Github Top Repositories
14.1K subscribers
2.83K photos
59 videos
10 files
2.94K links
Top GitHub repositories in one place 🚀
Explore the best projects in programming, AI, data science, and more.
Download Telegram
📌 Spotted on GitHub Trending: andrewyng/aisuite — let's break it down.

🔗 https://github.com/andrewyng/aisuite
📝 Simple, unified interface to multiple Generative AI providers
──────────────────────────────

The aisuite GitHub repository offers a lightweight Python library for building applications with large language models (LLMs). It features a unified Chat Completions API across multiple providers, including OpenAI, Anthropic, and Google, allowing for easy switching between them by changing a single string. The library also includes an Agents API with tools and toolkits for building more complex applications.

To get started with aisuite, you can install it using pip install aisuite, and then use the Client class to interact with the chat API. For example:
import aisuite as ai
client = ai.Client()
response = client.chat.completions.create(
model="openai:gpt-4o",
messages=[{"role": "user", "content": "Hello, how are you?"}],
temperature=0.75
)
print(response.choices[0].message.content)


aisuite is designed to be extensible, with a modular architecture that allows developers to add new providers and tools easily. The repository includes a Contributing Guide and a MIT License, making it easy for developers to get involved and use the library in their projects.

Overall, aisuite is a powerful tool for building applications with LLMs, and its unified API and extensible architecture make it a great choice for developers looking to work with multiple providers and tools. So why not harness the power of AI and start building with aisuite today?

──────────────────────────────
🧠 Channel: https://t.iss.one/GithubRe
1
Github Top Repositories
Photo
🚀 Meet affaan-m/ECC: a gem from today's GitHub trending list.

🔗 https://github.com/affaan-m/ECC
📝 The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
──────────────────────────────

The ECC repository provides an agent harness operating system, offering a coordinated engineering system and toolbox for agents to write code. It includes 67 agents, 281 skills, and 94 legacy command shims, along with features like hooks, rules, memory, continuous learning, and AgentShield security scanning.

ECC works with various harnesses, including Claude Code and Codex, and can be installed through different methods. The recommended default is to install the Claude Code plugin for Claude Code and use the supported sync flow for Codex.

The repository is MIT-licensed and open source, with a focus on providing a standardized process for agents to plan, test, implement, review, verify, and remember their work. The goal of ECC is to optimize the context window and persist everything else, making it a valuable tool for those looking to streamline their agent-based workflows.

The ECC system is designed to be user-friendly, with a simple installation process and a wide range of features to support agent development. Whether you're working with Claude Code, Codex, or another harness, ECC provides a powerful toolkit to help you get the most out of your agents.

Here's a sample
installation command
for Claude Code:
/plugin marketplace add https://github.com/affaan-m/ECC
/plugin install ecc@ecc


In summary, ECC is a powerful tool for agent harness operating systems, providing a wide range of features and a user-friendly installation process. Its focus on optimizing the context window and persisting everything else makes it an ideal choice for those looking to streamline their agent-based workflows. With ECC, you can unlock the full potential of your agents and take your workflows to the next level.

──────────────────────────────
🧠 Channel: https://t.iss.one/GithubRe
1
Github Top Repositories
Photo
🔍 Deep-diving into huggingface/speech-to-speech — fresh off the trending list.

🔗 https://github.com/huggingface/speech-to-speech
📝 Build local voice agents with open-source models
──────────────────────────────

The huggingface/speech-to-speech repo is an open-source pipeline for building voice agents. It consists of four interchangeable components: Voice Activity Detection (VAD), Speech to Text (STT), Language Model (LLM), and Text to Speech (TTS). The pipeline is modular, allowing users to swap out components as needed, and is exposed through an OpenAI Realtime-compatible WebSocket API.

The repo provides a range of features, including support for multiple STT and TTS models, as well as the ability to run the pipeline in different modes, such as realtime, local, websocket, and socket.

The pipeline is designed to be easy to use, with a simple pip install process and a range of optional backends that can be installed with pip extras. The repo also includes a range of examples and scripts to help users get started.

The target audience for this repo appears to be developers who want to build voice agents or other applications that require speech-to-speech functionality. With its modular design and support for multiple models and modes, huggingface/speech-to-speech is a powerful tool for anyone looking to build innovative voice-based applications.

Build your own voice agent with huggingface/speech-to-speech and revolutionize the way you interact with technology!

──────────────────────────────
🧠 Channel: https://t.iss.one/GithubRe
🔥 virgiliojr94/book-to-skill is trending — and it deserves your attention.

🔗 https://github.com/virgiliojr94/book-to-skill
📝 Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work.
──────────────────────────────

Book-to-Skill is a tool that turns any technical book, document folder, or collection of sources into a unified agent skill. This allows you to study, reference, and use the information while working in GitHub Copilot CLI, Amp, or Claude Code.

The tool works by distilling the book into a skill, including frameworks, decision rules, anti-patterns, and per-chapter files, and then loading it on demand. It supports various document formats, including PDF, EPUB, DOCX, and more.

Key features include:

* Turning books into structured skills that can be loaded on demand
* Supporting multiple document formats
* Generating core mental models, chapter index, glossary, patterns, and cheatsheet
* Allowing for updates and folding in of new material

The tool is designed for practitioners who want to get the most out of their technical books and documents. It's ideal for those who re-read documents often and want to make the information more accessible and usable.

From a technical standpoint, the tool uses various extraction methods, including Docling for technical books and pdftotext for text-heavy books. It also uses Claude to analyze the structure of the book and generate per-chapter summaries.

Usage is simple: just point the tool at a file, folder, or glob, and it will generate a full skill in your agent's skills directory.

Takeaway: With Book-to-Skill, you can turn any technical book into a powerful agent skill, making it easier to access and use the information you need to get the job done.

──────────────────────────────
🧠 Channel: https://t.iss.one/GithubRe
🔍 Deep-diving into opengeos/GeoLibre — fresh off the trending list.

🔗 https://github.com/opengeos/GeoLibre
📝 A lightweight, cloud-native GIS platform for visualizing, exploring, and analyzing geospatial data. It runs in the web browser, on the desktop, on mobile, and inside Jupyter notebooks.
──────────────────────────────

Meet GeoLibre, a free and open-source, lightweight, cloud-native GIS platform for visualizing, exploring, and analyzing geospatial data. It runs everywhere you do, in the web browser, on the desktop, on mobile, and inside Jupyter notebooks, all while keeping your data local and private. Key features include 3D Tiles, planetary basemaps, and a SQL Workspace.

To get started, you can launch the web app, download the desktop app, or run from source. The platform is built with Tauri v2, React, TypeScript, MapLibre GL JS, DuckDB-WASM Spatial, and deck.gl.

Technical highlights include a responsive design, a per-project ellipsoid for accurate distance and area measurements, and a plugin architecture. The platform is suitable for GIS professionals, data analysts, and researchers working with geospatial data.

In short, GeoLibre is a powerful tool that makes geospatial analysis accessible anywhere, anytime - and the best part is, it's completely free and open-source!

──────────────────────────────
🧠 Channel: https://t.iss.one/GithubRe
Github Top Repositories
Photo
🔥 paperswithbacktest/awesome-systematic-trading is trending — and it deserves your attention.

🔗 https://github.com/paperswithbacktest/awesome-systematic-trading
📝 A curated list of awesome libraries, packages, strategies, books, blogs, tutorials for systematic trading.
──────────────────────────────

The Awesome Systematic Trading GitHub repository is a treasure trove of resources for quantitative traders, featuring 97 libraries and packages, 40+ strategies, 55 books, 23 videos, and blogs and courses to help you find, develop, and run systematic trading strategies. You can explore backtesting and live trading frameworks, trading bots, analytics tools, and more. The repository is divided into sections, including libraries and packages, strategies, books, and videos, making it easy to navigate and find what you need. Whether you're a beginner or a professional, this repository has something for everyone. So, dive in and start exploring - your next trading strategy might just be a click away!

──────────────────────────────
🧠 Channel: https://t.iss.one/GithubRe
1
🎯 microsoft/agent-governance-toolkit landed on trending. Worth a proper look.

🔗 https://github.com/microsoft/agent-governance-toolkit
📝 AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.
──────────────────────────────

The Agent Governance Toolkit is an open-source framework that helps you manage and govern autonomous AI agents. Its primary goal is to ensure that AI agents behave as intended and follow the rules. The toolkit provides features like policy enforcement, identity management, sandboxing, and auditing to prevent potential risks.

Key Features:
- Policy Engine: Enforces rules and restrictions on AI agent actions
- Identity Management: Ensures that agents are authenticated and authorized
- Sandboxing: Limits agent privileges to prevent damage
- Auditing: Tracks and logs agent actions for transparency and accountability

To get started, you can install the toolkit using pip install agent-governance-toolkit[full] and follow the quick start guide. The toolkit supports multiple programming languages, including Python, TypeScript, .NET, Rust, and Go.

From a technical standpoint, the toolkit uses a stateless, deterministic, fail-closed policy decision runtime to ensure that agent actions are allowed or denied based on predefined rules. It also provides a range of tools and capabilities, including a CLI for verifying compliance and a PolicyEvaluator API for programmatic control.

The Agent Governance Toolkit is designed for developers, security teams, and organizations that work with autonomous AI agents. It's particularly useful for those who need to ensure that their agents comply with regulations and policies.

In summary, the Agent Governance Toolkit is a powerful framework for governing autonomous AI agents, providing a range of features and tools to ensure that agents behave as intended. With its easy-to-use govern() function, you can govern any tool function in just two lines of code - giving you peace of mind and a good night's sleep, knowing your AI agents are under control!

──────────────────────────────
🧠 Channel: https://t.iss.one/GithubRe
Github Top Repositories
Photo
🌟 yorukot/superfile caught my eye on GitHub Trending today.

🔗 https://github.com/yorukot/superfile
📝 Pretty fancy and modern terminal file manager
──────────────────────────────

Superfile is a powerful tool that simplifies file management. Its key features include a user-friendly interface, customizable plugins, and themes. To get started, you can install superfile using various methods, including a simple script for macOS and Linux:
bash -c "$(curl -sLo- https://superfile.dev/install.sh)"
. For Windows, you can use Powershell or package managers like Winget or Scoop. Technical highlights of superfile include its ability to handle large files and folders efficiently. The project is supported by the community and is suitable for developers, power users, and anyone looking for a robust file management solution. With its auto-update functionality and customizable hotkeys, superfile is a great choice for those who want a seamless file management experience. Overall, superfile is a must-have tool for anyone looking to streamline their file management workflow - give it a try and see the difference for yourself!

──────────────────────────────
🧠 Channel: https://t.iss.one/GithubRe
bradautomates/claude-video is making waves. Here's the full picture.

🔗 https://github.com/bradautomates/claude-video
📝 Give Claude the ability to watch any video. /watch downloads, extracts frames, transcribes, hands it all to Claude.
──────────────────────────────

Claude Video is a powerful tool that enables Claude to watch and analyze videos. With zero config, you can paste a URL or local path and ask a question, and Claude will fetch captions, download the video, extract frames, and provide a timestamped transcript.

The key features of Claude Video include:
- yt-dlp and ffmpeg installation on first run
- Caption support for most public videos
- Whisper API key for videos without captions
- Frame extraction and transcript analysis

Usage is simple: paste a URL or local path, ask a question, and Claude will provide an answer based on the video content. You can use Claude Video to:
- Analyze someone else's content
- Diagnose a bug from a video
- Summarize a video
- Cut the hype out of an update video
- Turn a playlist into notes

From a technical standpoint, Claude Video uses yt-dlp to check captions and download videos, and ffmpeg to extract frames. The script also handles frame deduplication to reduce token cost.

The target audience for Claude Video includes developers, content creators, and anyone who needs to analyze video content. Overall, Claude Video is a game-changer for anyone who wants to unlock the power of video analysis. Watch, analyze, and understand videos like never before!

──────────────────────────────
🧠 Channel: https://t.iss.one/GithubRe
1
🚀 Meet opengeos/GeoLibre: a gem from today's GitHub trending list.

🔗 https://github.com/opengeos/GeoLibre
📝 A lightweight, cloud-native GIS platform for visualizing, exploring, and analyzing geospatial data. It runs in the web browser, on the desktop, on mobile, and inside Jupyter notebooks.
──────────────────────────────

Meet GeoLibre, a free and open-source, lightweight, cloud-native GIS platform for visualizing, exploring, and analyzing geospatial data. It runs everywhere - in the web browser, on the desktop, on mobile, and inside Jupyter notebooks, while keeping your data local and private. Key features include 3D visualization, planetary basemaps, and a SQL workspace. Tauri v2, React, TypeScript, MapLibre GL JS, DuckDB-WASM Spatial, and deck.gl power the platform. Audience includes GIS professionals, researchers, and anyone working with geospatial data. With its extensive documentation and community-driven development, GeoLibre is an ideal choice for those seeking a flexible and customizable GIS solution. GeoLibre is perfect for anyone looking for a free and open-source GIS platform that can be used anywhere - your data, your way, anywhere.

──────────────────────────────
🧠 Channel: https://t.iss.one/GithubRe
Github Top Repositories
Photo
💡 moeru-ai/airi just hit the trending charts — here's why it matters.

🔗 https://github.com/moeru-ai/airi
📝 💖🧸 Self hosted, you-owned Grok Companion, a container of souls of waifu, cyber livings to bring them into our worlds, wishing to achieve Neuro-sama's altitude. Capable of realtime voice chat, Minecraft, Factorio playing. Web / macOS / Windows supported.
──────────────────────────────

AIRI: Your Cyber Living Companion

Imagine having a digital being that can chat, play games, and interact with you in various ways. Project AIRI aims to make this a reality, inspired by Neuro-sama, a virtual streamer. AIRI is an open-source project that lets you own your digital life, anywhere, anytime.

Key Features:
- Chat and roleplay with your digital companion
- Play games together
- Interact while watching videos or coding
- Personalize your digital being

Technical Highlights:
- Powered by modern large language models like ChatGPT and Claude
- Supports various platforms, including Windows, macOS, and Linux
- Available for mobile and web browsers

Usage:
- Download and install AIRI from the official website
- Follow the setup instructions to create your digital companion
- Start interacting with your AIRI companion

Audience:
- Anyone interested in AI-driven virtual companions
- Developers looking to contribute to an open-source project
- Fans of virtual streamers and digital humans

Get Started:
- Visit the AIRI website to learn more and download the application
- Join the Discord server for community support and updates

Takeaway: With AIRI, you can have your own digital companion, anytime, anywhere - own your digital life.

──────────────────────────────
🧠 Channel: https://t.iss.one/GithubRe