Discover the Best AI Tools

Lets AI clients control supported OBSBOT Tiny 2 and Tail 2 cameras, including gimbal settings, tracking and capture. Requires compatible hardware; Linux has gimbal feedback restrictions and simultaneous physical multi-camera use is not fully hardware-verified.

An Obsidian plugin for model chat, note workflows and retrieval using local vector search across several model backends. Model access must be configured, vault tools vary by backend, and local indexing does not prevent cloud models from receiving selected note content.

Lets AI clients search Yandex Lavka products, manage a cart and submit confirmed grocery orders. Uses unofficial private APIs and session cookies, so compatibility may break; real purchases require price confirmation and may need browser payment verification.

Helps Claude search DoorDash menus, compare totals and prepare food orders through chat, a local web interface or MCP. Requires a DoorDash session and compatible runtime; each real order requires user approval.

Anna is an experimental desktop assistant combining personal tasks, connected business systems and team workspaces with reviewable artifacts. The source preview targets macOS arm64; Jev assignee suggestions require explicit acceptance and do not themselves run the task.

TypeSafe Conversation is an unofficial Home Assistant integration that maps Assist commands to built-in device intents using Jev. It sends commands and exposed entities to TypeSafe with your API key; uncertain, conversational or free-text requests can use a configured fallback. It requires Home Assistant 2025.6 or later and currently uses English confirmation templates.

OllamaHandoff delegates supplied text to local Ollama models for chat, summaries, code reviews, extraction and commit-message drafts through MCP. It accepts text rather than file paths and requires a running Ollama instance with models installed. Local inference avoids a cloud-model API call, but the calling agent may still incur charges.

HA-Jev is a Home Assistant integration exposing typed Jev questions through sensors, actions and conversation features, with configurable home checks. It requires Home Assistant 2026.9+ and a TypeSafe API key; relevant home context is sent to the cloud service.

LingShu is an alpha-stage desktop agent for code and office documents, with worker sessions, artifact tracking and configurable model providers. It offers macOS and Windows previews; direct computer control is macOS-only and requires authorization. Output quality depends on the model and local toolchain.

Desktop assistant combining chat, voice, browser and computer tools, MCP connections and background agents. Supports Windows, macOS and Linux. Requires a configured local or hosted model; desktop control depends on OS permissions, and connected cloud services receive the content needed for requests.

Android assistant that reads visible conversations and offers replies to copy or fill, leaving sending to the user. Requires Android 11+, accessibility/overlay permissions and model credentials; conversation data goes to configured APIs.

A compact Spotify MCP client combining search and playback intents, queue control, playlists and library actions. Uses the user’s own developer app with PKCE and local token storage; playback requires Premium and an active device. Playlist visibility is limited by Spotify API permissions, and actions can modify the account.

A read-only MCP service for regional cinema schedules, with venue sources and freshness indicators. Requires no API key. Coverage is regional rather than global; omitted regions default to San Francisco, times use each cinema’s local timezone, and freshness does not guarantee schedule accuracy.

An MCP interface for Spotify playback, search, playlists and library indexing using PKCE OAuth. Some playback controls require Premium. Destructive tools are opt-in, but other tools can still create playlists; mood and energy labels use genre heuristics rather than direct audio analysis.

Chrome side-panel AI assistant for working with pages and logged-in sources, producing reports or drafts and saving repeatable workflows as Recipes.

Self-hosted Spring Boot agent platform with pluggable runtimes, knowledge and memory, approval workflows and shared access through web, desktop and messaging channels.

Off Grid AI is an on-device AI application for phones and Mac that supports chat, vision, speech-to-text, image generation, and tool calling.

OpenAgent is a personal AI assistant that uses large language models (LLMs), retrieval-augmented generation (RAG), and agent loops, with support for computers, browsers, and coding.

FutureOS is an AI agent accessible from terminal, desktop, mobile, and chat apps, with a Rust core.