Used by the Rust language community, NASA, Dropbox, and thousands of organizations worldwide with over 25,600 GitHub stars and 1,500+ contributors, Zulip is the only modern team chat app designed from the ground up for both real-time and asynchronous communication through its unique topic-based threading model where every message belongs to a named topic within a channel. This eliminates the context collapse of linear chat by letting teams follow specific conversations without scrolling through unrelated messages, resume threads days later without losing context, and catch up on missed discussions at per-topic granularity. Server 12.0 introduced end-to-end encryption for mobile push notifications, AI-powered search ranking, channel folders for workspace organization, and expanded video conferencing with Jitsi, BigBlueButton, and Zoom integration. Over 100 native integrations connect GitHub, GitLab, Jira, Sentry, PagerDuty, Travis CI, Redmine, dbt, Nextcloud, and n8n with bidirectional notifications, while LLM-driven agents access web-public channels via a standard llms.txt interface. Full-text search covers unlimited message history across all plans, code blocks render with syntax highlighting for 250+ languages, and LaTeX math expressions display inline. The REST API with typed Python and JavaScript SDKs enables custom bots, webhook integrations, and programmatic administration. Import tools migrate entire workspaces from Slack, Microsoft Teams, Mattermost, and Rocket.Chat. 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.

Codync turns the coding agents already installed on your computer into named bots you can message from your phone, so the Claude Code or Codex session on your desk keeps working while you are away. Each bot wraps one agent in one project folder, with its own standing instructions, memory, and approval rules, and several bots run side by side on one machine. Message any bot from the iPhone app, the desktop app, or a terminal; group rooms put bots in one thread, and an @name mention routes a question to exactly one of them. Bots ask each other for reviews inside the room and quote-reply to specific messages. File changes arrive as approval cards naming the file and computer, with Allow once, Always allow, or Deny; finished and blocked work both ping you as push notifications. The connection between phone and computer is end-to-end encrypted through a free relay, your own relay, or directly over the same Wi-Fi or Tailscale. Watch the computer's screen from your phone, hand a bot a computer-use tool, or talk to it in a voice call, and approve every new device per computer with a six-digit code. Your existing agent subscription does the work; Codync never calls a provider API with your login, and there is no paid tier. 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.

Modern engineering teams and busy households deploy Octop to run private, autonomous AI agents equipped with persistent memory workspaces, scheduled cron jobs, and direct browser automation. Users can orchestrate specialist agents tailored for software development, IT operations, content generation, and system diagnostics through an interactive React dashboard. The platform connects directly to Discord, Feishu, DingTalk, and WeCom, allowing team members to delegate complex tasks without leaving their everyday messaging apps. An integrated remote desktop and browser control engine lets agents navigate websites, capture screenshots, fill forms, and operate graphical software autonomously. Administrators can assign distinct MBTI personality profiles to agents, establish granular role-based permissions, configure scheduled cron workflows, and integrate custom Model Context Protocol servers for external tool access. Long-term memory persists across conversations through dedicated workspace files, ensuring contextual continuity whenever switching between underlying language models or team collaborators. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT 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.

Think of it as a team messaging platform where every feature beyond core chat is a plugin you can install or remove, inspired by VS Code's extension model but applied to real-time communication. The Moleculer microservice backend scales horizontally across nodes while Socket.io delivers instant message synchronization with text, images, files, mentions, reactions, and rich Markdown formatting. Available plugins provide LiveKit video conferencing, collaborative drawing boards, task management panels, end-to-end encryption, custom themes, and third-party push notification reception without touching core code. Groups use a two-level space system with customizable panel layouts arranged through drag-and-drop, while role-based access control enforces fine-grained permissions across the organization. The Open Platform exposes OAuth for single sign-on across connected applications and a Bot API enabling bidirectional message processing between Tailchat and external services via HTTP requests. Multi-platform clients cover web, Electron desktop with screenshot capabilities, and mobile apps with native push. Docker Compose deployment bundles MongoDB for persistence, Redis for caching and transport, and MinIO for S3-compatible file storage. Deploy on RepoCloud with a dedicated VPS for persistent team infrastructure under the Apache 2.0 license.

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.

Drag nodes onto a canvas and ship an LLM app: Flowise is an open-source visual builder for AI agents and LLM applications, written in Node.js on LangChain.js and licensed Apache-2.0. You assemble flows by dragging nodes onto a canvas: models, prompts, memory, vector stores, retrievers, and tools, then wire them together and test in the built-in chat panel. Three builder types cover increasing complexity: Assistant for simple RAG chat over uploaded files, Chatflow for single-agent systems with techniques like rerankers and Graph RAG, and Agentflow for multi-agent orchestration with branching, looping, shared flow state, and human-in-the-loop checkpoints. Over 100 integrations connect data sources, vector databases, and both proprietary and open-source models, plus MCP client and server nodes for standard tool interop. Finished flows are exposed as REST APIs, embedded chat widgets, or via JS and Python SDKs - each flow gets an endpoint the moment it is saved, removing the deployment gap between a working prototype and something your application can call. Execution logs, visual step debugging, and external log streaming trace behavior, while input moderation and rate limiting act as guardrails; RBAC, SSO, and workspaces cover team deployments. Self-hosting keeps prompts, encrypted credentials, and conversation data on your own instance, which matters when flows handle internal documents or customer data - and wiring a model, prompt, memory, and vector store on the canvas replaces the boilerplate a hand-coded LangChain project would need.

SourceWeft is an AI workstation you host yourself, where agents, your documents, and your model keys work in one place instead of scattering across chat tabs you do not control. Describe a job and a lead agent breaks it down, handing research, exploration, and execution to focused sub-agents that share the same working context and files. Agents draw on a skill library covering presentations, HTML pages, images, meeting summaries, and study guides, and you can add your own skills so good workflows become repeatable. MCP servers, web search, and web extraction connect agents to outside tools, while approved commands run inside a sandboxed environment that cannot touch the rest of your server. Feed it PDFs, web pages, notes, YouTube videos, Notion, Drive, Gmail, or Slack, then follow citations from any answer back to the source material it came from. Bring your own keys for the chat and indexing models you prefer, organize the team into workspaces with roles and access controls, and pick up any conversation from the web app or desktop clients. 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.

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.

A single ejabberd node carries chat, device telemetry, voice calls, and federated messaging at once, because the same Erlang server speaks XMPP, MQTT, SIP, and Matrix over one authentication, storage, and clustering layer. Users get standards-based instant messaging with group chats, message archives, publish-subscribe, message carbons, push notifications, and OMEMO encryption, and your server federates with the global XMPP network out of the box. Devices publish and subscribe through the built-in MQTT broker on TCP or WebSocket transports, sharing accounts and access rules with your chat users instead of needing a second broker. Voice and video calls route through the integrated SIP gateway and STUN/TURN support, so WebRTC clients get signalling and media relay from the same deployment. Matrix support bridges federated rooms into the same infrastructure, letting two decentralised ecosystems interoperate without a separate bridge stack to babysit. Clustering with consistent hashing scales a deployment across nodes, and a single node is rated at two million concurrent sessions for very large communities. Operators manage everything from the web admin and command line, with SQL or Mnesia storage, LDAP authentication, and virtual hosting for multiple domains on one server. 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 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.

Deploy autonomous conversational AI agents and coordinate complex multi-agent workflows through EDDI, an open-source orchestration middleware that turns declarative configuration files into secure, production-grade enterprise assistants. Engineering teams connect AI models from twelve different commercial and local providers, using bilateral Model Context Protocol tools to let external desktop clients and coding assistants interact directly with running conversational services. Autonomous agents collaborate through structured group interaction patterns including round table discussions, peer reviews, Delphi consensus rounds, and devil's advocate debates to refine generated solutions before delivery. Declarative workflow extensions automate external REST API calls with dynamic request templating, extracting structured properties into persistent conversation memory and chaining multi-step service interactions without custom script glue. Built-in secret vaults safely manage sensitive API credentials, while the centralized web dashboard provides live conversation inspection, token quota enforcement, and comprehensive audit logging for regulatory compliance. 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 over 7,500 GitHub stars and 140 contributors, Matterbridge is the Go-powered chat bridge that connects over 20 messaging platforms through a single TOML configuration file, letting teams communicate across platform boundaries without forcing anyone to switch applications. The gateway architecture routes messages bidirectionally between any combination of Discord, Slack, Telegram, Matrix, IRC, Mattermost, Microsoft Teams, XMPP, Rocket.Chat, Nextcloud Talk, Keybase, Mumble, Twitch, WhatsApp, VK, Gitter, Zulip, ssh-chat, and Harmony, with transparent username and avatar spoofing so bridged messages appear native on each platform. Message edits and deletes propagate across bridges, file attachments and inline images transfer between protocols, threading and reply context is preserved where platforms support it, and private group bridging enables confidential cross-platform conversations. Multiple independent gateways can run simultaneously, each bridging different channel sets with different protocol combinations. The REST API enables third-party integrations and custom bridges without modifying the Matterbridge codebase, while the tengo scripting engine allows inline message transformation and filtering. Game chat support bridges Minecraft and Counter-Strike server chat into messaging platforms. Deployment runs as a single static Go binary with zero dependencies, or as the official Docker image with the configuration file mounted as a volume. 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.

big-AGI is an open-source generative AI workspace that provides a unified, local-first interface for orchestrating multi-model reasoning, automated code execution, and custom persona workflows across private infrastructure. Users query multiple large language models simultaneously through the Beam scatter-gather engine, which prompts independent AI systems in parallel, compares candidate completions side by side, and merges optimal passages into a single refined response. Knowledge workers assemble tailored AI personas equipped with specialized system instructions, custom temperature settings, and predefined document context to handle domain-specific tasks ranging from architectural design reviews to legal contract analysis. The application renders rich multimedia outputs including interactive Mermaid sequence diagrams, LaTeX mathematical formulas, syntax-highlighted code blocks with live execution previews, and AI-generated image generation canvases. Teams integrate local inference servers like Ollama and LocalAI alongside commercial API endpoints to route confidential datasets strictly through internal networks while monitoring per-prompt token usage and operational latency. Users attach complex PDF documents, spreadsheets, and source code repositories for automatic parsing and semantic retrieval, while local-first storage engines ensure private chat transcripts and custom presets remain encrypted on host drives. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

In seven wizard steps, PandaWiki sets up a product docs, manual, FAQ, or blog site whose built-in AI answers visitors using only your own content. Those visitors can chat with an assistant that cites its sources and accepts image questions, or switch to a docs-only search that lists ranked pages with summaries. Publishing stays under control: each document has three switches, visible in navigation, reachable by URL, and answerable by AI, and nothing appears or gets learned until it is published. Authors write in a Markdown and HTML editor, or import from URLs, RSS and Atom feeds, sitemaps, offline .txt, .md, .xlsx, .docx, and .pdf files, Notion, Yuque, SiYuan, Wiki.js, Feishu, Confluence, and DingTalk. Pages export to Word, PDF, or Markdown. The wizard covers models, domain, HTTP or HTTPS ports, import, publishing, answer testing, and page decoration. One knowledge base can also feed a web widget and DingTalk, Feishu, WeCom, and Discord bots. Administrators get a dashboard of visits, questions, visitor regions, hot documents, and referring domains. Chat models come from Baizhi Cloud, DeepSeek, OpenAI, or Ollama, while vector and reranking models are built in. The open-source edition covers one wiki site, 300 documents, and one admin, and its console and documentation are in Chinese. 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.

Self-hosting a language model is only half the job; people still need somewhere pleasant to talk to it, and Chat UI is that window, the same interface that powers HuggingChat. Point it at any OpenAI-compatible endpoint, your own Ollama or llama.cpp server, the Hugging Face router, or a hosted gateway like OpenRouter, and the models it serves appear in the picker automatically, with no per-model configuration. Conversations are saved to your database and stay browsable in the sidebar, so a thread from last week can be reopened, continued, and compared against a fresh answer from another model. Multimodal models accept image uploads right in the composer, and models that support it can call MCP tools mid-conversation to fetch data or run actions. For a shared team deployment, OpenID Connect sign-in keeps individual histories and settings separate, and per-user defaults travel with each account. Everything a consumer chatbot would keep on someone else's servers, prompts, uploaded files, and usage history, stays in the MongoDB you control on the same machine. 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.

Platypus gives a whole team always-on AI agents that reason, call tools, and keep working on your own servers while everyone is offline. Build an agent once by choosing a provider and model, writing its instructions, and capping its tool-calling loop, then reuse that preset across chats and scheduled runs. Agents load reusable Skills on demand and delegate specialist work to sub-agents that appear to the parent as tools. Connect local and remote data through Model Context Protocol servers, or expose an agent to outside agents and chat platforms through A2A endpoints with a token per client. Triggers run agents on a cron schedule, as one-off jobs, or when workspace events such as a card moving on a board occur, and every run records its result. Kanban boards give agents work they can move and update themselves, while notifications and HMAC-signed webhooks push board and workspace events into your own systems with filtering and retries. Facts and preferences are extracted from conversations in the background and injected into future chats, so returning users are remembered. Sandbox backends give agents shell and filesystem access inside an isolated per-workspace environment instead of the host. Organizations and workspaces keep each team's agents and data separate, and blueprints package shared agents, skills, MCP servers, and providers so a new workspace starts pre-equipped. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.