OpenHuman

Open WebUI is a self-hosted, extensible AI platform developed as an interface for local Ollama models and OpenAI-compatible APIs. It provides a provider-agnostic chat interface with custom models and agents, tools and plugins, MCP, MCPO and OpenAPI tool-server connections, persistent memory, web browsing, voice and video calls, image generation, multi-model conversations, and workflow automation. Its local retrieval-augmented generation system connects document extraction engines and vector databases, supports hybrid BM25 and vector search with reranking, and can import documents into chats or knowledge libraries. Agents can use an Open Terminal to run scripts, access files, analyze data, and produce files; the platform also includes role-based access control, user groups, calendars, channels, analytics, observability, enterprise authentication, and horizontally scalable deployments. Open WebUI can be installed with pip, Docker, Kubernetes, Docker Compose, Kustomize, or Helm, and can run entirely offline. It supports SQLite or PostgreSQL and local or cloud object storage. The repository states that the codebase uses multiple licenses, including the Open WebUI License with an additional requirement to preserve the Open WebUI branding.

OpenDots is an open-source, self-hostable template for building persistent AI coworkers, called Dots, each with its own role, instructions, permitted tools, browser profile, files, and workspace. It provides a web and mobile workspace with Spaces, searchable pages, visual editing, page-specific conversations, and specialist Dots. Its workflow connects agents to interfaces through AG-UI and uses CopilotKit components, TanStack AI for model streaming and server-side tool execution, Intelligence for durable conversation Threads, and Channels SDK for Slack. Dots can perform browser and workspace actions through OpenBot computers, with permissions, activity records, human takeover, and persistent browser profiles and files. Drafts can be paused for human approval before being saved as pages; the template also includes text conversations, configurable voice calls, background work, research, memory, and automatic-learning flows. OpenDots is a starting point rather than a hosted product: operators clone and run the application, configure its model, conversation, channel, speech, browser, and computer services, and customize the workflows. The repository describes the project as early-stage, with some connected-service behavior still requiring verification. It is distributed under the MIT license.

OpenHands is an open-source, self-hosted developer control center for running autonomous coding agents and automations, including agents that work on GitHub issues. Its Agent Canvas starts conversations and connects to local, remote, or cloud agent backends, including Docker containers, virtual machines, OpenHands Cloud or Enterprise infrastructure, and ACP-compatible agents such as Claude Code, Codex, Gemini CLI, Pi, and OpenCode. Automations can run on schedules or webhook events and integrate with services including Slack, GitHub, Linear, Notion, and Datadog. The repository includes the Agent Canvas frontend, backend selection, and local-stack orchestration; the Agent Server provides the REST API for running multiple agents on a host, while related repositories provide the SDK, TypeScript client, and automation services. It can use remote model providers or language models installed locally.

OpenBot is an open-source AI agent platform from CopilotKit that gives each agent its own computer with a browser, logins, files, tools, and a dedicated interaction channel. It runs in the user's infrastructure and accepts agents that speak the AG-UI protocol, including agents built with LangGraph, Mastra, CrewAI, Pydantic AI, Google ADK, or custom code. A single gateway mediates actions involving the computer, files, MCP servers, and UI components: it decides whether an action is permitted before execution and records it afterward. Agents can operate their own browser screen, hand control to a human for restricted actions, and return component-based responses. Docker Compose runs the application components and PostgreSQL, while the administrator supplies the model credentials; the repository describes the project as alpha software under active development.