A self-hosted AI workspace that bolts chat, agents, email triage, calendars, and deep research onto your own hardware.
Chat Assistants
heavyweights · velocity + momentumA locally-runnable voice-interactive AI VTuber that can see your screen, interrupt you mid-sentence, and sulk in desktop pet mode.
Electron GUI for Hermes Agent, an AI assistant that can message you on 16 platforms and won't stop learning.
OpenClaw is a self-hosted AI assistant that plugs into the messaging apps you already use, so you don't need another dashboard.
Hermes WebUI gives a browser and phone interface to the Hermes agent without frameworks, bundlers, or extra config.
A single web UI that swallows Ollama, OpenAI APIs, RAG, image generation, and enterprise auth into one Docker container.
Self-hosted chat UI that unifies OpenAI, Anthropic, Google, AWS, and two dozen other providers under one roof.
AstrBot is a Python framework for wiring LLMs into QQ, WeChat, Telegram, Slack, and a dozen other chat platforms without writing platform glue.
Hermes Web UI wraps a multi-platform agent runtime in a Vue3 dashboard so you can chat, schedule, and bill from one place instead of eight browser tabs.
A Saturday hack that turns model comparison into a structured debate with anonymous peer review and a chairman.
Self-hostable AI workspace with RAG, agents, and multi-user support—no cloud required.
A locally-run frontend that wrangles dozens of LLM APIs, image generators, and TTS into one obsessively customizable interface.
Cherry Studio talks to OpenAI, Anthropic, Google, local Ollama models, and 300+ pre-built assistants without making you choose just one.
A single-file chat UI that races jailbreak prompts against multiple LLMs and scores which one "wins."
Khoj wires any LLM into your notes, files, and messaging apps so you can query your own data instead of begging ChatGPT to remember context.
Onyx wraps chat, RAG, agents, and enterprise governance into one deployable stack with a one-line installer.
XiaoZhi crams a voice-activated LLM chatbot onto ESP32 hardware, using the MCP protocol to bridge AI models with physical devices.
An open-source AI companion that plays Minecraft, chats in real-time, and streams itself while you code.
RikkaHub is a native Android client that lets you switch between OpenAI, Google, Anthropic, DeepSeek, and dozens of other LLM providers without juggling separate apps.
OpenLess turns rambling speech into polished, structured text — or full AI prompts — inserted live at your cursor across macOS and Windows.



