Every major model provider behind one ChatGPT-style interface: LibreChat spans OpenAI, Anthropic, Google, Azure, AWS Bedrock, Vertex AI, Groq, Mistral, OpenRouter, DeepSeek, and any OpenAI-compatible endpoint including local Ollama. You can switch models mid-conversation and compare providers without changing tools. Its Agents framework builds no-code custom assistants with tool access via Model Context Protocol servers, file search over uploaded documents through an optional pgvector-backed RAG service, and a sandboxed Code Interpreter that executes Python, JavaScript, Go, C++, Java, PHP, and Rust. Artifacts render React components, HTML, and Mermaid diagrams directly in chat, and image generation works through DALL-E and other configured providers. Multi-user support is enterprise-grade, with OAuth, SAML, LDAP, and two-factor authentication, per-user conversation history in MongoDB, and Meilisearch-powered search across all messages and files, plus reusable presets, forkable threads, and persistent memory across conversations. The economics favor teams: instead of a ChatGPT Plus seat per person, everyone shares one instance billed per API token, with access to every provider rather than one - and providers see individual API calls, not your accumulated organizational knowledge. Deployment is Docker Compose; API keys and endpoints are configured through .env and librechat.yaml.

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.

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.

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.

Whirl puts every top AI model in a single conversation and remembers what you were working on last week, so you can switch models mid-thought without losing the thread. Ask for a report, a chart, or a small interactive page and it appears as a living artifact in a side panel, still editable while you keep chatting, and shareable by link when it is ready to leave the conversation. Connect your own tools over MCP, with OAuth sign-in handled for you, or install skills that teach the app new tricks your team relies on. Long-term memory carries your preferences and project context from chat to chat, and live web search with page reading grounds answers in today's pages instead of the model's training data. Sensitive threads can be locked with a password that encrypts them on your device, where the server never sees the key and only zero-retention models may answer. Around those headline pieces sits the everyday kit: incognito mode, a message queue for when you think faster than the model replies, voice input, image generation, file attachments, folders, and sharing controls. An admin console manages the model catalog, integrations, and skills, and the interface itself switches between light and dark with your choice of accent color, installable as a mobile web app. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Your team's group chat could have a colleague who has read every email, ticket, and document, remembers all of it, and answers in seconds; MindRoom puts AI agents like that into your chat rooms as full participants. Each agent is a real user on the open Matrix protocol, so you talk to it in MindRoom Chat on web or mobile, in any other Matrix client, or through bridges in Slack, Telegram, WhatsApp, and Discord. Give every agent its own model: a local model for private rooms, a frontier model for hard coding problems, and switch per room or thread whenever the work changes. Agents connect to more than 100 tools, including Gmail, calendars, GitHub, Google Drive, Home Assistant, and any MCP server, and they search your own documents and knowledge bases for answers with sources. Memory persists across conversations and platforms, so an agent remembers people, preferences, and project context months later and can turn repeated work into reusable skills. Before an agent sends an email or runs a command, an approval card shows exactly what will happen; you tap once to allow it, and sandboxed workers keep executed code away from your credentials. Schedule morning briefings, silent inbox checks, and recurring digests in plain language, or wake an agent from any other system with a single HTTP request. 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.

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.

Dify turns the notoriously complex process of building production-grade AI applications into a visual drag-and-drop experience that teams can actually ship and maintain. With over 87,000 GitHub stars and backing from prominent investors, the platform has become the go-to open-source LLMOps solution for organizations that refuse to be locked into proprietary AI stacks. The visual workflow canvas lets developers wire together LLM calls, conditional logic, iteration loops, tool invocations, and human-in-the-loop checkpoints without writing boilerplate integration code. Its RAG pipeline engine handles the full document lifecycle from ingestion of PDFs, Word documents, and HTML through configurable chunking strategies, embedding with models from OpenAI or open-source alternatives, vector storage in Weaviate, Qdrant, Pinecone, or pgvector, and hybrid semantic-plus-keyword retrieval with citation tracking. Dify integrates with hundreds of model providers including OpenAI GPT-4o, Anthropic Claude, Google Gemini, Mistral, Llama, and any OpenAI-compatible endpoint like Ollama for fully local inference. The agent framework supports both ReAct and function-calling strategies with 50-plus built-in tools spanning Google Search, DALL-E, Stable Diffusion, WolframAlpha, and custom API definitions. Published apps can be deployed as hosted web interfaces, embedded chat widgets, REST API endpoints, or MCP-compatible tools. Enterprise features include role-based access control, SSO integration, and audit logging. A built-in marketplace enables teams to share and reuse model providers, tools, and workflow templates across projects. 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 an open-source community edition.

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.

Langflow turns LLM application development into a visual canvas where every node maps to a real LangChain primitive (chains, agents, retrievers, memory, vector stores, and tools) that teams wire together without writing integration boilerplate. The platform supports 15+ LLM provider components including OpenAI, Anthropic, Google Gemini, Mistral, Groq, Cohere, Azure OpenAI, HuggingFace, and Ollama for fully local inference, with LiteLLM proxying to over 100 additional providers through a single OpenAI-compatible endpoint. Vector database integrations cover Pinecone, Weaviate, Chroma, Qdrant, Astra DB, OpenSearch, FAISS, and Milvus, while built-in Knowledge Bases introduced in version 1.8 allow RAG pipelines without any external vector service. Multi-agent orchestration enables agent-to-agent communication with conversation management, persistent Memory Bases for cross-session context retrieval, and step-by-step reasoning visibility in the interactive Playground. Every flow automatically becomes a callable REST API endpoint via the /run route and an MCP server exposable to Claude Desktop, Cursor, or any MCP-compatible client. Every component is a real Python class that developers can customize, extend, or replace, while Extension Bundles package third-party integrations as independent pip packages for modular installation. Tool integrations include web search, Slack, Gmail, Google Drive, GitHub, and custom REST API calls. Docker deployment with PostgreSQL persistence runs on port 7860. Backed by 153,000+ stars and DataStax. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Agent Zero equips large language models with a persistent virtual Linux desktop, letting autonomous AI agents write code, research the web, and execute multistep tasks without supervision. Operating within an isolated container, the system opens an interactive XFCE graphical desktop in your browser canvas where the agent interacts with GUI applications like Blender and terminal sessions directly. Its embedded browser features interactive annotation tools, letting you click web elements to inspect stylesheet hierarchies, extract component markup, or submit automated testing instructions. You can cowork on spreadsheets, presentations, and Markdown specifications in real time alongside the agent, preserving document revisions through snapshot time travel. A multi-tier memory architecture backed by FAISS vector indexing and SearXNG web discovery retains problem-solving context across projects, while hierarchical delegation spins up specialized subordinate agents to parallelize complex engineering audits. The platform connects seamlessly to commercial LLMs via OpenAI, Anthropic, or OpenRouter, runs private local models through Ollama, and integrates custom toolkits via the Model Context Protocol and community Plugin Hub. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

LocalAGI builds AI agents that never leave your hardware: a self-hosted platform for creating assistants, chat bots, and automations from a browser, with no cloud keys and no code required. Agents are configured in the Web UI with their own models, behaviors, and tools, and cooperative teams of agents can be generated from a single prompt. Each agent exposes a drop-in replacement for the OpenAI Responses API, and the platform also serves an MCP endpoint, connects to external MCP servers, and manages reusable Skills that can be created, imported, or synced from git. A built-in knowledge base gives agents short and long-term memory with file uploads and semantic search over collections. Planning, reasoning, and multimodal inputs let agents handle text, vision, and more, and custom actions can be scripted in Go without compiling. Connectors put agents on Discord, Slack, Telegram, GitHub Issues, and IRC, cron-style periodic tasks keep them working on schedule, and real-time observability shows what every agent is doing. It runs on consumer CPU or GPU hardware through Docker Compose, serving the interface on port 8080, pairing with LocalAI or your own models. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Nakama gives your whole team a shared home for AI agents, where each agent has its own identity, memory, tools, and permissions and meets people where they already talk. The dashboard feels like a familiar chat app: pick an agent from the rail, start a conversation, and watch it use tools, recall memory, and reply inside Telegram, WhatsApp, Discord, or Slack when the work lives there. Every agent is configured as a small personality you can read and edit, with prompt files for its soul, style, instructions, and memory, plus tabs for its channels, tools, MCP servers, and skills. One server hosts many organizations with invites and roles, and agents stay isolated from each other so the support agent never wanders into the finance agent's toolbox. The control center manages workspace settings, model providers, plugins, and integrations, and a connector layer opens the door to more than a thousand external apps. Daily encrypted backups and an in-app update button keep operations boring, and the entire platform idles in about two hundred megabytes inside a single container. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Open Agent Builder delivers a visual canvas for orchestrating AI agent workflows without writing Python scripts or managing complex codebases. The React Flow-powered drag-and-drop interface supports seven node types — Agent, Scraper, Transform, If/Else, Loop, User Approval, and MCP Tool — each configurable with provider-specific settings for Anthropic Claude (Haiku 4.5 and Sonnet 4.5), OpenAI GPT-5, Groq, or any OpenAI-compatible endpoint. The LangGraph orchestration engine handles state management, conditional routing, and human-in-the-loop approval gates while Firecrawl integration converts any website into structured, LLM-ready data through scrape, crawl, and map operations. E2B sandboxed code execution powers Transform nodes for secure data manipulation without risking host system integrity. Real-time streaming updates show execution progress node-by-node as workflows run, with Convex providing reactive database synchronization for workflow state and execution history. The TypeScript-first architecture (96.8% TypeScript) built on Next.js 16 App Router with Tailwind CSS delivers a responsive interface across devices. Clerk handles multi-user authentication with JWT integration for secure workspace isolation. Deploy via npm install and environment configuration with Firecrawl, Convex, and Clerk API keys. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Drag an AI agent onto a canvas beside a Gmail trigger, a condition, and a Google Sheets step, and ByteChef runs the whole thing as one durable workflow that resumes where it stopped. Runs that fail or wait for a human pick up from the step they reached. The visual editor maps values between steps with data pills, and its 250+ connectors double as agent tools and MCP tools. An agent combines a model from twelve LLM providers, including OpenAI, Anthropic, Mistral, and Ollama, with chat memory, knowledge-base retrieval, and tools. It streams structured answers. Flow controls cover conditions, branches, loops, parallel and fork-join paths, subflows, error handling, and approval steps that pause for a person. Workflows start from webhooks, polling, schedules, forms, or app events, and code steps run JavaScript, Python, or Ruby. Workflows can be exposed through an MCP server for Claude Desktop, Cursor, or Windsurf, and ByteChef consumes external MCP servers too. Data Tables add typed relational tables with a spreadsheet-like grid and CSV import and export. The Agent Playbook opens a chat with the agent as you build it. Every run is listed with per-step input, output, and errors. 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 + EE 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.

One endpoint for every MCP server you run: MCPHub gathers local and remote Model Context Protocol servers behind stable URLs, so AI clients connect once and see what you allow. Claude Code, Cursor, and Cherry Studio can use four routes: everything at /mcp, a named group at /mcp/{group}, one server at /mcp/{server}, or semantic tool search at /mcp/$smart. Smart routing runs vector search on PostgreSQL with pgvector and an OpenAI-compatible key, so the model gets a shorter tool list. Servers attach over stdio, SSE, or streamable HTTP, OpenAPI services can be wrapped as MCP tools, and changes apply without downtime. In the other direction, MCP tools can be exported as an OpenAPI 3.0.3 spec for OpenWebUI and other OpenAPI clients. Bearer keys, OAuth 2.0 (client and server modes), and GitHub or Google sign-in in database mode control access, with per-user visibility for servers and groups. Encrypted per-user credentials let one shared server use each person's own key. Logs show tool-call activity, request status, and latency, health checks track each connection, and the dashboard controls which tools, prompts, and resources each server exposes. Large text tool results can be compressed, interactive MCP Apps are proxied through MCPHub routes, and a built-in market lets you browse a server catalog. Typical uses include a team-wide gateway, per-project groups, and direct single-server routes for debugging. 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.

OpenVoiceUI is the voice-first front end for a self-hosted AI agent that lives entirely on your own hardware; you talk, it answers out loud, and it builds live pages on screen while the conversation runs. Hold a hands-free conversation with wake word, push-to-talk, and the ability to interrupt, or switch to text when the room is quiet. Speech recognition runs in the browser for free or through Deepgram, Groq Whisper, or your own Whisper server, while nine speech providers from local Supertonic to ElevenLabs give the agent its voice, cloned voices included. As it talks, the agent opens live canvas pages, dashboards, galleries, reports, and tools, and files them on an OS-style desktop you can reopen from the start menu. Ask for music and it generates songs with a built-in player and playlists; ask for images and it creates those too, alongside an audio clip maker and a soundboard. Profiles swap the agent's persona, voice, and model provider, animated faces react while it speaks, and sub-agents and workspace files stay visible in the admin dashboard. The agent itself runs in the OpenClaw gateway with your choice of model provider, so your keys, conversations, and files never leave your server. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.