Chat with your own documents: AnythingLLM, from Mintplex Labs, wraps retrieval-augmented generation (RAG) in an open-source application anyone can run. You organize content into workspaces, each an isolated namespace with its own documents, vector embeddings, chat history, and settings, so one instance can hold several separate knowledge bases. Upload PDFs, DOCX, TXT, and other formats, or scrape web pages; the built-in collector parses and chunks them into a vector database (LanceDB by default, with Pinecone, Chroma, Qdrant, and others supported). Answers cite their source documents. It works with both cloud LLMs (OpenAI, Anthropic, Gemini) and local ones via Ollama or LM Studio, and the embedding model is separately configurable. Beyond RAG chat, it includes AI agents that can browse the web and run tools, an embeddable chat widget for your website, a developer API, and multi-user mode with admin, manager, and default roles plus per-workspace access control. Context assembly is smarter than naive RAG: pinned documents, attached files, vector search hits, and recent chat history are combined under a token budget so the model's context window is filled efficiently, and each workspace supports multiple independent conversation threads against the same knowledge base. Because the embedding model, vector store, and chat LLM are all independently swappable, you can move between providers without re-ingesting a single document. The stack is Node.js with a React frontend, MIT-licensed.

Retrieval-augmented chatbots on your own knowledge base - that is the whole mission of Dialoqbase, an open-source bot-building platform. Feed it content through a broad set of data loaders - web pages and full crawls, sitemaps, PDFs, DOCX, CSV, plain text, GitHub repositories, YouTube videos, and MP3/MP4 audio - and it handles the whole RAG pipeline in one self-contained app: chunking, embedding, vector storage, and LLM querying. The distinguishing architecture choice is PostgreSQL with pgvector for embedding storage and similarity search, which removes the separate vector-database dependency, and Redis-backed Bull queues for ingesting large documents without blocking the API. Model choice is wide open: OpenAI, Anthropic Claude, Google Gemini, Cohere, Fireworks, Hugging Face, local models via Ollama, and any OpenAI-compatible endpoint, with an equally broad list of embedding providers. Finished bots embed on any website with customizable styling or deploy to Telegram, Discord, and WhatsApp, and an API creates and manages bots programmatically. Multi-user support adds registration limits and per-user bot quotas. MIT-licensed and free for commercial use.

Teams that cannot send messages through someone else's cloud run Mattermost - the open-core, self-hosted alternative to Slack. It provides public and private channels, threaded discussions, unlimited search history, file sharing with previews, one-to-one audio calls, and screen sharing, with desktop clients for Windows, macOS, and Linux plus iOS and Android apps. Messages support full Markdown, which suits engineering conversations with code blocks and logs. Playbooks turn repeatable processes such as incident response and release management into checklist-driven workflows with automated triggers and retrospectives. Integration is a core strength: prebuilt connectors for GitHub, GitLab, Jira, ServiceNow, and PagerDuty, plus webhooks, slash commands, bots, a REST API, and a plugin marketplace with 700+ entries - together making it a working surface for ChatOps rather than just a chat room. Playbooks add keyword and event triggers, task assignment, status broadcasting, and post-incident retrospectives, so operational knowledge is not trapped in individuals' heads. The server is a single Go binary backed by PostgreSQL, with React clients, released monthly under MIT license and deployable fully air-gapped - which is why governments and defense organizations run it inside closed networks, and why the same control applies to any team with confidentiality requirements. The compiled Team Edition is free for unlimited users with no message history cutoff, so costs stay flat as the team grows.

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.

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.

Character-based chat and storywriting with large language models: TavernAI is the open-source frontend that leaves model choice to you. It generates no text itself; it connects to the backend of your choice - OpenAI (including GPT-4), Anthropic Claude, KoboldAI and KoboldCpp, Oobabooga's Text Generation Web UI, NovelAI, Ollama, and the crowdsourced Horde - so cost, model quality, and content policy are decided by your backend, not the interface. Characters are defined by portable card files in PNG or JSON format with personality, scenario, and example dialogue, and tens of thousands of community-made cards from sites like Chub.ai import directly. Conversations support group chats with multiple characters, a story mode for long-form writing, message swiping to branch between alternative responses, and full editing of any message. World Info injects lore into context when keywords trigger, keeping long roleplays consistent. Themes, custom backgrounds, and configurable generation settings round out the interface. It runs on Node.js, and the SillyTavern project began as a fork of it.

"Forget about bouncers" became a real sentence because of The Lounge: a Node.js web IRC client that holds persistent connections to your networks 24/7, logging everything while you sleep, so closing the browser tab never means missing a message or losing your place in a channel. Open it again from any device - desktop, phone, tablet - and you resume exactly where you left off, with full history synchronized. Because it combines bouncer and client in one process, the experience feels like a modern chat app rather than 1990s infrastructure: push notifications for highlights and private messages (with self-generated VAPID keys, so even Web Push needs no third-party service), automatic link previews, inline file and image uploads, and full IRCv3 protocol support. It installs as a progressive web app from any modern browser, so phones get a native-feel client without an app store. Multi-user support means one instance serves your whole team or community, each user with their own networks and history, and LDAP integration ties into existing authentication. A public mode alternatively serves as an open, registration-free web chat for events or support channels. MIT-licensed, born as a fork of Shout, and a fixture of self-hosting stacks since.

A fair-source chatbot and conversational-form builder: Typebot assembles conversations in a visual graph editor. In a visual graph editor you chain blocks from four categories: bubbles display text, images, video, audio, and embeds; inputs collect data through text fields, email, phone, buttons, picture choices, date pickers, file uploads, and Stripe payments; logic blocks handle conditional branching, variables, URL redirects, A/B testing, and custom JavaScript; integration blocks call webhooks, OpenAI, Google Sheets, Google Analytics, Meta Pixel, Zapier, Make, and Chatwoot. Build once, deploy anywhere: custom domains, WhatsApp, or embedded in any site as a container, popup, or chat bubble through a fast native JS library with no iframe and no external dependencies - plus an HTTP API for executing bots programmatically from any language. Theming covers fonts, colors, roundness, and shadows with custom CSS and reusable templates, and results arrive in real time with drop-off and completion analytics plus CSV export. Two Next.js apps (builder and viewer) self-host via Docker under the Functional Source License, which converts to Apache 2.0 after two years.