Recently updated open-source projects
Projects with recent public repository activity, ordered by factual GitHub update time.
- Projects
- 4,306
- Authors
- 3,645
- GitHub Stars
- 13,022,829
4306 projects · page 13 of 240
Open Soul-of-WaifuDesktop appPersonal and daily lifeWindows
Soul-of-Waifu↗
@jofizcd·Python
Run a voiced AI roleplay companion with animated avatars and local models on Windows.
Project overviewSoul of Waifu is a Windows desktop roleplay and AI companion app with Live2D or VRM avatars, voice conversations, emotional reactions, long-term story memory, and a transparent desktop companion mode. It can search and download GGUF models inside the app and run them locally through llama.cpp, while cloud providers remain optional. Windows 10 or 11 and at least 8 GB of RAM are required, with a capable GPU recommended for local generation.
- Stars
- ★ 790
- Forks
- ⑂ 46
- License
- GPL-3.0
Open Auto-Empirical-Research-SkillsCollection or directoryResearch and knowledge
Auto-Empirical-Research-Skills↗
@brycewang-stanford·Stata
Browse more than 23,000 agent skills for empirical social-science research.
Project overviewAuto-Empirical Research Skills curates more than 23,000 reusable skills across eight social-science disciplines, giving researchers and agents a large catalog of empirical methods and workflows. The repository also includes numeric benchmark tasks and behavioral evaluation scenarios intended to test reproducibility and methodological rigor.
- Stars
- ★ 2,846
- Forks
- ⑂ 385
- GitHub updated
- Jul 14, 2026
Open pydantic-ai-skillsLibrarySoftware development
pydantic-ai-skills↗
@DougTrajano·Python
Add progressively loaded Agent Skills to Pydantic AI applications.
Project overviewAttach skill directories to an agent and let it discover metadata first, then load full instructions, resources, or scripts only when needed. The package supports standard filesystem skills as well as skills created programmatically in Python, exposed through capability or toolset integrations. It also validates skill structure, accepts multiple source directories, and includes safeguards against path traversal.
- Stars
- ★ 341
- Forks
- ⑂ 27
- License
- MIT
Open GPT-Image2-SkillPrompt packImage generation and editingClaude Code
GPT-Image2-Skill↗
@wuyoscar·Python
Generate and edit GPT Image 2 visuals with curated prompts and a CLI.
Project overviewGPT-Image2-Skill combines a curated prompt gallery, an Agent Skill, and the `gpt-image` CLI for OpenAI image generation and editing. You can request gallery examples in natural language from Codex, Claude Code, OpenClaw, Hermes, and similar runtimes, or copy prompts into the command line and adapt them for posters, UI mockups, game interfaces, photography, maps, typography, or reference-image edits. The repository also explains prompt structure in English and Chinese. Scientific figures are framed as references or reproducible workflow targets, not unchecked final publication assets.
- Stars
- ★ 3,734
- Forks
- ⑂ 312
- License
- MIT
Open metacubexdWeb appData visualizationREST
metacubexd↗
@MetaCubeX·TypeScript
Monitor and manage Mihomo traffic, proxy groups, connections, and profiles.
Project overviewMetaCubeXD provides a visual control surface for Mihomo, with live traffic statistics, latency testing for proxy groups, connection management, searchable rules, and streaming logs. It can run as a browser panel connected to an existing remote kernel, a desktop app that supervises a bundled Mihomo, or an all-in-one server for a router, NAS, or VPS. Bundled modes also add profile editing, validation, and activation. Desktop TUN routing requires a privileged helper, and a server exposed beyond a trusted LAN needs separate network controls or an authenticated reverse proxy.
- Stars
- ★ 3,972
- Forks
- ⑂ 500
- License
- MIT
Open awesome-local-llmCollection or directorySoftware development
awesome-local-llm↗
@rafska
Find platforms, models, and tools for running LLMs locally.
Project overviewawesome-local-llm is a categorized directory for researching local and self-hosted language-model stacks. It groups inference platforms and engines, user interfaces, models, benchmarks, RAG projects, agent frameworks, MCP servers, safeguards, and other supporting tools so users can compare options before building a setup. The repository is a navigation resource rather than an application, and each entry links to an external project or reference.
- Stars
- ★ 2,395
- Forks
- ⑂ 287
- License
- MIT
Open ab-download-managerDesktop appProductivity and officeLinux
ab-download-manager↗
@amir1376·Kotlin
Speed up, queue, and schedule downloads across supported platforms.
Project overviewAB Download Manager organizes file transfers with download acceleration, queues, schedules, themes, and browser integration. It is useful for users who regularly manage batches of files or need downloads to run at specific times. Builds are listed for Android, Windows, Linux, and macOS through the project site, GitHub Releases, and platform package managers.
- Stars
- ★ 16,686
- Forks
- ⑂ 861
- License
- Apache-2.0
Open sunnify-spotify-downloaderDesktop appMedia, audio and videoLinux
sunnify-spotify-downloader↗
@sunnypatell·Python
Use Spotify links to find and save matched audio as tagged local files.
Project overviewPaste a Spotify playlist, album, or track link and Sunnify reads metadata from Spotify’s public pages, finds matching audio through yt-dlp, and transcodes it locally to MP3, M4A, FLAC, Opus, or WAV with titles, artists, albums, years, track numbers, and artwork embedded. Its graphical app runs on Windows, macOS, and Linux without a Spotify account or API key. The project is presented as an educational demonstration and should be used only for content the user owns or is allowed to download, for personal and non-commercial use.
- Stars
- ★ 275
- Forks
- ⑂ 27
- GitHub updated
- Jul 14, 2026
Open EdgeMarkDesktop appWriting and editingmacOS
EdgeMark↗
@Ender-Wang·Swift
Reveal and organize plain Markdown notes from the edge of your Mac screen.
Project overviewEdgeMark keeps a Markdown notes panel one gesture or global shortcut away from any macOS app. You can pin the panel while copying between windows, then organize plain `.md` files with folders, tags, search, previews, and batch actions without locking them into a proprietary database. The app requires macOS 15.7 or later.
- Stars
- ★ 181
- Forks
- ⑂ 13
- License
- GPL-3.0
Open cinnyWeb appCommunication and collaboration
cinny↗
@cinnyapp·TypeScript
Use Matrix messaging through a clean web client you can self-host.
Project overviewCinny is a web client for the Matrix communication network. Users can open the hosted application or self-host the static build on a web server, Docker container, or container registry image. Administrators can configure default homeservers and explore pages, and must set up routing so direct application URLs resolve correctly. This repository focuses on the browser application; downloadable native desktop builds are maintained in the separate cinny-desktop project.
- Stars
- ★ 3,784
- Forks
- ⑂ 552
- License
- AGPL-3.0
Open dbt-agent-skillsCollection or directoryData and analyticsClaude Code
dbt-agent-skills↗
@dbt-labs·Python
Guide agents through dbt modeling, testing, semantic layers, operations, and migrations.
Project overviewdbt Agent Skills lets compatible assistants automatically load guidance when a natural-language request matches a dbt workflow. The collection covers model development and tests, MetricFlow semantic layers, dbt Mesh governance, job troubleshooting, command usage, and MCP configuration, with separate skills for one-off migrations to Fusion or across data platforms. Most workflows assume dbt is installed and configured and that the user is working in a project containing `dbt_project.yml`.
- Stars
- ★ 627
- Forks
- ⑂ 53
- License
- Apache-2.0
Open AutoCLICLI appResearch and knowledgeLinux
AutoCLI↗
@nashsu·Rust
Fetch structured data from dozens of websites with one CLI command.
Project overviewAutoCLI gives scripts and AI agents a single command-line interface for retrieving information from dozens of websites, controlling supported desktop apps, and passing through local tools such as gh or kubectl. Public commands run directly, while authenticated sites reuse an existing Chrome session through the companion extension. Users can also define YAML adapters or generate and sync new adapters through AutoCLI.ai, and the core tool ships as a standalone binary.
- Stars
- ★ 2,875
- Forks
- ⑂ 269
- License
- Apache-2.0
Open CapDesktop appMedia, audio and videomacOS
Cap↗
@CapSoftware·TypeScript
Record, edit, and share screen recordings with optional self-hosting.
Project overviewCap helps teams create product demos, bug reports, tutorials, and asynchronous updates from screen, camera, and microphone recordings. Instant Mode uploads while recording and produces a link when recording stops, while Studio Mode records locally for editing and export. Content can remain local, use your own S3-compatible storage, or run through a fully self-hosted deployment.
- Stars
- ★ 20,144
- Forks
- ⑂ 1,691
- GitHub updated
- Jul 14, 2026
Open tonkatsu_boxDesktop appPersonal and daily lifeAndroid
tonkatsu_box↗
@hacan359·Dart
Organize games, films, shows, anime, books, and progress in one app.
Project overviewTonkatsu Box is a cross-platform personal collection manager for games, movies, television, anime, manga, visual novels, books, and comics. Users can search external catalogs, import existing libraries, track status and ratings, build visual boards or tier lists, and continue using the app offline after setup. Local-network device sync copies the entire database and replaces the receiving device instead of merging changes, while macOS and Linux support is currently described as experimental.
- Stars
- ★ 363
- Forks
- ⑂ 14
- License
- MIT
Open nyatermDesktop appDevOps and deploymentLinux
nyaterm↗
@nyakang·TypeScript
Manage remote terminals, file transfers, and related tools in one desktop workspace.
Project overviewNyaTerm is a cross-platform desktop client for people who move between servers, local shells, network devices, and remote files. It combines tabbed and split SSH, local terminal, Telnet, and serial sessions with an SFTP browser, transfer queue, tunnels, OTP, remote editing, diagnostics, and encrypted backup or sync. AI assistance can generate commands and inspect output within the active terminal context. The application organizes and connects to existing shells and endpoints; it is not a replacement shell of its own.
- Stars
- ★ 850
- Forks
- ⑂ 68
- License
- MIT
Open ruoyi-aiOrchestration frameworkAI and agent developmentModel Context Protocol
ruoyi-ai↗
@ageerle·Java
Build enterprise AI agents with visual workflows, RAG, and multiple models.
Project overviewRuoYi AI is a full-stack platform for enterprise agent applications. It connects multiple model providers, builds local RAG knowledge bases, and lets teams compose model calls, email, human review, and other steps in a visual workflow. Its agent layer supports multiple decision modes, multi-agent coordination, MCP, and Skills extensions. A Docker Compose setup can start the backend, administration UI, user UI, and supporting services together.
- Stars
- ★ 5,506
- Forks
- ⑂ 1,350
- License
- MIT
Open chopsDesktop appSoftware developmentmacOS
chops↗
@Shpigford·Swift
Manage coding-agent skills across tools from one native macOS app
Project overviewChops scans the skill and agent folders used by Claude Code, Cursor, Codex, Windsurf, Copilot, Aider, and Amp, then presents them in one native macOS interface. It offers full-text search, editing, collections, live file watching, boilerplate creation, and symlink-aware deduplication. Remote server layouts can also be browsed for skill installation. The app requires macOS 15 or later and intentionally needs broad filesystem access.
- Stars
- ★ 1,449
- Forks
- ⑂ 93
- GitHub updated
- Jul 14, 2026
Open textgenDesktop appCommunication and collaborationREST
textgen↗
@oobabooga·Python
Run local language models through a chat interface or compatible API.
Project overviewTextGen provides portable desktop builds and a web interface for loading local models, including GGUF files, and using them for chat, vision, document questions, and free-form generation. It can switch among several inference backends and expose OpenAI- and Anthropic-compatible endpoints with tool calling and MCP support. Core use can remain fully offline with no telemetry, while training, additional backends, image generation, and some extensions require the full installation.
- Stars
- ★ 47,447
- Forks
- ⑂ 5,983
- License
- AGPL-3.0