Stoat
Stoat delivers a complete Discord-like community chat experience that organizations can self-host on their own infrastructure with full data ownership. The platform provides text channels organized in categories, real-time voice calls powered by LiveKit, file sharing with automatic media proxying, custom emoji support, bot framework, GIF search, server invites, and granular role-based permissions — all wrapped in a polished web UI that feels immediately familiar to Discord users. The architecture separates concerns across dedicated Rust binaries handling the REST API, WebSocket real-time events, file storage with S3-compatible backends, push notifications, and media proxying, backed by MongoDB for persistence and Redis for caching. Web, desktop, and mobile clients connect through the same API, ensuring consistent experience across platforms. Unlike federated alternatives such as Matrix, Stoat provides a single-server deployment model focused on the Discord-style community experience: server invites, channel categories, member management, and an invite-first onboarding flow that communities expect. The Docker Compose deployment stack handles all microservices with Caddy providing automatic TLS via Let's Encrypt. 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.
Centrifugo
Benchmarked at one million concurrent WebSocket connections and 30 million delivered messages per minute on a single server, Centrifugo is a self-hosted real-time messaging server that integrates with any backend language — Node.js, Python, Go, Ruby, PHP, Java — without requiring architectural changes to your existing application. It handles persistent connections over WebSocket, HTTP-streaming, Server-Sent Events, gRPC, and experimental WebTransport, routing messages through a channel-based PUB/SUB model with automatic reconnection recovery that replays missed messages from hot channel history. Built-in horizontal scaling operates through Redis (including Redis Cluster, AWS ElastiCache, Valkey, KeyDB, and DragonflyDB), NATS, or PostgreSQL brokers, allowing multi-node deployments without external message queues. The server provides JWT-based authentication using HMAC or RSA keys, granular channel permissions, online presence tracking showing who is currently subscribed to a channel, and an RPC proxy that forwards client calls to your backend over HTTP or gRPC. The embedded ReactJS admin web interface displays real-time connection statistics, node information, and provides an interactive API console for publishing messages, managing subscriptions, and inspecting channel history. Official client SDKs are available for JavaScript, Dart, Go, Swift, and Java, with unidirectional transports requiring no SDK at all. Centrifugo also supports delta updates to minimize bandwidth, connection event proxying, and Prometheus-compatible metrics for Grafana monitoring. 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.
Mumble
Voice chat for a gaming community, a podcast crew, or a distributed team stops depending on someone else's platform once you run your own Mumble server. The Murmur server hosts channels where hundreds of users can talk at once with latency low enough for competitive play, and every conversation is encrypted in transit with certificate-based authentication for identities. Administrators shape access with a detailed permission system: channels can be public, password-gated, or arranged so two groups stay separate while their leaders can speak to both. Users get positional audio in supported games, an in-game overlay showing who is talking, a multi-channel recorder for podcast production, and a public server browser for finding communities. The server side is built for automation: the Ice middleware interface exposes user and channel management to scripts, authenticator modules check logins against existing account databases, and community web interfaces and channel viewers plug into the same API. Running the server is light on resources, and regulars can register their identity once and be recognized across visits without passwords. 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.
Liwan
When you want honest traffic numbers without tracking cookies or stored IP addresses, Liwan puts a real-time analytics dashboard on your own server. The dashboard ranks pages, referrers, countries, browsers, platforms, and devices, charts visitors over time, and filters out bot traffic by default. Session metrics add bounce rate, average time on site, and entry and exit pages, while UTM fields attribute visits to campaigns. Collection is adjustable globally and per site: choose how visitors are grouped, whether to store country and city, country only, or no location, and how long events are kept. Drop rules discard internal, test, and local traffic before storage, and a pruning tool applies new settings to history after a dry-run preview. Tracking is one line of HTML, or your own server can send events with custom names and properties. Location can come from a MaxMind database or from Cloudflare, Vercel, and other proxy headers. One instance holds several projects and sites, with team accounts and single sign-on through Google Workspace, Microsoft Entra ID, or an OpenID Connect provider such as Keycloak or Dex. 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.
Flowcat
Real-time voice agents get a native Rust runtime in Flowcat: it carries a phone or WebRTC call through a composable media pipeline on your own infrastructure, so latency-sensitive audio never queues behind a managed platform. Audio flows from transport into voice activity detection and turn-taking, then through speech-to-text, an LLM, and text-to-speech, or a single speech-to-speech model, and back out to the caller, with in-process SIP and RTP for telephony. Pair it with local Whisper transcription, Kokoro, Piper, or XTTS for speech, and Ollama for reasoning, and a call's audio and transcript never leave your network; cloud providers plug in by name when you prefer them. Describe one agent in a YAML or JSON node-and-edge graph and the single flowcat-server binary serves it over HTTP, opening a browser page with microphone and live transcript, or bridging a Plivo number into the same agent. The runtime stays flat as call volume grows: benchmarked against a multiprocess Python baseline, one process holds p99 round-trip overhead at or below 0.61 milliseconds from 10 to 2,000 concurrent calls, at roughly 19.6 KB of RAM per idle session. Deploy it inside your VPC or an air-gapped environment where call recordings are sensitive. 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.
Openfire
Openfire is a self-hosted XMPP server that gives your organization its own instant messaging network, with one-to-one chat, persistent group rooms, and federation to other XMPP servers, all administered from a web console. Team members connect with any XMPP client on desktop, mobile, or the web and get presence, rosters, offline message delivery, and file sharing inside conversations. Multi-user chat rooms stay available around the clock with configurable history, moderation roles, and access controls, so a support channel or project room keeps its context instead of dissolving into scattered direct messages. The plugin catalog installs from inside the admin console and adds capabilities like message archiving and compliance monitoring, a browser-based chat client, HTTP file upload, and push notifications for mobile clients. An LDAP directory or an existing database can supply users and groups, so accounts stay in sync with the directory your organization already maintains. Server-to-server federation connects your users with contacts on other XMPP domains over encrypted connections, and load balancing spreads busy deployments across multiple instances. TLS certificates, encrypted client ports, and IP-based access lists for the admin console keep the deployment under your control from the first setup wizard onward. 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.
Octo Server
Most team chat keeps people in one app and AI agents in another; Octo Server is the backend that puts both in the same conversation. It powers the OCTO workplace, where Lobsters, the platform's OpenClaw-powered AI agents, sit in channels as first-class participants that read context, run tool calls, and report back alongside their human teammates. Every request flows through one pipeline: token and cookie authentication, organisation-aware role checks and per-channel permissions, business logic that can start or resume an agent session, then fan-out through WuKongIM for real-time delivery. Channels support threaded subspaces, shared files, and a GROUP.md document that stores the group's standing context where the whole team can edit it. The smart summary service reads busy channels and produces structured digests, so catching up means reading one brief instead of hundreds of messages. External bridges connect conversations to GitHub, WeCom, Feishu, and Loop through adapters, and webhooks push group events to your own systems. The official one-command deployment runs the server with the web client, admin console, task service, WuKongIM, MySQL, Redis, and MinIO behind nginx, scaling as one backend that every client speaks to. 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.
Kuzzle
Kuzzle ships a production-ready backend from day one: data storage with Elasticsearch search, real-time pub/sub notifications, user authentication, role-based permissions, and a multi-protocol API serving HTTP, WebSocket, and MQTT simultaneously on port 7512. Rather than rebuilding these standard features from scratch for each project, you get a ready-made backend that accepts connections from web applications, mobile clients, and IoT devices through one unified API surface. Elasticsearch provides persistent document storage with full-text search, geospatial queries, and aggregation pipelines, while Redis handles internal caching and memory storage operations. The Koncorde real-time engine powers pub/sub messaging and database notifications, enabling clients to subscribe to document changes with filter conditions that trigger instant updates when matching data is created, modified, or deleted. User management includes JWT-based authentication, role-based access control with granular permissions at the controller and action level, and pluggable authentication strategies via Passport.js. The extensible plugin framework allows developing custom business logic, additional authentication providers, storage connectors, and protocol handlers. Client SDKs for JavaScript, Dart, Kotlin, and C++ accelerate frontend development, while the Kourou CLI provides command-line API access and project scaffolding. The Vue.js Admin Console offers a web interface for managing indexes, collections, documents, users, profiles, and roles. Horizontal scaling through masterless cluster mode targets 99.99% uptime without single points of failure. 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.
Skytable
Some data refuses to sit still in rows and columns. Skytable is an open-source NoSQL database that stores information in spaces and models instead of rigid tables, letting a record carry strings, numbers, nested lists, and other complex types the way your application actually thinks about them. Developers query it with BlueQL, a language that feels familiar to anyone who writes SQL but adds modern collection syntax and mandatory parameterisation that blunts injection attacks before they start. Underneath, the engine keeps working data in memory, drives multithreaded asynchronous network I/O, batches writes, and persists through a custom append-only storage layer with delayed-durability transactions that trade a tunable sliver of risk for a lot of speed. Client drivers connect applications directly, an interactive shell handles administration and exploration, authentication protects the root account and additional users, and clustering work in progress aims at the high-availability deployments larger systems expect. Teams reach for it when a document store feels too shapeless, a relational database feels too stiff, and latency budgets leave no room for either. 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.