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 46 of 240
Open learning-opportunitiesPluginEducation and learningClaude Code
learning-opportunities↗
@DrCatHicks·Shell
Turn completed AI-assisted coding work into short deliberate learning exercises.
Project overviewLearning Opportunities is a Claude and Codex skill that turns significant coding work into optional 10–15 minute learning exercises. After architectural changes, new modules, refactors, or unfamiliar patterns, it uses prediction, generation, retrieval practice, and spacing to build lessons from the user's own project. The agent pauses for the developer's answers instead of completing the exercise itself, and an optional companion orientation skill can prepare lessons for an unfamiliar repository.
- Stars
- ★ 2,256
- Forks
- ⑂ 81
- License
- CC-BY-4.0
Open awesome-ascend-skillsCollection or directorySoftware development
awesome-ascend-skills↗
@ascend-ai-coding·Python
Install task-specific skills for Huawei Ascend development and troubleshooting.
Project overviewAwesome Ascend Skills organizes Huawei Ascend NPU development knowledge into installable agent skills for environment checks, model migration and conversion, inference deployment, distributed training, profiling, and operator work. Users can start with a base bundle, add a domain bundle, or copy only the individual skills needed for a project. It is a workflow and knowledge collection rather than a runtime, so real tasks still depend on the relevant Ascend hardware, software stack, and external tools.
- Stars
- ★ 136
- Forks
- ⑂ 51
- GitHub updated
- Jul 14, 2026
Open CouncilDesktop appProductivity and officemacOS
Council↗
@albertofettucini·Swift
Compare parallel AI answers, blind critiques, and areas of disagreement.
Project overviewCouncil is a native macOS app that sends one question to several cloud or local language models, streams independent answers, and lets the models critique one another anonymously. It then shows agreement, camps, outliers, and divergence so the user can decide. Users bring their own provider keys or connect Ollama and OpenAI-compatible endpoints; keys stay in the macOS Keychain, with no Council account, server, or telemetry. It requires macOS 14 or later and shows a Gatekeeper warning on first launch because the release lacks a paid Apple certificate.
- Stars
- ★ 102
- Forks
- ⑂ 6
- License
- MIT
Open medisDesktop appBackend developmentmacOS
medis↗
@luin·JavaScript
Connect to and manage Redis databases through a graphical desktop application.
Project overviewMedis offers an Electron-based desktop interface for working with Redis, with compiled macOS releases, a community Windows build, and documented connection steps for Heroku Redis. This repository contains the original application. Its documentation directs users to the separately rebuilt Medis 2, so adopters should distinguish between the legacy source here and the newer product.
- Stars
- ★ 11,734
- Forks
- ⑂ 782
- License
- MIT
Open skillsCollection or directorySoftware developmentClaude Code
skills↗
@qdrant·Python
Guide coding agents through Qdrant scaling, search quality, and deployment decisions.
Project overviewQdrant Skills gives coding agents decision-oriented guidance for vector-search engineering. It covers scaling, quantization, performance, search quality, monitoring, deployment, tenant isolation, embedding-model migration, upgrades, and SDK use across several languages. Users can install the Qdrant Advisor to load matching guidance dynamically or keep the full set locally for offline triggering. The material acts as a solutions-architecture handbook explaining when and why to choose an approach and pointing to relevant documentation, rather than teaching Qdrant from scratch.
- Stars
- ★ 198
- Forks
- ⑂ 23
- License
- Apache-2.0
Open bitterbot-desktopGeneral agentPersonal and daily life
bitterbot-desktop↗
@Bitterbot-AI·TypeScript
Run a local personal AI with persistent memory and a peer-to-peer skill economy.
Project overviewBitterbot is a local-first personal AI system with a browser control interface for chat, sessions, memory, skills, and scheduled work. Its dream engine periodically reorganizes stored knowledge, while optional integrations connect messaging channels, a peer-to-peer skills network, and an agent wallet using Base and USDC. Setup is substantial: it requires Node 22, pnpm, several local dependencies, and onboarding for model authentication, embeddings, search, channels, and optional wallet features, making it best suited to users comfortable maintaining an experimental agent environment.
- Stars
- ★ 2,425
- Forks
- ⑂ 421
- GitHub updated
- Jul 14, 2026
Open infra-skillsCollection or directoryDevOps and deploymentClaude Code
infra-skills↗
@yzlnew·Python
Add specialized skills for GPU kernels, distributed training, and technical communication.
Project overviewUse focused skills for TileLang GPU kernel development, Megatron memory estimation, SLIME reinforcement-learning training, and supporting tasks such as technical diagrams or presentations. Some skills are complete while planned SGLang and vLLM modules are not yet available. The repository is under active development and much of its content was generated with LLM assistance, so code and recommendations should be verified before production use.
- Stars
- ★ 139
- Forks
- ⑂ 10
- GitHub updated
- Jul 14, 2026
Open grideaDesktop appWriting and editingLinux
gridea↗
@getgridea·TypeScript
Write and publish a static blog from a desktop app
Project overviewGridea provides a desktop workflow for writing Markdown posts, inserting images and cover art, grouping articles, configuring menus, and choosing themes. It can publish the generated site through GitHub Pages or Coding Pages, connect Gitalk or DisqusJS comments, and keep its source folder synchronized across devices through services such as OneDrive, iCloud, or Dropbox.
- Stars
- ★ 10,269
- Forks
- ⑂ 836
- License
- MIT
Open elasticvueDesktop appTesting and debuggingREST
elasticvue↗
@cars10·TypeScript
Manage Elasticsearch clusters, indices, and documents through a graphical interface.
Project overviewElasticvue is an open-source graphical client for managing Elasticsearch data and cluster state. It is available as a desktop app, browser extension, hosted web app, or self-hosted deployment. Users can view a cluster overview, manage indices, aliases, and shards, search or edit documents, and run REST queries. Web and Docker-based use generally require Elasticsearch CORS configuration, while the desktop app needs less cluster-side setup.
- Stars
- ★ 2,701
- Forks
- ⑂ 194
- License
- MIT
Open AI-CubbyDesktop appProductivity and officeWindows
AI-Cubby↗
@miragecoa·Vue
Track opened files and apps to build a searchable, private usage history.
Project overviewAI Cubby is a Windows media and usage manager that records the programs and files you actively open, including launch counts, runtime, and last-used dates. You can also index folders, tag important items, and search the resulting local library when you cannot remember a tool or filename. Data stays in a local SQLite database, while natural-language search and AI auto-categorization are still listed as upcoming features.
- Stars
- ★ 207
- Forks
- ⑂ 4
- License
- AGPL-3.0
Open Abu-CoworkGeneral agentProductivity and officeModel Context Protocol
Abu-Cowork↗
@PM-Shawn·TypeScript
Plan and execute local desktop tasks across files, commands, browsers, and documents.
Project overviewAbu Cowork is a local-first desktop AI agent that can plan multi-step work, read and write files, run commands, control a real browser, and create documents or web pages from natural-language requests. Risky actions such as deletion, overwriting, sending, or installation can be placed behind a reviewable plan and explicit approval. Each conversation can use its own model and permission mode. The app also supports installable skills, MCP connectors, schedules, and team messaging channels for broader automation.
- Stars
- ★ 194
- Forks
- ⑂ 53
- GitHub updated
- Jul 14, 2026
Open mdfluxDesktop appDocument productivityWindows
mdflux↗
@ibrahimqureshae·Svelte
Convert documents and scanned PDFs into clean Markdown locally on Windows.
Project overviewMDFlux is a Windows desktop app for turning PDFs, Office files, ebooks, web formats, images, and audio into structured Markdown without using a terminal. Built-in OCR recovers text from scanned or image-only PDFs, and folder batching provides progress and per-file diagnostics. The first launch needs internet access to prepare a local Python environment; later conversions run offline, while macOS support is still only planned.
- Stars
- ★ 178
- Forks
- ⑂ 17
- License
- MIT
Open mermaid-skillAutomationDocument productivityClaude Code
mermaid-skill↗
@Agents365-ai·Mermaid
Generate, validate, and export multiple Mermaid diagram types from natural language.
Project overviewmermaid-skill turns descriptions of processes, API calls, data relationships, or timelines into version-control-friendly `.mmd` source. It chooses an appropriate diagram type, validates the syntax before export, and inspects the rendered image for clipped labels, excessive density, or poor orientation. More than eleven Mermaid formats are covered, with PNG, SVG, and PDF export through a local `mmdc` installation or the Kroki API.
- Stars
- ★ 130
- Forks
- ⑂ 10
- License
- MIT
Open qiaomu-designRules or configurationDesign and creative workClaude Code
qiaomu-design↗
@joeseesun·JavaScript
Compare four visual directions before Claude Code implements the chosen interface.
Project overviewqiaomu-design is a Claude Code skill that begins with a product and interface diagnosis, then creates four deliberately different browser-viewable directions for comparison. After a user selects one, it implements the design using either the existing product system or a newly defined combination of typography, color, layout, motion, and density. It requires Claude Code, and the project recommends Claude or GLM 5.2 when visual quality is the priority.
- Stars
- ★ 387
- Forks
- ⑂ 35
- License
- MIT
Open ok-skillsCollection or directorySoftware developmentClaude Code
ok-skills↗
@mxyhi·HTML
Add reusable development, design, and office workflows to multiple coding agents.
Project overviewOK Skills packages 32 reusable skills plus AGENTS.md and CLAUDE.md playbooks for Codex, Claude Code, Cursor, and other compatible tools. The library covers documentation lookup, browser automation, planning, debugging, frontend work, and office documents, while some skills still depend on tools such as gh, a browser environment, or external MCP services.
- Stars
- ★ 452
- Forks
- ⑂ 40
- License
- Apache-2.0
Open browserwingMCP serverSoftware developmentModel Context Protocol
browserwing↗
@browserwing·Go
Record browser workflows and export them as MCP commands or skills.
Project overviewCapture clicks, typing, navigation, and waits with a visual recorder, edit and replay the workflow, then export it as reusable MCP commands or Skills files for AI agents. BrowserWing also offers an agent-friendly CLI, an HTTP automation API, session and cookie management, and built-in scripts that return structured data. It requires an accessible Chrome or Chromium installation.
- Stars
- ★ 1,367
- Forks
- ⑂ 129
- License
- MIT
Open Pandora-BoxDesktop appSecurity and privacy
Pandora-Box↗
@snakem982·Vue
Manage and convert Mihomo proxy subscriptions from a desktop interface.
Project overviewPandora-Box is a cross-platform desktop client for Mihomo that helps users manage and convert proxy subscriptions. It supports multiple proxy protocols, automatic rule grouping, and TUN mode. Prebuilt releases are available, while source builds require Node.js 18 or later and Go 1.24 or later.
- Stars
- ★ 1,167
- Forks
- ⑂ 125
- License
- GPL-3.0
Open effective-htmlCollection or directoryDesign and creative workClaude Code
effective-html↗
@plannotator·HTML
Generate clean HTML plans, architecture diagrams, and visual documents.
Project overvieweffective-html is a collection of Agent Skills for producing self-contained visual HTML deliverables. The general html skill handles broad pages, html-diagram creates full-screen architecture and system diagrams with SVG-first presentation, and html-plan builds structured planning pages. Each skill bundles a local example corpus to guide the intended style. Users can install the full collection or one skill, then optionally annotate the rendered result with Plannotator or share it through a separate service.
- Stars
- ★ 1,358
- Forks
- ⑂ 108
- License
- MIT