Github Top Repositories
Photo
🔍 Deep-diving into microsoft/ai-agents-for-beginners — fresh off the trending list.
🔗 https://github.com/microsoft/ai-agents-for-beginners
📝 12 Lessons to Get Started Building AI Agents
──────────────────────────────
AI Agents for Beginners is a comprehensive course that teaches everything you need to know to start building AI Agents. The course covers the fundamentals of building AI Agents, with lessons on topics such as intro to AI agents, AI agentic frameworks, and designing trustworthy AI agents.
The course includes multi-language support for over 50 languages, making it accessible to a wide range of learners. You can access the course materials, including
To get started, simply navigate to the lesson that interests you the most, and follow the instructions in the
This course is perfect for beginners and experienced learners alike, with a focus on hands-on learning and practical applications. So why wait? Dive in and start building your own AI agents today - with this course, you'll be well on your way to creating intelligent agents that can interact with the world in complex and fascinating ways!
──────────────────────────────
🧠 Channel: https://t.me/GithubRe
🔗 https://github.com/microsoft/ai-agents-for-beginners
📝 12 Lessons to Get Started Building AI Agents
──────────────────────────────
AI Agents for Beginners is a comprehensive course that teaches everything you need to know to start building AI Agents. The course covers the fundamentals of building AI Agents, with lessons on topics such as intro to AI agents, AI agentic frameworks, and designing trustworthy AI agents.
The course includes multi-language support for over 50 languages, making it accessible to a wide range of learners. You can access the course materials, including
Python code samples, by forking the repo or cloning it locally using git. The course utilizes Microsoft Agent Framework and Azure AI Foundry Agent Service V2, with some code samples also supporting alternative OpenAI-compatible providers.To get started, simply navigate to the lesson that interests you the most, and follow the instructions in the
README file. You can also join the Microsoft Foundry Discord channel to meet other learners, get your questions answered, and stay up-to-date with the latest developments in AI agents. This course is perfect for beginners and experienced learners alike, with a focus on hands-on learning and practical applications. So why wait? Dive in and start building your own AI agents today - with this course, you'll be well on your way to creating intelligent agents that can interact with the world in complex and fascinating ways!
──────────────────────────────
🧠 Channel: https://t.me/GithubRe
Github Top Repositories
Photo
🔍 Deep-diving into HKUDS/ViMax — fresh off the trending list.
🔗 https://github.com/HKUDS/ViMax
📝 "ViMax: Agentic Video Generation (Director, Screenwriter, Producer, and Video Generator All-in-One)"
──────────────────────────────
ViMax is an innovative video generation platform that aims to revolutionize the way we create videos. The traditional process of video creation is time-consuming, requiring multiple specialists and lengthy workflows. ViMax changes this by automating the entire pipeline from narrative input to final video output.
The key features of ViMax include:
-
-
-
-
From a technical standpoint, ViMax uses a multi-agent framework to ensure character and scene consistency. The system features intelligent long script generation, expressive storyboard design, and automated shot planning.
ViMax is designed for anyone looking to create high-quality videos without the need for extensive technical expertise. Whether you're a filmmaker, a writer, or simply someone with a great idea, ViMax provides the tools to bring your vision to life.
In short, ViMax is a game-changer for video creation - just input your concept, and let ViMax handle the rest. Automate your video production, amplify your creativity.
──────────────────────────────
🧠 Channel: https://t.me/GithubRe
🔗 https://github.com/HKUDS/ViMax
📝 "ViMax: Agentic Video Generation (Director, Screenwriter, Producer, and Video Generator All-in-One)"
──────────────────────────────
ViMax is an innovative video generation platform that aims to revolutionize the way we create videos. The traditional process of video creation is time-consuming, requiring multiple specialists and lengthy workflows. ViMax changes this by automating the entire pipeline from narrative input to final video output.
The key features of ViMax include:
-
Idea2Video: transforming raw ideas into complete video stories-
Novel2Video: adapting complete novels into episodic video content-
Script2Video: creating videos from scripts-
AutoCameo: generating videos from user-uploaded photosFrom a technical standpoint, ViMax uses a multi-agent framework to ensure character and scene consistency. The system features intelligent long script generation, expressive storyboard design, and automated shot planning.
ViMax is designed for anyone looking to create high-quality videos without the need for extensive technical expertise. Whether you're a filmmaker, a writer, or simply someone with a great idea, ViMax provides the tools to bring your vision to life.
In short, ViMax is a game-changer for video creation - just input your concept, and let ViMax handle the rest. Automate your video production, amplify your creativity.
──────────────────────────────
🧠 Channel: https://t.me/GithubRe
❤1
Github Top Repositories
Photo
🔍 Deep-diving into colbymchenry/codegraph — fresh off the trending list.
🔗 https://github.com/colbymchenry/codegraph
📝 Pre-indexed code knowledge graph for Claude Code, Codex, Cursor, and OpenCode — fewer tokens, fewer tool calls, 100% local
──────────────────────────────
Overview of CodeGraph
The codegraph repository offers a cutting-edge solution to supercharge code exploration with semantic code intelligence. It provides a local, pre-indexed knowledge graph for agents like Claude Code, Cursor, Codex CLI, and opencode, enabling them to query the graph instantly instead of scanning files.
Key Features
The key features of CodeGraph include:
- Smart Context Building: one tool call returns entry points, related symbols, and code snippets
- Full-Text Search: find code by name instantly across the entire codebase
- Impact Analysis: trace callers, callees, and the full impact radius of any symbol
- Always Fresh: file watcher uses native OS events with debounced auto-sync
- Support for 19+ languages and framework-aware routes for 13 frameworks
Usage
To get started, run the installer with
Technical Highlights
CodeGraph offers significant performance improvements, with 94% fewer tool calls and 77% faster exploration in benchmark tests. It is 100% local, with no data leaving your machine and no external services required.
Audience
CodeGraph is designed for developers who use agents like Claude Code, Cursor, Codex CLI, or opencode for code exploration. It is particularly useful for large codebases and complex projects.
Punchy Takeaway
CodeGraph revolutionizes code exploration by providing a pre-indexed knowledge graph, making it an indispensable tool for developers seeking to supercharge their coding experience: CodeGraph - explore smarter, not harder.
──────────────────────────────
🧠 Channel: https://t.me/GithubRe
🔗 https://github.com/colbymchenry/codegraph
📝 Pre-indexed code knowledge graph for Claude Code, Codex, Cursor, and OpenCode — fewer tokens, fewer tool calls, 100% local
──────────────────────────────
Overview of CodeGraph
The codegraph repository offers a cutting-edge solution to supercharge code exploration with semantic code intelligence. It provides a local, pre-indexed knowledge graph for agents like Claude Code, Cursor, Codex CLI, and opencode, enabling them to query the graph instantly instead of scanning files.
Key Features
The key features of CodeGraph include:
- Smart Context Building: one tool call returns entry points, related symbols, and code snippets
- Full-Text Search: find code by name instantly across the entire codebase
- Impact Analysis: trace callers, callees, and the full impact radius of any symbol
- Always Fresh: file watcher uses native OS events with debounced auto-sync
- Support for 19+ languages and framework-aware routes for 13 frameworks
Usage
To get started, run the installer with
npx @colbymchenry/codegraph, then initialize your project with codegraph init -i. Agents will use CodeGraph tools automatically when a .codegraph/ directory exists.Technical Highlights
CodeGraph offers significant performance improvements, with 94% fewer tool calls and 77% faster exploration in benchmark tests. It is 100% local, with no data leaving your machine and no external services required.
Audience
CodeGraph is designed for developers who use agents like Claude Code, Cursor, Codex CLI, or opencode for code exploration. It is particularly useful for large codebases and complex projects.
Punchy Takeaway
CodeGraph revolutionizes code exploration by providing a pre-indexed knowledge graph, making it an indispensable tool for developers seeking to supercharge their coding experience: CodeGraph - explore smarter, not harder.
──────────────────────────────
🧠 Channel: https://t.me/GithubRe
Forwarded from Machine Learning with Python
🙏💸 500$ FOR THE FIRST 500 WHO JOIN THE CHANNEL! 🙏💸
Join our channel today for free! Tomorrow it will cost 500$!
https://t.me/+-WZeIeP8YI8wM2E6
You can join at this link! 👆👇
https://t.me/+-WZeIeP8YI8wM2E6
Join our channel today for free! Tomorrow it will cost 500$!
https://t.me/+-WZeIeP8YI8wM2E6
You can join at this link! 👆👇
https://t.me/+-WZeIeP8YI8wM2E6
❤1
🎯 Imbad0202/academic-research-skills landed on trending. Worth a proper look.
🔗 https://github.com/Imbad0202/academic-research-skills
📝 Academic Research Skills for Claude Code: research → write → review → revise → finalize
──────────────────────────────
The Academic Research Skills GitHub repository, created by Imbad0202, offers a comprehensive toolkit for academic researchers to streamline their workflow from research to publication. This suite of skills is designed to work with the Claude Code platform, providing a range of features to assist in research, paper writing, and peer review.
The key features include Deep Research with 13-agent research teams, Academic Paper writing assistance with Style Calibration and Writing Quality Check, and Academic Paper Reviewer for multi-perspective peer review. It also includes an Academic Pipeline orchestrator with adaptive checkpoints and claim verification.
To use this toolkit, you can install it in 30 seconds using the Claude Code CLI or VS Code. Simply run the commands
The technical highlights of this toolkit include its ability to handle the grunt work of research, such as hunting down references, formatting citations, and verifying data, allowing researchers to focus on the parts that require their brainpower. The toolkit is designed with a human-in-the-loop approach, avoiding the failure modes of fully autonomous AI research pipelines.
This toolkit is suitable for academic researchers who want to improve the quality and efficiency of their research workflow. With its comprehensive features and user-friendly interface, it's an ideal tool for researchers looking to streamline their workflow and produce high-quality research papers.
In summary, the Academic Research Skills toolkit is a powerful tool for academic researchers, providing a range of features to assist in research, paper writing, and peer review, and is designed to work in conjunction with the Claude Code platform.
The punchy one-liner takeaway is: Augment your research with AI, not the other way around.
──────────────────────────────
🧠 Channel: https://t.me/GithubRe
🔗 https://github.com/Imbad0202/academic-research-skills
📝 Academic Research Skills for Claude Code: research → write → review → revise → finalize
──────────────────────────────
The Academic Research Skills GitHub repository, created by Imbad0202, offers a comprehensive toolkit for academic researchers to streamline their workflow from research to publication. This suite of skills is designed to work with the Claude Code platform, providing a range of features to assist in research, paper writing, and peer review.
The key features include Deep Research with 13-agent research teams, Academic Paper writing assistance with Style Calibration and Writing Quality Check, and Academic Paper Reviewer for multi-perspective peer review. It also includes an Academic Pipeline orchestrator with adaptive checkpoints and claim verification.
To use this toolkit, you can install it in 30 seconds using the Claude Code CLI or VS Code. Simply run the commands
/plugin marketplace add Imbad0202/academic-research-skills and /plugin install academic-research-skills, then try /ars-plan to start a Socratic dialogue for your paper structure.The technical highlights of this toolkit include its ability to handle the grunt work of research, such as hunting down references, formatting citations, and verifying data, allowing researchers to focus on the parts that require their brainpower. The toolkit is designed with a human-in-the-loop approach, avoiding the failure modes of fully autonomous AI research pipelines.
This toolkit is suitable for academic researchers who want to improve the quality and efficiency of their research workflow. With its comprehensive features and user-friendly interface, it's an ideal tool for researchers looking to streamline their workflow and produce high-quality research papers.
In summary, the Academic Research Skills toolkit is a powerful tool for academic researchers, providing a range of features to assist in research, paper writing, and peer review, and is designed to work in conjunction with the Claude Code platform.
The punchy one-liner takeaway is: Augment your research with AI, not the other way around.
──────────────────────────────
🧠 Channel: https://t.me/GithubRe
Github Top Repositories
Photo
🌟 tinyhumansai/openhuman caught my eye on GitHub Trending today.
🔗 https://github.com/tinyhumansai/openhuman
📝 Your Personal AI super intelligence. Private, Simple and extremely powerful.
──────────────────────────────
OpenHuman is an open-source AI assistant designed to integrate with your daily life, providing a simple and powerful experience. With 118+ third-party integrations and auto-fetch, it connects to your accounts and pulls data locally, compressing everything into Markdown files stored in a Karpathy-style Obsidian wiki.
Key features include:
-
-
-
To get started, you can either download from the website or run the installation script:
OpenHuman is suitable for anyone looking for a powerful and private AI assistant, with a focus on minimizing vendor sprawl and keeping workflow knowledge on-device.
The project is still in early beta and under active development, but it has the potential to revolutionize the way we interact with AI assistants.
Star the repo and help others find the path: OpenHuman is the agent that learns about you in minutes, not weeks.
──────────────────────────────
🧠 Channel: https://t.me/GithubRe
🔗 https://github.com/tinyhumansai/openhuman
📝 Your Personal AI super intelligence. Private, Simple and extremely powerful.
──────────────────────────────
OpenHuman is an open-source AI assistant designed to integrate with your daily life, providing a simple and powerful experience. With 118+ third-party integrations and auto-fetch, it connects to your accounts and pulls data locally, compressing everything into Markdown files stored in a Karpathy-style Obsidian wiki.
Key features include:
-
Simple, UI-first & Human: a clean desktop experience with a mascot that speaks and reacts to its surroundings-
Memory Tree + Obsidian Wiki: a local-first knowledge base built from your data and activity-
Batteries included: web search, web-fetch scraper, coder toolset, and native voice are wired in by defaultTo get started, you can either download from the website or run the installation script:
curl -fsSL https://raw.githubusercontent.com/tinyhumansai/openhuman/main/scripts/install.sh | bash
OpenHuman is suitable for anyone looking for a powerful and private AI assistant, with a focus on minimizing vendor sprawl and keeping workflow knowledge on-device.
The project is still in early beta and under active development, but it has the potential to revolutionize the way we interact with AI assistants.
Star the repo and help others find the path: OpenHuman is the agent that learns about you in minutes, not weeks.
──────────────────────────────
🧠 Channel: https://t.me/GithubRe
⚡ multica-ai/andrej-karpathy-skills is making waves. Here's the full picture.
🔗 https://github.com/multica-ai/andrej-karpathy-skills
📝 A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
──────────────────────────────
The multica-ai/andrej-karpathy-skills GitHub repository is based on Andrej Karpathy's observations about the pitfalls of Large Language Models (LLMs) in coding. The repository aims to improve the behavior of Claude Code, an LLM-based coding assistant, by providing a set of guidelines that address common issues such as wrong assumptions, overcomplication, and lack of clarity.
The guidelines are based on four key principles:
Think Before Coding,
Simplicity First,
Surgical Changes, and
Goal-Driven Execution. These principles encourage the LLM to think critically, write simple code, make targeted changes, and focus on achieving specific goals.
To use these guidelines, you can install them as a Claude Code plugin or add them to your project's
The key insight behind these guidelines is that LLMs are good at looping until they meet specific goals, so it's better to give them success criteria and let them work towards it. By following these guidelines, you can expect to see fewer unnecessary changes, simpler code, and cleaner pull requests.
In summary, the multica-ai/andrej-karpathy-skills repository provides a set of guidelines to help you get the most out of your LLM-based coding assistant, and the punchy one-liner takeaway is: Give your LLMs clear goals, and they'll code like pros!
──────────────────────────────
🧠 Channel: https://t.me/GithubRe
🔗 https://github.com/multica-ai/andrej-karpathy-skills
📝 A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
──────────────────────────────
The multica-ai/andrej-karpathy-skills GitHub repository is based on Andrej Karpathy's observations about the pitfalls of Large Language Models (LLMs) in coding. The repository aims to improve the behavior of Claude Code, an LLM-based coding assistant, by providing a set of guidelines that address common issues such as wrong assumptions, overcomplication, and lack of clarity.
The guidelines are based on four key principles:
Think Before Coding,
Simplicity First,
Surgical Changes, and
Goal-Driven Execution. These principles encourage the LLM to think critically, write simple code, make targeted changes, and focus on achieving specific goals.
To use these guidelines, you can install them as a Claude Code plugin or add them to your project's
CLAUDE.md file. The repository also includes a committed Cursor project rule, allowing you to apply the same guidelines when working with Cursor.The key insight behind these guidelines is that LLMs are good at looping until they meet specific goals, so it's better to give them success criteria and let them work towards it. By following these guidelines, you can expect to see fewer unnecessary changes, simpler code, and cleaner pull requests.
In summary, the multica-ai/andrej-karpathy-skills repository provides a set of guidelines to help you get the most out of your LLM-based coding assistant, and the punchy one-liner takeaway is: Give your LLMs clear goals, and they'll code like pros!
──────────────────────────────
🧠 Channel: https://t.me/GithubRe
🎯 rohitg00/ai-engineering-from-scratch landed on trending. Worth a proper look.
🔗 https://github.com/rohitg00/ai-engineering-from-scratch
📝 Learn it. Build it. Ship it for others.
──────────────────────────────
The GitHub repository rohitg00/ai-engineering-from-scratch offers a comprehensive curriculum for learning AI engineering from the ground up. This free, open-source resource provides
The curriculum is structured to help learners build a strong foundation in AI concepts, with each lesson following a consistent pattern of reading, deriving math, writing code, running tests, and keeping reusable artifacts. The repository includes a range of features, such as a placement quiz to help learners find their starting point and a personalized learning path with hour estimates.
The target audience for this repository includes individuals who want to understand how AI actually works, not just call APIs. The curriculum is designed to be accessible to those with basic coding skills, and no prior knowledge of AI is required.
By the end of the curriculum, learners will have a portfolio of
In short, rohitg00/ai-engineering-from-scratch is a valuable resource for anyone looking to learn AI engineering from scratch, with a focus on hands-on implementation and practical application. Build it, don't just learn it.
──────────────────────────────
🧠 Channel: https://t.me/GithubRe
🔗 https://github.com/rohitg00/ai-engineering-from-scratch
📝 Learn it. Build it. Ship it for others.
──────────────────────────────
The GitHub repository rohitg00/ai-engineering-from-scratch offers a comprehensive curriculum for learning AI engineering from the ground up. This free, open-source resource provides
428 lessons across 20 phases, covering topics from math foundations to autonomous systems, with a focus on hands-on implementation in Python, TypeScript, Rust, and Julia. The curriculum is structured to help learners build a strong foundation in AI concepts, with each lesson following a consistent pattern of reading, deriving math, writing code, running tests, and keeping reusable artifacts. The repository includes a range of features, such as a placement quiz to help learners find their starting point and a personalized learning path with hour estimates.
The target audience for this repository includes individuals who want to understand how AI actually works, not just call APIs. The curriculum is designed to be accessible to those with basic coding skills, and no prior knowledge of AI is required.
By the end of the curriculum, learners will have a portfolio of
428 artifacts that they can use in their daily workflow, including prompts, skills, agents, and MCP servers. The repository also includes a range of tools and resources, such as SkillKit, to help learners get started and stay on track.In short, rohitg00/ai-engineering-from-scratch is a valuable resource for anyone looking to learn AI engineering from scratch, with a focus on hands-on implementation and practical application. Build it, don't just learn it.
──────────────────────────────
🧠 Channel: https://t.me/GithubRe