system adds custom behavior, and the whole thing runs as a single small binary with SQLite by default - near-zero resource footprint. Because dozens of tools (and Apprise) speak Gotify natively, it slots in as the notification hub for an entire homelab or ops stack.
WA-AKG
WA-AKG turns ordinary WhatsApp numbers into a programmable messaging API, so your apps, CRMs, and automations can send and receive WhatsApp messages through a dashboard and REST endpoints instead of a phone. Connect several numbers at once by scanning QR codes, and each session stays visible with its connection state, ready for messages, media, documents, and stickers. The scheduler queues text and media for exact delivery times, and broadcasts go out in batches with randomized delays that keep sending patterns human. Keyword auto-replies answer common questions around the clock in private chats, groups, or both, with whitelists and blacklists deciding who the bot engages. Webhooks forward incoming messages, connection changes, and group events to your own systems in real time, and an n8n node plugs the gateway straight into workflow automations. Contacts sync with verified names and profile pictures, a sticker maker with background removal handles media chores, and the full API is documented in Swagger for client generation. The dashboard speaks English, Bahasa Indonesia, and Brazilian Portuguese, so support teams can run campaigns and customer conversations from the browser. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
Text Generation Web UI
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.
Papercups
Companies with privacy and security concerns about piping customer conversations through Intercom or Zendesk run Papercups - open-source live customer chat. The stack is a deliberate strength: an Elixir/Phoenix API over PostgreSQL, with real-time messaging powered by Phoenix Channels and Presence - the same BEAM foundation trusted by Discord and PagerDuty for fault-tolerant, low-latency messaging. Customers see a customizable chat widget that embeds in any site as an HTML snippet, a React component, or even inside React Native apps, with configurable colors, greetings, and away messages. Your team sees a dashboard for managing conversations - close, assign, and prioritize - with Markdown and emoji in replies. The killer workflow is the reply-channel integration: connect Slack or Mattermost and every customer conversation becomes a synced thread your team answers without leaving the tool they already live in, with two-way message syncing handled by webhooks. Email and SMS channels extend intake beyond the widget, an analytics dashboard tracks communication patterns, and the Storytime feature adds real-time screen sharing to watch users navigate while you help them. A documented API supports fully custom chat UIs in Svelte, Flutter, or Vue. MIT-licensed and GDPR-conscious - customer data stays in your PostgreSQL.
MediaWiki
With MediaWiki, the wiki software behind Wikipedia, a team writes one shared knowledge base in plain wikitext or a visual editor while every revision stays saved for comparison and rollback. Page history names the author and edit summary of each change, and a side-by-side diff shows exactly what moved before anyone reverts. Talk pages hold threaded discussions with inline replies, notifications announce mentions and thanks, and watchlists flag the pages you follow. Namespaces, categories, redirects, and reusable templates give a large wiki its structure, and Lua modules written for Scribunto power infoboxes. Uploaded images get automatic thumbnails and a full-screen lightbox. Bundled extensions add PDF handling and math rendering for documentation that needs more than text. Group-based permissions decide who may read, edit, protect, or delete. A wiki can stay open to everyone or sit behind a login. AbuseFilter, CAPTCHAs, blocklists, and two-factor sign-in help fend off spam and account takeovers. Vector 2022 brings a sticky table of contents and an optional dark mode. The interface is localized in over 350 languages. Bots and scripts log in, read, search, and edit with the Action API. Use it for company handbooks, engineering runbooks, course notes, fandom encyclopedias, and public reference sites. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. GPL-2.0-or-later licensed.
Flagsmith
With over 6,400 GitHub stars, 130 contributors, and 512 releases, Flagsmith is the open-source feature flag and remote configuration platform that gives development teams granular control over feature releases, remote configuration values, user segmentation, and A/B testing from a single self-hosted dashboard. Feature flags support boolean toggles and remote config values simultaneously — every flag carries both an enabled state and a configurable value, letting teams deploy functional and visual changes without code modifications or app store approvals. User segments target audiences by attributes, percentage rollouts, and custom rules, enabling beta testing, canary releases, and gradual feature rollouts with real-time toggle control. Multivariate flags split traffic across multiple variations with configurable percentage weights for A/B and multivariate testing with analytics integration. The flag evaluation engine runs server-side with local evaluation mode in SDKs for sub-millisecond performance without network calls, supporting 15+ languages including TypeScript, Python, Java, C#/.NET, Go, Ruby, PHP, Swift, Kotlin, Flutter, React, and Next.js. The REST API and webhooks enable integration with CI/CD pipelines, and pre-built connectors exist for Datadog, New Relic, Amplitude, Mixpanel, Segment, Heap, Rudderstack, and Slack. Built on Django with a React frontend, self-hosting deploys via Docker Compose with PostgreSQL, or via Helm charts and the OpenShift Operator for Kubernetes environments. Change history provides a complete audit trail of flag modifications. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. BSD-3-Clause licensed.
Logseq
Every line an indentable bullet, every bullet a first-class block that can be referenced, embedded, and queried anywhere: Logseq is a privacy-first, local-first knowledge platform built around the block outliner. The daily journal is the system's beating heart - each day opens a fresh date-stamped page where tasks, meeting notes, and fleeting ideas land as blocks without filing decisions, then connect later through [[wikilinks]] with automatic bidirectional backlinks and ((block references)) that transclude any bullet into any page. Everything persists as plain Markdown or Org-mode files on disk - git-friendly, greppable, and owned forever, with sync via iCloud, Dropbox, Syncthing, Git, or an optional end-to-end encrypted service. Built-in tooling goes beyond notes: TODO/DOING task states with scheduling, native PDF annotation with area highlights, spaced-repetition flashcards, whiteboards for visual thinking, Zotero integration for researchers, and Datalog-powered queries that build dynamic views across the entire graph. A marketplace of hundreds of community plugins and themes adds AI chat, Ollama local-model integration, and custom workflows. Written in Clojure/ClojureScript, AGPL-3.0 licensed with 320+ contributors, and completely free - the local-first Roam for people who refuse subscriptions and lock-in.
Duplicati
Encrypted, incremental, compressed backups on storage you already have - Amazon S3, Backblaze B2, Google Drive, Azure, OneDrive, Dropbox, MEGA, Storj, WebDAV, SFTP, FTP, SMB, or a plain local disk - is what the MIT-licensed Duplicati has quietly done for years. Its security model is Trust No One: every block is encrypted with AES-256 (or a local GPG instance) before leaving the machine, and the passphrase never travels, so the storage provider holds only ciphertext. The block-based storage engine gives the best of both backup worlds: after one initial full backup, only changed data blocks upload - modify a tiny part of a huge file and only that part transfers - yet every backup version restores like a full backup in a single operation, with no incremental chains to replay. Deduplication and compression keep remote storage growth slow even across years of versions. A web interface manages everything: the built-in scheduler keeps backups current automatically, flexible filters select folders, file types, or custom patterns, retention policies prune old versions, and an integrated updater flags new releases. On compatible object-lock backends, immutable (WORM) storage protects backup data from ransomware that reaches the credentials. Runs on Windows, macOS, and Linux, free even for commercial use.
Netron
Hand Netron an ONNX, TensorFlow Lite, PyTorch, Core ML, or Keras file and the whole network appears as a zoomable graph, with no training framework or inference runtime required to read it. The same viewer opens TorchScript, torch.export, ExecuTorch, TensorFlow, OpenVINO, Caffe, Darknet, Safetensors, and NumPy files, with experimental support for MLIR, JAX, GGUF, RKNN, ncnn, MNN, PaddlePaddle, and scikit-learn. Click a layer to read its type, attributes, inputs, and outputs; click a weight to see its shape, data type, minimum, maximum, mean, standard deviation, and sparsity. Find searches nodes, connections, and weights by name and centers the graph on the match you pick. Toggle attributes, names, and weights on the canvas, flip between vertical and horizontal layouts, and watch light and dark themes follow the system setting. Model and graph panels list the format, producer, imports, graph inputs and outputs, and parameter counts. Any view exports as a PNG or SVG image for documentation, pull requests, and papers. Install with pip, then run netron model.onnx with a host and port, or call netron.start from Python, and the built-in HTTP server delivers the graph to any browser that can reach it. Teams point reviewers at one shared address to check exported models and conversion results. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.