A complete WhatsApp Business Platform covering messaging, chatbot automation, and voice calling with IVR — a combination most self-hosted projects never attempt. The Fastglue/fasthttp backend processes WhatsApp Cloud API webhooks through PostgreSQL and Redis into a real-time WebSocket layer powering instant chat updates across a Vue 3 frontend built with shadcn-vue and TailwindCSS. Chatbot automation supports keyword triggers, multi-step conversation flows with branching logic, AI-powered responses from OpenAI, Anthropic, or Google models, knowledge base integration via vector stores, and seamless handoff to human agents when the bot gets stuck. The visual IVR builder uses a drag-and-drop node canvas where you wire greeting prompts, DTMF menu capture, HTTP callbacks to external APIs mid-call, business-hours routing by IANA timezone, agent team transfers with hold music, and reusable sub-flows. Every call recording streams encrypted to your S3-compatible bucket with retention you control. Multi-tenant architecture isolates organizations with separate data, roles, and API keys while a unified inbox presents both chat and call conversations to agents in a single dashboard. Meta-approved template management, bulk campaign messaging, analytics tracking, and a full REST API round out the platform. Deploy via Docker Compose with Postgres and Redis included. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL v3 licensed.

A private ChatGPT built with Next.js: Lobe Chat is the open-source AI chat interface teams self-host instead. Its main advantage is provider breadth: one interface connects to 40+ model providers, including OpenAI, Anthropic Claude, Google Gemini, Mistral, Groq, AWS Bedrock, Azure, and local models served through Ollama, so you can switch models per conversation and compare outputs. It handles multi-modal work: image recognition, image generation, text-to-speech, and speech-to-text. A plugin system based on function calling and the Model Context Protocol (MCP) adds external tools like web search and code execution. Run it in standalone mode as a single container with settings in browser storage, or in database mode with PostgreSQL and S3-compatible storage for persistent history, multi-user auth, and RAG knowledge bases built from uploaded documents with pgvector retrieval. Because tools arrive through function calling and MCP rather than a proprietary plugin format, custom internal tools can be exposed to the assistant with a standard server over STDIO or HTTP. Hundreds of pre-configured assistant roles import from the community marketplace. For teams the cost model matters: provider API keys billed per token typically undercut a ChatGPT Plus seat per person, and self-hosting keeps API keys, uploaded files, embeddings, and conversation history entirely on your own server.

FastGPT lets you build production AI agents and knowledge base chatbots through a visual drag-and-drop workflow editor, connecting any LLM provider to your documents with retrieval-augmented generation that cites sources and reduces hallucination. The workflow canvas chains LLM calls, conditional branching, HTTP requests, code sandbox execution, and plugin nodes into complex conversation flows and agent skill pipelines without writing backend code. The knowledge base engine ingests documents in ten formats (TXT, Markdown, HTML, PDF, DOCX, PPTX, CSV, XLSX, URL scraping, and CSV batch import) then applies automatic chunking, hybrid vector retrieval with semantic reranking, and QA-pair splitting to deliver accurate, citation-backed answers. FastGPT connects to virtually any LLM provider through its AI Proxy aggregation layer: OpenAI GPT-4o, Anthropic Claude, Google Gemini, DeepSeek, Qwen, ERNIE Bot, and models hosted via Ollama all work through a unified OpenAI-compatible API. Bidirectional MCP support enables agents to call external tools and expose their own capabilities to other systems. Completed applications can be shared via login-free links, embedded as iframe widgets, or integrated with WeCom, Lark, DingTalk, and WeChat Official Accounts through the published REST API. Application operation logs, conversation annotation, and per-model usage analytics provide full lifecycle governance for compliance-sensitive deployments. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. FastGPT Open Source License (Apache 2.0 based) licensed.

With 34,000+ GitHub stars and a v1.5 release driven by 36 merged community pull requests, DeepTutor from Hong Kong University's Data Science Lab delivers a full agent-native learning workspace that goes far beyond chatbot wrappers. Eight integrated surfaces — Chat, Deep Solve, Quiz Generation, Deep Research, Math Animator, Co-Writer, Book generation, and Mastery Practice — share a unified context so the objective follows the learner, not the tool. The platform's three-layer memory architecture (L1 working, L2 session, L3 long-term) makes personalization inspectable rather than opaque, letting users see exactly what the system remembers and why. Knowledge retrieval operates across five pluggable engines — LlamaIndex with FAISS vectors, PageIndex for page-level citations, GraphRAG for knowledge-graph traversal, LightRAG for local or server-offloaded retrieval, and linked Obsidian vaults — with document parsing via MinerU, Docling, markitdown, or PyMuPDF4LLM. Partners extend the tutoring brain to 15+ messaging platforms including Slack, Discord, Telegram, Matrix with E2EE, and Mattermost, each carrying private memory with branch, resume, and replay capabilities. Subagent integration brings Claude Code, Codex, Gemini, and Kimi directly into learning sessions. The system supports 30+ LLM providers from OpenAI and Anthropic to Ollama for fully local operation, with multi-user isolation, admin controls, and a full CLI interface. 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.

Matrix's flagship client, built by the protocol's creators: Element brings the decentralized open standard for real-time communication to web, desktop, iOS, and Android. Paired with a Matrix homeserver, it delivers Slack-quality team messaging where you own every message, file, encryption key, and byte of metadata. End-to-end encryption is on by default, built on Olm and Megolm - the Double Ratchet algorithm family Signal popularized, extended for large-room scalability and publicly audited by NCC Group. Messages encrypt per-device with cross-signed device verification, so even a compromised server yields nothing readable. Federation is the defining capability: like email, users on different homeservers converse seamlessly, and 30+ bridges connect Matrix rooms to Slack, Discord, WhatsApp, and Telegram, so moving to sovereign infrastructure doesn't sever contact with anyone. Rooms support threads, reactions, file sharing, and voice and video calls via Element Call. The result is digital sovereignty chosen by governments and enterprises across Europe: your data sits on your server in your jurisdiction, portable to any other Matrix host because the protocol is an open standard. Apache-2.0 licensed, with no per-user fees at any scale.

Twitch and YouTube Live, replaced by infrastructure you control: Owncast is a self-hosted live streaming and chat server. Point OBS, Streamlabs, or any RTMP-capable broadcaster at the server's ingest port, and Owncast transcodes the feed with FFmpeg into HLS with multiple quality variants, playing it in a built-in web page with a real-time chat beside it. Chat supports anonymous participation, custom emotes, and moderation tools - message removal, user bans and suspensions - with optional authentication via IndieAuth or a Fediverse account. ActivityPub integration puts the stream on the Fediverse: viewers on Mastodon and compatible services can follow a channel and get notified the moment it goes live. Video delivery can come straight off the server or offload HLS segments to S3-compatible object storage so a modest VPS handles thousands of concurrent viewers while only managing ingest and chat. The backend is a single Go binary with a React frontend - no accounts platform, no database server, no dependency stack - and the player embeds in any website. MIT-licensed, with roughly 9k GitHub stars, zero platform fees, and no algorithm or takedown policy between you and your audience.

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.

With over 24,000 GitHub stars and origins in the MemGPT research paper on virtual context management, Letta has evolved into the leading open-source platform for building AI agents that maintain persistent memory, identity, and continuity across sessions rather than operating as stateless prompt-response loops. The core architecture uses memory blocks — structured, labeled text chunks that reside permanently in the agent's context window — allowing agents to programmatically rewrite their own memory, learn new skills, and improve through a sleeptime dreaming process that runs reflection and memory organization during idle periods. The self-hosted App Server deploys via Docker and exposes a WebSocket API on port 4500, letting the TypeScript Agent SDK connect from any application using local, remote, or cloud backends. Agents support git-versioned memory through MemFS where every memory change is tracked and auditable, multi-agent communication via subagents, scheduled tasks, and integration with messaging platforms including Slack, Discord, Telegram, WhatsApp, and Signal. The platform is fully model-agnostic, routing to OpenAI, Anthropic, xAI, or self-hosted open-weight models through Ollama depending on cost, performance, and data residency requirements. The Agent File format serializes complete agent state — memory, skills, prompts, and conversation history — into portable snapshots. Desktop applications for macOS, Windows, and Linux provide native interfaces alongside the terminal CLI and web chat at chat.letta.com. 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.

Casibase lets organizations build AI-powered knowledge bases that answer questions from their own documents, connecting to 30+ model providers through a unified admin interface with RAG retrieval and multi-agent orchestration via MCP and A2A protocols. The platform plugs into OpenAI GPT-4o, Anthropic Claude, Meta Llama, Google Gemini, DeepSeek, Ollama local models, HuggingFace, Azure OpenAI, and additional providers, while embedding APIs from OpenAI Ada and Baidu handle vector representation of ingested documents. Document ingestion parses TXT, Markdown, DOCX, PDF, CSV, XLSX, and PPTX files with intelligent chunking strategies for optimal retrieval accuracy. The built-in chat interface provides real-time AI conversations with manual session handover for human agent escalation, and comprehensive chat session logging enables audit trails for compliance. Enterprise identity management integrates Casdoor for Single Sign-On supporting GitHub, Google, WeChat, and OIDC providers with fine-grained access control via the Casbin permission engine. The multi-tenant architecture supports isolated knowledge bases per organization with role-based user management and configurable storage, model, and embedding providers per tenant. The React frontend with Ant Design v5 provides a polished admin dashboard for managing providers, knowledge stores, chat sessions, and user access, while the Go backend with Beego framework handles API logic with MySQL or MariaDB persistence. 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.

With nearly 5,000 GitHub stars and a Hacker News launch that garnered 147 points, Colanode delivers the first genuinely local-first alternative to both Slack and Notion in a single self-hosted workspace — writing every operation to a client-side SQLite database before syncing to your server, so teams work at full speed offline, on planes, or through intermittent connections without ever losing a draft. The real-time chat system provides channels and direct messages with instant delivery via WebSocket, while the rich text editor offers Notion-style block-based pages for documents, wikis, meeting notes, and knowledge bases with headings, code blocks, embeds, and nested hierarchies. Customizable databases organize structured data with custom fields and three dynamic views — table for spreadsheet-style browsing, kanban for visual workflow boards, and calendar for time-based planning. Conflict-free Replicated Data Types powered by Yjs handle concurrent editing across pages and database records: multiple users modify the same document simultaneously and the system merges changes automatically without manual conflict resolution. File management supports upload, sharing, and organization within workspaces using pluggable storage backends including local filesystem, S3-compatible services, Google Cloud Storage, and Azure Blob Storage with TUS resumable uploads for large files. The server runs Fastify with Zod validation on Node.js 20+, persists to PostgreSQL with pgvector extension, uses Redis for event broadcasting, and deploys via a single Docker image. 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.

LibreDesk unifies live chat, email, and future channel integrations into a single agent inbox where every customer conversation converges regardless of origin, replacing per-seat-priced tools like Zendesk, Intercom, and Freshdesk with a zero-cost alternative that has surpassed 2,000 GitHub stars. Built on a Go backend with a Vue.js 3 and ShadcN UI frontend, it ships as a single binary requiring only PostgreSQL and Redis. The embeddable live chat widget drops onto any website with a snippet, while the AI assistant handles initial customer queries using answers grounded in your knowledge base before escalating to human agents when needed. Agent copilot drafts replies, summarizes conversation threads, and rewrites messages for tone adjustment directly within the inbox interface. Automation rules trigger on conversation events to tag, assign, and route tickets based on configurable conditions, while auto-assignment distributes workload by agent capacity or custom criteria. SLA management tracks response and resolution time targets with breach notifications, and automated CSAT surveys measure satisfaction after conversation closure. Macros save frequently sent responses as reusable templates that simultaneously set tags and assign conversations. Role-based access control provides granular per-action permissions for teams and individual agents, and SSO supports Google, Microsoft, and any OIDC provider. The HTTP/JSON API and webhook system enable custom integrations with external tools. 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.

Evolution API gives your applications a production-ready REST interface to WhatsApp, supporting both free Baileys-based Web connections and Meta's official Business Cloud API from the same server. With 9,200+ stars and 7,100+ forks, it is the most widely deployed WhatsApp integration layer available. Each installation handles unlimited isolated instances (one per phone number) with independent auth, webhooks, and database separation via Prisma ORM against PostgreSQL or MySQL, cached through Redis. Message types include text, images, audio, video, documents, contacts, locations, interactive buttons, list messages, carousel cards, and PIX payment links through unified endpoints. Native integrations connect to Typebot for chatbot flows, Chatwoot for multi-agent support, Dify and OpenAI for AI conversations, N8N and Flowise for workflow automation, and RabbitMQ, Kafka, or SQS for enterprise event streaming. Socket.io delivers real-time message and connection events. Amazon S3 or MinIO handles media offloading. The Evolution Manager v2 dashboard provides visual instance creation, QR code scanning, connection monitoring, and integration configuration without touching the API directly. Docker Compose bundles the server, PostgreSQL, and Redis with environment-variable-driven setup. 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.

Tiledesk lets you build AI-powered conversational agents with a visual drag-and-drop designer, then deploy them simultaneously across web chat, WhatsApp, Telegram, Facebook Messenger, Instagram, email, and Slack without rebuilding per channel. The no-code Design Studio combines LLM-powered conversations with conditional logic, external API calls, and branching dialogue trees that work identically everywhere. Multi-RAG knowledge management separates content into isolated repositories with hybrid search combining traditional full-text retrieval and semantic understanding via Qdrant vector embeddings, enabling accurate answers even when users phrase queries in unexpected ways. LLM integration supports GPT-4, GPT-4o, Anthropic Claude, and any model exposing an OpenAI-compatible API including locally hosted models via Ollama for complete data sovereignty. The human-in-the-loop system provides seamless escalation from AI agents to live support staff with full conversation context preserved, while multi-agent workflows enable complex orchestration where specialized bots collaborate on different aspects of a customer interaction. REST and MQTT APIs power integration with external systems and webhook-triggered automations, and pre-designed templates accelerate common scenarios. Docker Compose deployment starts the full stack including server, dashboard, messaging engine, and widget. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

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.

Haven gives your community a private chat server with voice calls, screen sharing, and end-to-end encrypted direct messages where friends join via invite link in their browser without installing apps or creating third-party accounts. Real-time messaging supports image uploads via paste and drag-drop, emoji reactions, replies, threads, typing indicators, @mentions with autocomplete, and inline GIF search through Tenor or GIPHY. Peer-to-peer WebRTC voice chat includes per-user volume sliders, mute and deafen controls, talking indicators, and screen sharing with picture-in-picture mode. Direct messages use ECDH P-256 key exchange with AES-256-GCM symmetric encryption where private keys never leave the browser, ensuring not even the server operator can read them. Twenty-plus visual themes with stackable effects including CRT scanlines, Matrix Rain, Cyberpunk Text Scramble, Snowfall, and Campfire Embers let users personalize the experience with configurable intensity sliders. Rich Presence integration shows what members are playing or listening to via Last.fm, Steam, and Spotify. A built-in bot API supports webhooks and custom slash commands, while Discord history import preserves channels, threads, forums, reactions, pins, and avatars. The Node.js server deploys via Docker Compose or a single batch file that auto-handles dependencies, SSL certificates, and 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.

Bring your own API keys and work with OpenAI GPT models, Anthropic Claude, Google Gemini, Mistral, DeepSeek, Grok, Azure endpoints, and local models in one organized workspace: TypingMind is a unified chat frontend for large language models, replacing a browser tab per provider. Parallel chat sends the same prompt to multiple models and compares answers side by side, and models can be switched mid-conversation. A prompt library stores reusable, tagged prompts with variables, and the AI Agents system builds specialized assistants that bundle a base model, custom instructions, assigned plugins, and uploaded knowledge files for RAG. Plugins extend every connected model with web search, image generation (DALL-E, Stable Diffusion), Deep Research, URL reading via Firecrawl, and Zapier automation - plus MCP server integrations for Notion, Atlassian, and other external tools, and a JavaScript extension API for custom behavior. Chats store locally by default with optional sync. Self-hosting puts the interface on your own domain and, for teams, adds branding, member access limits, and shared prompt and agent libraries.

Build, deploy, and monitor chatbots and LLM-powered agents on one open-source conversational AI platform: Botpress. Its Studio is a visual development environment: a drag-and-drop canvas arranges conversation logic with nodes for messages, questions, choices, and actions, while a built-in emulator simulates conversations for debugging before anything goes live. Agents ground their answers in a knowledge base assembled from uploaded documents, ingested websites, and past conversations via retrieval-augmented generation, and the LLM layer connects to multiple model providers - GPT-4, Claude, Mistral - with a configurable model strategy. An autonomous engine handles reasoning, tool orchestration, persistent memory across sessions, and sandboxed code execution, and custom code actions in TypeScript extend agents past prebuilt workflows. Over 100 integrations deploy the same bot to WhatsApp, Telegram, Slack, Microsoft Teams, and web chat, and connect it to HubSpot, Zendesk, Zapier, and arbitrary APIs and webhooks. Human handoff, conversation analytics, and quality monitoring cover production operation. Originating in 2017 from a Montreal team, the community edition is developed openly on GitHub.

Revolt gives communities the full Discord experience without ads, behavioral tracking, or subscription fees: servers with text and voice channels, direct messages, group conversations, roles, bots, and custom emoji at zero cost per user. The Rust microservices backend splits responsibilities across Delta for REST API and authentication, Bonfire for persistent WebSocket real-time event delivery, Autumn for file upload routing to MinIO S3-compatible object storage, and January for link preview proxy and embed generation. Voice chat operates through LiveKit with WebRTC audio streaming supporting multiple concurrent participants per channel. Server administrators configure hierarchical role-based permissions at the server, channel, and per-role level, controlling who can send messages, manage channels, kick members, and access moderation tools. Text channels support Markdown formatting, custom emoji, file attachments up to 20 MB, GIF search via Tenor integration, and message reactions. The bot API enables automated moderation, entertainment, and custom workflow integration with community-maintained libraries available in JavaScript, Python, and Rust. The TypeScript and Solid.js web frontend provides a responsive interface with theme customization. Docker Compose deployment spins up the complete stack including MongoDB for message and user storage, Redis for caching, and MinIO for attachments, providing complete data sovereignty over all conversations and files. 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.