Chat Assistants

Open-source client code for hardware makers who want real-time voice AI without building the backend themselves.

Hexabot v3 is a TypeScript runtime that keeps agentic workflows on rails by binding them to YAML definitions, Zod schemas, and explicit memory across chat channels.

An open-source AI assistant built in Kotlin that remembers context across chats, draws interactive screens, and runs a sandboxed Linux distro on your phone.

Rocketnotes pairs a hierarchical note editor with an AI agent that reads your scattered snippets and archives them where they belong.

It exists to hide a real-time Gemini copilot from Zoom, Meet, and OBS while you work through technical interviews.

OpenMinis exists to turn your smartphone into a private AI workstation with a real Linux shell, system integrations, and your own API keys.

RAG Web UI bundles document ingestion, vector search, and multi-provider LLM dialogue into a single dockerized stack so you don't have to wire FastAPI and LangChain together for the hundredth time.

A mobile-native AI chat client that refuses to settle for a wrapped web view.

Hope Agent wants to be the desktop AI that actually remembers what you were doing when you switch from Mac to phone to browser.

Kelivo unifies access to major LLM providers in a single Flutter app that runs on six platforms, including HarmonyOS.

Conduit wraps Open WebUI in a polished Flutter app so you can actually use your private LLM from a phone without wrestling mobile browsers.

TauriTavern ports the SillyTavern LLM frontend into a native Tauri v2 desktop app, swapping browser HTTP calls for Rust-backed commands while keeping the upstream UI intact.

A self-hosted Vue3 dashboard that consolidates multi-platform chat, cron jobs, usage analytics, and remote file management for the Hermes AI agent.

Jarvis treats conversation as context, not a series of disconnected commands.

Hermex is a free, native SwiftUI client that turns your iPhone into a control panel for a self-hosted Hermes agent, keeping the compute on your hardware and the controls in your pocket.

A production-grade Next.js template that wires together the AI SDK, multi-model routing, auth, and persistence so you don't have to.

ChatLab turns exported chat dumps from WhatsApp, WeChat, Discord and others into a private, queryable database you can interrogate with SQL and AI agents on your own machine.

assistant-ui exists to stop React developers from reimplementing streaming chat, tool rendering, and keyboard shortcuts every time they adopt a new LLM backend.

It gives iOS and Android users a way to download and chat with small language models without sending a single prompt to the cloud.

A privacy-first plugin that turns your markdown vault into a locally controllable second brain with chat, search, and autonomous agents.