Github Top Repositories
Photo
🚀 Meet santifer/career-ops: a gem from today's GitHub trending list.
🔗 https://github.com/santifer/career-ops
📝 AI-powered job search system built on Claude Code. 14 skill modes, Go dashboard, PDF generation, batch processing.
──────────────────────────────
The Career-Ops system is an open-source, AI-powered job search command center that helps candidates find their dream roles. It evaluates job listings, generates tailored CVs, and scans company portals for new offers. With its
The system is agentic, using AI to navigate career pages, evaluate fit, and adapt resumes per listing. It's built with technologies like
To get started, users can
The key features of Career-Ops include auto-pipeline, interview story bank, and pipeline integrity. It also supports
In summary, Career-Ops is a powerful tool for job seekers, providing a personalized and efficient approach to finding their dream roles: it's like having a personal recruiter in your pocket.
──────────────────────────────
🧠 Channel: https://t.me/GithubRe
🔗 https://github.com/santifer/career-ops
📝 AI-powered job search system built on Claude Code. 14 skill modes, Go dashboard, PDF generation, batch processing.
──────────────────────────────
The Career-Ops system is an open-source, AI-powered job search command center that helps candidates find their dream roles. It evaluates job listings, generates tailored CVs, and scans company portals for new offers. With its
6-block evaluation system and negotiation scripts, Career-Ops provides a comprehensive approach to job searching. The system is agentic, using AI to navigate career pages, evaluate fit, and adapt resumes per listing. It's built with technologies like
Claude Code, OpenCode, and Gemini CLI, and supports Node.js and Go. To get started, users can
clone and install the repository, configure their profiles, and add their CVs. The system is designed to be customized by Claude Code itself, allowing users to change modes, archetypes, and scoring weights.The key features of Career-Ops include auto-pipeline, interview story bank, and pipeline integrity. It also supports
Gemini CLI integration and provides a dashboard TUI for browsing and filtering the pipeline.In summary, Career-Ops is a powerful tool for job seekers, providing a personalized and efficient approach to finding their dream roles: it's like having a personal recruiter in your pocket.
──────────────────────────────
🧠 Channel: https://t.me/GithubRe
❤2
Github Top Repositories
Photo
💡 phuryn/pm-skills just hit the trending charts — here's why it matters.
🔗 https://github.com/phuryn/pm-skills
📝 PM Skills Marketplace: 100+ agentic skills, commands, and plugins — from discovery to strategy, execution, launch, and growth.
──────────────────────────────
The pm-skills GitHub repository is a game-changer for product managers, offering a comprehensive AI-powered operating system for making better product decisions. With 68 PM skills and 42 chained workflows across 9 plugins, this marketplace provides a structured approach to product management, covering discovery, strategy, execution, launch, growth, and shipping AI-built code.
The
To get started, users can install the marketplace using
The repository includes a range of plugins, such as pm-product-discovery, pm-product-strategy, and pm-execution, each with its own set of skills and commands. For example, the
In summary, the pm-skills repository empowers product managers to make better product decisions with its comprehensive AI-powered operating system - Upgrade your product management workflow with pm-skills and start making data-driven decisions today!
──────────────────────────────
🧠 Channel: https://t.me/GithubRe
🔗 https://github.com/phuryn/pm-skills
📝 PM Skills Marketplace: 100+ agentic skills, commands, and plugins — from discovery to strategy, execution, launch, and growth.
──────────────────────────────
The pm-skills GitHub repository is a game-changer for product managers, offering a comprehensive AI-powered operating system for making better product decisions. With 68 PM skills and 42 chained workflows across 9 plugins, this marketplace provides a structured approach to product management, covering discovery, strategy, execution, launch, growth, and shipping AI-built code.
The
skills are the building blocks, encoding proven PM frameworks and guiding users through specific tasks. Commands chain one or more skills into end-to-end processes, while plugins group related skills and commands into installable packages.To get started, users can install the marketplace using
Claude Cowork or Claude Code, or even use the skills with other AI assistants like Codex, Gemini CLI, OpenCode, Cursor, or Kiro.The repository includes a range of plugins, such as pm-product-discovery, pm-product-strategy, and pm-execution, each with its own set of skills and commands. For example, the
/discover command chains four skills together: brainstorm-ideas, identify-assumptions, prioritize-assumptions, and brainstorm-experiments.In summary, the pm-skills repository empowers product managers to make better product decisions with its comprehensive AI-powered operating system - Upgrade your product management workflow with pm-skills and start making data-driven decisions today!
──────────────────────────────
🧠 Channel: https://t.me/GithubRe
⚡ openai/plugins is making waves. Here's the full picture.
🔗 https://github.com/openai/plugins
📝 OpenAI Plugins
──────────────────────────────
The openai/plugins repository is a treasure trove of community-driven innovation, hosting a wide range of Codex plugin examples to streamline your workflow. Each plugin is carefully organized under its own directory, complete with a
Some highlighted examples include plugins for Figma, Notion, iOS and macOS app development, web apps, Expo, and more. These plugins are designed to make your life easier, whether you're working on design systems, planning and research, or building and deploying apps.
The technical details are straightforward: each plugin has a required
This repository is perfect for developers, designers, and makers looking to tap into the power of Codex and automate their workflows.
In short, the openai/plugins repository is your one-stop shop for unlocking Codex's full potential - join the community and start building today!
──────────────────────────────
🧠 Channel: https://t.me/GithubRe
🔗 https://github.com/openai/plugins
📝 OpenAI Plugins
──────────────────────────────
The openai/plugins repository is a treasure trove of community-driven innovation, hosting a wide range of Codex plugin examples to streamline your workflow. Each plugin is carefully organized under its own directory, complete with a
plugin.json manifest and optional supporting files like skills/, agents/, and assets/. Some highlighted examples include plugins for Figma, Notion, iOS and macOS app development, web apps, Expo, and more. These plugins are designed to make your life easier, whether you're working on design systems, planning and research, or building and deploying apps.
The technical details are straightforward: each plugin has a required
plugin.json file and may include additional files and directories. For example, a plugin might include a hooks.jsonfile for custom hooks or an
agents/ directory for custom agent implementations. This repository is perfect for developers, designers, and makers looking to tap into the power of Codex and automate their workflows.
In short, the openai/plugins repository is your one-stop shop for unlocking Codex's full potential - join the community and start building today!
──────────────────────────────
🧠 Channel: https://t.me/GithubRe
Github Top Repositories
Photo
🎯 Andyyyy64/whichllm landed on trending. Worth a proper look.
🔗 https://github.com/Andyyyy64/whichllm
📝 Find the local LLM that actually runs and performs best on your hardware. Ranked by real, recency-aware benchmarks, not parameter count. One command, run it instantly.
──────────────────────────────
whichllm is a handy tool that helps you find the best local LLM (Large Language Model) that can run on your hardware. It auto-detects your GPU, CPU, and RAM, and then ranks the top models from HuggingFace that fit your system. You can use it to simulate a GPU before buying, compare upgrade candidates, and even start a chat with a model.
The tool uses evidence-based ranking, not just size heuristics, to choose the top pick. It also considers recency-aware scores, so stale leaderboards are demoted. You can use
Technical highlights include architecture-aware estimates, live data from the HuggingFace API, and a simple, scriptable command-line interface. whichllm is designed for developers, researchers, and anyone who wants to work with LLMs.
To get started, simply run
Here's a punchy one-liner takeaway: With whichllm, you can easily find the perfect LLM for your hardware and start building amazing AI projects!
──────────────────────────────
🧠 Channel: https://t.me/GithubRe
🔗 https://github.com/Andyyyy64/whichllm
📝 Find the local LLM that actually runs and performs best on your hardware. Ranked by real, recency-aware benchmarks, not parameter count. One command, run it instantly.
──────────────────────────────
whichllm is a handy tool that helps you find the best local LLM (Large Language Model) that can run on your hardware. It auto-detects your GPU, CPU, and RAM, and then ranks the top models from HuggingFace that fit your system. You can use it to simulate a GPU before buying, compare upgrade candidates, and even start a chat with a model.
The tool uses evidence-based ranking, not just size heuristics, to choose the top pick. It also considers recency-aware scores, so stale leaderboards are demoted. You can use
whichllm to get a copy-paste Python snippet for any model, and it supports various model formats like GGUF, AWQ, and GPTQ. Technical highlights include architecture-aware estimates, live data from the HuggingFace API, and a simple, scriptable command-line interface. whichllm is designed for developers, researchers, and anyone who wants to work with LLMs.
To get started, simply run
uvx whichllm@latest or install it using brew install andyyyy64/whichllm/whichllm or pip install whichllm. Here's a punchy one-liner takeaway: With whichllm, you can easily find the perfect LLM for your hardware and start building amazing AI projects!
──────────────────────────────
🧠 Channel: https://t.me/GithubRe
💡 MemPalace/mempalace just hit the trending charts — here's why it matters.
🔗 https://github.com/MemPalace/mempalace
📝 The best-benchmarked open-source AI memory system. And it's free.
──────────────────────────────
MemPalace is a local-first AI memory solution that stores conversation history as verbatim text and retrieves it with semantic search. It features a pluggable backend, with ChromaDB as the default, and supports alternative backends like sqlite_exact, qdrant, and pgvector.
To get started, users can install MemPalace using
MemPalace boasts an impressive 96.6% R@5 raw on the LongMemEval benchmark, with no API calls required. It also includes a temporal entity-relationship graph and supports MCP tools for palace reads/writes, knowledge-graph operations, and more.
The target audience for MemPalace includes developers, researchers, and individuals seeking a robust, local-first AI memory solution.
Overall, MemPalace offers a powerful and flexible solution for storing and retrieving conversation history, making it an excellent choice for those seeking a reliable and efficient AI memory system.
Takeaway: MemPalace revolutionizes local-first AI memory, making it a game-changer for anyone seeking to harness the power of semantic search.
──────────────────────────────
🧠 Channel: https://t.me/GithubRe
🔗 https://github.com/MemPalace/mempalace
📝 The best-benchmarked open-source AI memory system. And it's free.
──────────────────────────────
MemPalace is a local-first AI memory solution that stores conversation history as verbatim text and retrieves it with semantic search. It features a pluggable backend, with ChromaDB as the default, and supports alternative backends like sqlite_exact, qdrant, and pgvector.
To get started, users can install MemPalace using
uv tool install mempalace or pipx install mempalace, then initialize it with mempalace init ~/projects/myapp. The mempalace mine command is used to mine content into the palace, while mempalace search retrieves relevant information.MemPalace boasts an impressive 96.6% R@5 raw on the LongMemEval benchmark, with no API calls required. It also includes a temporal entity-relationship graph and supports MCP tools for palace reads/writes, knowledge-graph operations, and more.
The target audience for MemPalace includes developers, researchers, and individuals seeking a robust, local-first AI memory solution.
Overall, MemPalace offers a powerful and flexible solution for storing and retrieving conversation history, making it an excellent choice for those seeking a reliable and efficient AI memory system.
Takeaway: MemPalace revolutionizes local-first AI memory, making it a game-changer for anyone seeking to harness the power of semantic search.
──────────────────────────────
🧠 Channel: https://t.me/GithubRe
Github Top Repositories
Photo
💡 roboflow/supervision just hit the trending charts — here's why it matters.
🔗 https://github.com/roboflow/supervision
📝 We write your reusable computer vision tools. 💜
──────────────────────────────
Supervision is a Python library for building computer vision applications. Its purpose is to provide a simple and efficient way to work with computer vision models, datasets, and annotations. The library offers key features such as model-agnostic detection, segmentation, and classification, as well as tools for data loading, splitting, and merging.
To use Supervision, you can install it via pip:
Technical highlights of Supervision include its ability to load and annotate images and videos, as well as its support for customizable annotators. The library is designed for data scientists and machine learning engineers who want to build and deploy computer vision applications quickly and efficiently.
In summary, Supervision is a powerful library that simplifies computer vision development - build computer vision apps faster with Supervision.
──────────────────────────────
🧠 Channel: https://t.me/GithubRe
🔗 https://github.com/roboflow/supervision
📝 We write your reusable computer vision tools. 💜
──────────────────────────────
Supervision is a Python library for building computer vision applications. Its purpose is to provide a simple and efficient way to work with computer vision models, datasets, and annotations. The library offers key features such as model-agnostic detection, segmentation, and classification, as well as tools for data loading, splitting, and merging.
To use Supervision, you can install it via pip:
pip install supervision. The library supports various models and datasets, including Ultralytics, Transformers, and MMDetection, and provides connectors for popular libraries. Technical highlights of Supervision include its ability to load and annotate images and videos, as well as its support for customizable annotators. The library is designed for data scientists and machine learning engineers who want to build and deploy computer vision applications quickly and efficiently.
In summary, Supervision is a powerful library that simplifies computer vision development - build computer vision apps faster with Supervision.
──────────────────────────────
🧠 Channel: https://t.me/GithubRe
Github Top Repositories
Photo
🔥 CopilotKit/CopilotKit is trending — and it deserves your attention.
🔗 https://github.com/CopilotKit/CopilotKit
📝 The Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI Protocol
──────────────────────────────
CopilotKit is a multi-platform agentic framework that enables you to build full-stack agentic applications, Generative UI, and chat applications. The framework allows agents to power your web app, mobile app, and team's Slack workspace. It features a chat UI, backend tool rendering, generative UI, shared state, and human-in-the-loop workflows. CopilotKit supports various platforms, including React, Angular, Vue, and React Native.
The framework is built on top of the
CopilotKit is suitable for developers, product teams, and companies looking to build agentic applications and integrate AI into their products. The framework is constantly evolving, with new features and updates being added regularly. To get started with CopilotKit, you can install it using
With CopilotKit, you can add AI to your app in just 1 minute and unlock the power of agentic applications. Build the future of AI-powered applications with CopilotKit - where agents meet applications.
──────────────────────────────
🧠 Channel: https://t.me/GithubRe
🔗 https://github.com/CopilotKit/CopilotKit
📝 The Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI Protocol
──────────────────────────────
CopilotKit is a multi-platform agentic framework that enables you to build full-stack agentic applications, Generative UI, and chat applications. The framework allows agents to power your web app, mobile app, and team's Slack workspace. It features a chat UI, backend tool rendering, generative UI, shared state, and human-in-the-loop workflows. CopilotKit supports various platforms, including React, Angular, Vue, and React Native.
The framework is built on top of the
AG-UI Protocol, which is adopted by major companies like Google, LangChain, AWS, Microsoft, Mastra, and PydanticAI. CopilotKit provides a range of tools and features, including a useAgent hook, generative UI, and self-learning agents. The framework is designed to be easy to use, with a simple installation process and a comprehensive documentation.CopilotKit is suitable for developers, product teams, and companies looking to build agentic applications and integrate AI into their products. The framework is constantly evolving, with new features and updates being added regularly. To get started with CopilotKit, you can install it using
npx copilotkit@latest create -f <framework> or npx copilotkit@latest init for existing projects.With CopilotKit, you can add AI to your app in just 1 minute and unlock the power of agentic applications. Build the future of AI-powered applications with CopilotKit - where agents meet applications.
──────────────────────────────
🧠 Channel: https://t.me/GithubRe
📌 Spotted on GitHub Trending: TapXWorld/ChinaTextbook — let's break it down.
🔗 https://github.com/TapXWorld/ChinaTextbook
📝 所有小初高、大学PDF教材。
──────────────────────────────
ChinaTextbook is a GitHub repository that provides free access to Chinese textbooks, promoting equal access to education. The repository includes textbooks for elementary school, junior high school, high school, and university levels, covering subjects like mathematics.
To use the repository, simply browse through the folders and download the desired textbooks. Note that some files are split into smaller parts due to GitHub's upload size limits. To merge these files, you can use the
The project encourages open-source contributions and community involvement. You can support the project by donating or joining their Telegram community to stay updated on the latest developments.
One-liner takeaway: ChinaTextbook is a valuable resource for anyone looking for free access to Chinese educational materials, promoting education equality and open access to knowledge.
──────────────────────────────
🧠 Channel: https://t.me/GithubRe
🔗 https://github.com/TapXWorld/ChinaTextbook
📝 所有小初高、大学PDF教材。
──────────────────────────────
ChinaTextbook is a GitHub repository that provides free access to Chinese textbooks, promoting equal access to education. The repository includes textbooks for elementary school, junior high school, high school, and university levels, covering subjects like mathematics.
To use the repository, simply browse through the folders and download the desired textbooks. Note that some files are split into smaller parts due to GitHub's upload size limits. To merge these files, you can use the
mergePDFs-windows-amd64.exe program provided in the repository.The project encourages open-source contributions and community involvement. You can support the project by donating or joining their Telegram community to stay updated on the latest developments.
One-liner takeaway: ChinaTextbook is a valuable resource for anyone looking for free access to Chinese educational materials, promoting education equality and open access to knowledge.
──────────────────────────────
🧠 Channel: https://t.me/GithubRe
💡 luongnv89/claude-howto just hit the trending charts — here's why it matters.
🔗 https://github.com/luongnv89/claude-howto
📝 A visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.
──────────────────────────────
The luongnv89/claude-howto GitHub repository is a comprehensive, structured guide to mastering Claude Code. It's designed to help you go from basic usage to orchestrating agents, hooks, skills, and MCP servers in a weekend. The guide features visual tutorials,
Key features include:
* 10 tutorial modules covering every Claude Code feature
* Copy-paste configs for slash commands, CLAUDE.md templates, hook scripts, MCP configs, subagent definitions, and full plugin bundles
*
* A guided learning path with time estimates and interactive quizzes to identify knowledge gaps
The guide is suitable for developers of all levels, from those who have just installed Claude Code to experienced users looking to combine features into workflows. It's actively maintained, compatible with Claude Code 2.1+, and available under the MIT license, making it free to use forever.
To get started, you can
In summary, luongnv89/claude-howto is the ultimate resource for unlocking Claude Code's full potential, and with it, you can master Claude Code in a weekend and take your productivity to the next level - start learning now and 10x your productivity!
──────────────────────────────
🧠 Channel: https://t.me/GithubRe
🔗 https://github.com/luongnv89/claude-howto
📝 A visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.
──────────────────────────────
The luongnv89/claude-howto GitHub repository is a comprehensive, structured guide to mastering Claude Code. It's designed to help you go from basic usage to orchestrating agents, hooks, skills, and MCP servers in a weekend. The guide features visual tutorials,
copy-paste templates, and a guided learning path that takes you from beginner to power user in 11-13 hours.Key features include:
* 10 tutorial modules covering every Claude Code feature
* Copy-paste configs for slash commands, CLAUDE.md templates, hook scripts, MCP configs, subagent definitions, and full plugin bundles
*
Mermaid diagrams showing how each feature works internally* A guided learning path with time estimates and interactive quizzes to identify knowledge gaps
The guide is suitable for developers of all levels, from those who have just installed Claude Code to experienced users looking to combine features into workflows. It's actively maintained, compatible with Claude Code 2.1+, and available under the MIT license, making it free to use forever.
To get started, you can
clone the repository, copy a slash command template, and try it in 15 minutes. The guide also includes a 1-hour essential setup to get you up and running quickly.In summary, luongnv89/claude-howto is the ultimate resource for unlocking Claude Code's full potential, and with it, you can master Claude Code in a weekend and take your productivity to the next level - start learning now and 10x your productivity!
──────────────────────────────
🧠 Channel: https://t.me/GithubRe