Capture screenshots, screen recordings, audio, video, and GIFs in one cross-platform desktop app.
Project overview
pear-rec is a cross-platform desktop tool for taking screenshots and recording the screen, audio, video, or animated GIFs. Its screenshot workflow includes cropping, drawing, shapes, color tools, filters, QR recognition, clipboard export, and history, while recordings are handled through WebRTC and WebCodecs-based components. The feature checklist may include work completed in development but not yet shipped in the latest release, so release notes should be checked before relying on a specific function.
Create and run interactive live wallpapers across Windows multi-monitor setups.
Project overview
Sucrose turns GIFs, videos, websites, YouTube content, and applications into interactive Windows wallpapers across multiple displays and resolutions. Users can build their own wallpapers, add audio-responsive behavior or system-status elements through its APIs, and rotate backgrounds on a schedule or randomly. The app includes resource controls for everyday desktop use: it can pause animated wallpapers when a full-screen application or game is active and stop them while a laptop is running on battery power.
Dictate context-aware text into any app using local speech recognition and models.
Project overview
Amical is a local-first dictation application that turns speech into text through a global shortcut and floating control. It detects the active application and can format output differently for an email, chat, coding prompt, or other writing context, while current releases also support hotkeys, voice macros, and custom workflows. Whisper and open-source models can run on the user's machine for offline processing. Smart note generation is still in progress, while MCP app control and meeting transcription are listed as planned rather than finished features.
Trace, evaluate, simulate, and improve LLM and agent applications.
Project overview
Future AGI is a self-hostable open-source platform for observing and improving LLM or agent applications. It combines tracing, evaluations, simulations, datasets, guardrails, an AI gateway, and prompt optimization in one feedback loop. Traces use OpenTelemetry, while the gateway exposes OpenAI-compatible HTTP and integrates with many providers and frameworks. A full deployment includes PostgreSQL, ClickHouse, Redis, RabbitMQ, and Temporal, so it best fits teams that need unified quality and observability infrastructure.
Install, switch, and pin Node.js versions through a GUI or CLI.
Project overview
nvm-desktop manages multiple Node.js runtimes on macOS, Windows, and Linux through both a visual desktop app and the nvmd command-line tool. Users can browse available releases, install or remove versions, change the global default, and bind a specific Node.js version to each project so environments remain isolated. Common operations are available by clicking or from terminal workflows. The application keeps installed runtimes, command shims, project bindings, and settings together in a dedicated directory under the user’s home folder.
Complete desktop tasks with local models, memory, tools, and agent workflows.
Project overview
Row-Bot is a local-first desktop AI assistant for working across files, repositories, workflows, and messaging channels. It combines chat, durable memory, configurable tools, agent profiles, visible goals, and scoped child-agent delegation for longer tasks. Users can run models through Ollama or self-hosted endpoints, or opt into cloud and subscription providers. App data stays on the device by default, while content is sent externally only when a selected provider or integration requires it.
Watch supported video and live-stream danmaku through IINA on macOS.
Project overview
IINA+ is a macOS companion application that opens content from several video and live-streaming services in IINA and displays danmaku where supported. The compatibility table includes services such as Bilibili, Douyu, Huya, Douyin, and NetEase CC, but live status, video decoding, and danmaku availability differ by site. Users can install a release build, while source builds require the latest Xcode and the project's dependency setup script.
Launch Epic and compatible Windows games from one open-source macOS library.
Project overview
Mythic is an open-source macOS game launcher that can run 64-bit DirectX 9–12 Windows games through its custom Apple Game Porting Toolkit implementation. It integrates Epic Games, supports manual imports, and provides game management from one library. Built-in Steam support is not yet available, although Windows Steam can be installed manually, and the launcher requires macOS 14 Sonoma or later.
Record and search private conversation memory locally across desktop, CLI, and MCP workflows.
Project overview
Minutes turns meetings, voice memos, and dictated thoughts into locally stored Markdown that AI tools can search directly. Record through the desktop app, import and query through the CLI, or expose meeting memory to Claude, Codex, Gemini CLI, and other clients through MCP. Live transcripts can also support assistance during a meeting. Because transcription and storage stay on the user's machine, the project suits people who want searchable conversation history without giving up ownership of recordings and notes.
Continue and control local AI coding sessions from other devices.
Project overview
Happier keeps Claude Code, Codex, OpenCode, and other coding-agent sessions running on a computer while making them accessible from a phone, browser, or desktop client. Users can follow, take over, fork, replay, or hand off live sessions without discarding context. Communication is end-to-end encrypted, and the relay can use the hosted service or a self-managed deployment. Remote access requires the target machine and its daemon to remain online; it complements existing agent CLIs rather than replacing their model services.
Web appProductivity and officeModel Context Protocol
langchain4j-aideepin↗
@moyangzhan·Java
Build business AI assistants with chat, RAG, workflows, tools, voice, and memory.
Project overview
LangChain4j-AIDeepin is a self-hostable web platform for teams building intelligent business assistants. It combines multi-character chat, image generation, RAG knowledge bases, visual workflows, MCP tools, speech input and output, and conversation memory, with separate admin and user interfaces plus REST APIs. Docker deployment is documented, while supported capabilities vary across model providers.
Organize large offline photo libraries with private, on-device AI search.
Project overview
Lap manages photos and videos directly in existing local folders without requiring a cloud account or upload. It offers timeline and metadata browsing, on-device text and similarity search, smart tags, face clustering, duplicate cleanup, and basic editing for large personal libraries. Builds are available for macOS, Windows, and Linux. Because the application keeps its own database and cache separate from source folders, uninstalling it or deleting those support files does not remove the original media.
Browse, search, and organize images and videos produced by AI generation tools.
Project overview
Infinite Image Browsing helps people manage large folders of AI-generated images and videos from tools such as Stable Diffusion WebUI, Fooocus, NovelAI, and StableSwarmUI. It indexes generation metadata for tag, filename, and advanced search, while also providing previews, file operations, comparisons, statistics, and bulk downloads. It can run as a desktop app, a standalone Python service, or a WebUI extension. Semantic clustering and natural-language search require an OpenAI-compatible embedding and chat provider plus additional Python dependencies.
Scan disk images or raw devices and recover lost or deleted files.
Project overview
Digler analyzes disk images and physical devices through either a command-line interface or desktop application. Its scan-first workflow creates a DFXML report, which can then guide selective file recovery; on Linux, results can also be mounted as a browsable FUSE filesystem. File carving is designed to work independently of the original filesystem, and plugins can add scanners for new formats. Prebuilt binaries cover macOS, Windows, and Linux, but the project remains at an early v0.1.0 stage.
Run Artisan commands, use Tinker, and serve Laravel projects from a desktop interface.
Project overview
Laravel Kit gives Laravel developers a desktop interface for common project operations on Windows, macOS, and Linux. It reads Artisan commands from the selected application, lets users execute them through a graphical view, provides a Tinker code editor, and can start the Laravel app locally with a button. Per-project setup is not required, but PHP must already be installed on the system, and the downloadable macOS DMG is not code-signed.
Generate art, hold voice conversations, and expose local AI inference through an offline app.
Project overview
AI Runner combines an offline conversational companion with configurable personality, voice, and memory, plus a layered canvas for generating and editing images. It can also run headlessly and expose local LLM, image, speech-to-text, and text-to-speech functions over HTTP. Docker is the recommended setup, while manual installation requires Python 3.13 and a substantial set of system dependencies.
Run Alpaca and LLaMA-based chats locally on Windows without using a command line.
Project overview
Alpaca Electron gives Windows users a graphical way to chat with Alpaca and other llama.cpp-based local models without compiling software or using a command line. After installing the app, you point it at a supported 4-bit .bin model and it runs inference on the CPU; internet access is only needed to obtain models. The repository mentions experimental builds for other systems, but its current notice says only Windows is supported.
Write offline Markdown notes and choose where they are stored and synced.
Project overview
Beaver Notes is a local-first, Markdown-native notes app for macOS, Windows, Linux, Android, and iOS. It works offline without requiring an account and includes folders, tags, note links, locked notes, and flexible synchronization, allowing notes to stay on a device, a user-controlled server, or the project’s service. The repository currently presents the in-progress version 5 rewrite, which is expected to have rough edges. Users who need a stable build should use the installers provided on the project’s downloads page.