1. GoogleCloudPlatform/generative-ai Not new today
Sample code and notebooks for Generative AI on Google Cloud, with Gemini on Vertex AI
First seen: March 08, 2026 | Streak: 2d
Analysis
The Google Cloud Generative AI repository serves as a comprehensive educational hub for developers looking to integrate Google’s advanced AI models, such as Gemini, Imagen, and Chirp, into their applications. Technically, it provides a curated collection of notebooks, code samples, and end-to-end architecture patterns that leverage the Vertex AI platform. By utilizing these resources, users can implement diverse workflows ranging from function calling and multi-modal generation to complex agentic systems and custom model fine-tuning.
This project is an essential resource for software engineers, data scientists, and cloud architects aiming to build and scale generative AI solutions on Google Cloud. It is highly trending because it provides immediate access to the latest foundational model updates—such as Gemini 3.1 Pro—while offering production-ready templates that address real-world challenges like observability, deployment, and evaluation. By consolidating high-quality, practical examples into a single repository, it significantly accelerates the development lifecycle for professionals transitioning from prototyping to enterprise-grade AI production.
2. 666ghj/MiroFish Not new today
A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎，预测万物
First seen: March 08, 2026 | Streak: 2d
Analysis
MiroFish is a swarm intelligence engine designed to simulate and predict complex real-world scenarios by creating high-fidelity digital environments populated by autonomous agents. Technically, the platform leverages GraphRAG for memory construction, entity relationship extraction, and multi-agent simulation to analyze input seeds such as news, policy drafts, or literature. By dynamically injecting variables into these "digital sandboxes," the system allows users to observe social evolution and emergent behaviors to generate detailed predictive reports and interactive simulations.
This project is primarily aimed at decision-makers requiring low-risk policy pre-simulation, as well as creative users looking to explore narrative outcomes or hypothetical scenarios. It is gaining traction because it bridges the gap between abstract data analysis and concrete, visual interaction, turning static information into a dynamic "God’s-eye view" of potential futures. By democratizing access to complex multi-agent simulations, MiroFish offers a versatile, "playful" yet powerful tool for both professional strategic planning and personal intellectual curiosity.
3. shadcn-ui/ui Not new today
A set of beautifully-designed, accessible components and a code distribution platform. Works with your favorite frameworks. Open Source. Open Code.
First seen: March 08, 2026 | Streak: 2d
Analysis
shadcn/ui is a collection of re-usable, accessible, and highly customizable UI components designed to be copied directly into a project’s codebase. Unlike traditional component libraries distributed as npm packages, it utilizes a CLI tool to provide the source code for each component, allowing developers to own and modify the implementation according to their specific needs. It is built on top of robust foundations like Radix UI for accessibility and Tailwind CSS for styling, ensuring that components are both functionally sound and visually cohesive.
This project is ideal for developers and teams who want to build high-quality, bespoke design systems without the constraints of rigid, pre-compiled library dependencies. It has become a dominant trend in the frontend ecosystem because it solves the "black box" problem of traditional UI kits, granting users total control over their markup and styling. By prioritizing developer experience and transparency, shadcn/ui enables rapid prototyping while maintaining the flexibility required for long-term project scalability.
4. openclaw/openclaw Not new today
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
First seen: February 02, 2026 | Streak: 1d
Analysis
OpenClaw is a personal, local-first AI assistant platform designed to unify communication across a vast array of messaging services, including WhatsApp, Discord, Slack, and Signal. Technically, it functions as a central Gateway that acts as a control plane for agents, utilizing a robust CLI wizard for onboarding and a WebSocket-based architecture to manage multi-channel sessions and tool integration. It supports advanced features such as voice wake-word activation, a live visual "Canvas" for agent interaction, and cross-device connectivity via companion apps for macOS, iOS, and Android.
This project is ideal for power users and developers seeking a centralized, self-hosted AI experience that eliminates the need to switch between individual messaging app interfaces. It is currently trending because it offers a highly customizable, privacy-conscious alternative to proprietary AI platforms, allowing users to consolidate their automation, tools, and communication in one private hub. By bridging the gap between disparate messaging channels and powerful LLM capabilities, OpenClaw provides a versatile toolkit for those who want their AI assistant to be truly integrated into their daily digital workflow.
5. toeverything/AFFiNE Not new today
There can be more than Notion and Miro. AFFiNE(pronounced [ə‘fain]) is a next-gen knowledge base that brings planning, sorting and creating all together. Privacy first, open-source, customizable and ready to use.
First seen: March 08, 2026 | Streak: 2d
Analysis
AFFiNE is an open-source, all-in-one workspace designed as a privacy-focused alternative to tools like Notion and Miro. By merging documentation, whiteboarding, and project management into a single "edgeless" canvas, it allows users to organize various media and data types through a modular, block-based architecture. Technically, the project prioritizes a local-first approach using CRDTs (via Yjs and y-octo) to ensure real-time collaboration and data ownership, while utilizing a Rust-based engine called OctoBase for high-performance database management.
This project is ideal for creative professionals, developers, and teams who prioritize data privacy and seek a highly customizable, unified operating system for their knowledge base. It is gaining significant traction because it addresses the growing demand for self-hostable, open-source productivity software that avoids the limitations of closed-ecosystem alternatives. By integrating AI-assisted workflows and providing a developer-friendly, extensible environment, AFFiNE empowers users to build their own bespoke productivity tools without sacrificing control over their information.
6. Ed1s0nZ/CyberStrikeAI Not new today
CyberStrikeAI is an AI-native security testing platform built in Go. It integrates 100+ security tools, an intelligent orchestration engine, role-based testing with predefined security roles, a skills system with specialized testing skills, and comprehensive lifecycle management capabilities.
First seen: March 07, 2026 | Streak: 1d
Analysis
CyberStrikeAI is an AI-native security testing platform built in Go that orchestrates over 100 industry-standard security tools to automate the entire vulnerability lifecycle. By integrating natively with the Model Context Protocol (MCP) and supporting various LLM backends like GPT and DeepSeek, the platform transforms conversational commands into complex attack chains, knowledge retrieval, and actionable security reporting. It features a sophisticated modular architecture that includes role-based testing, YAML-based tool extensions, and a persistent SQLite backend to ensure that security workflows are both auditable and highly repeatable.
Security professionals, penetration testers, and CTF enthusiasts would benefit significantly from this project, as it effectively bridges the gap between manual security research and automated AI agent workflows. It is trending because it moves beyond simple chatbot interfaces by providing a structured, team-oriented environment that simplifies tool management, audit logging, and vulnerability tracking. By reducing the friction involved in chaining together disparate security utilities, CyberStrikeAI offers a powerful, collaborative framework that significantly enhances efficiency for modern security teams.
Bash is all you need - A nano Claude Code–like agent, built from 0 to 1
First seen: March 09, 2026 | Streak: 1d
Analysis
The `learn-claude-code` repository provides a comprehensive educational framework for building an autonomous AI coding agent from the ground up, mirroring the functionality of Claude Code. Through 12 progressive sessions, it demonstrates how to build an agent loop that integrates tool usage, task planning, sub-agent delegation, and environment isolation. Technically, it relies on a minimalist "Agent Pattern" where an LLM orchestrates tool calls via a standard loop, layering on sophisticated mechanisms like background processing, task graphs, and persistent mailboxes without complicating the core execution logic.
This project is an ideal resource for software engineers and AI developers who want to demystify agentic workflows and move beyond simple chat-based interactions. It is currently trending because it offers a practical, "code-first" approach to understanding agent internals, providing mental models and clean reference implementations that are far more accessible than production-grade frameworks. By deconstructing complex concepts like worktree isolation and multi-agent coordination, it serves as a foundational guide for those looking to build their own custom CLI agents or embed agentic capabilities into their own software products.
8. openai/skills Not new today
Skills Catalog for Codex
First seen: February 04, 2026 | Streak: 3d
Analysis
The `openai/skills` repository serves as a centralized catalog for "Agent Skills," which are standardized sets of instructions, scripts, and resources designed to enhance the capabilities of AI agents within the Codex ecosystem. By packaging specific task-oriented functionalities, these skills allow developers to create repeatable workflows that can be seamlessly integrated across different environments. Technically, the system utilizes a command-line interface, `$skill-installer`, to fetch and implement curated or experimental skills directly from the repository, requiring only a simple restart of Codex to activate the new logic.
This project primarily benefits software engineers and AI developers who seek to streamline complex automation tasks and improve the modularity of their AI-driven applications. It is trending because it addresses the growing demand for an open standard in agentic workflows, enabling teams to share and adopt standardized toolsets for diverse technical requirements. By fostering a collaborative ecosystem where custom functionalities can be easily distributed and reused, this repository significantly lowers the barrier to deploying specialized AI agents in professional development environments.
9. virattt/ai-hedge-fund Not new today
An AI Hedge Fund Team
First seen: March 07, 2026 | Streak: 3d
Analysis
The AI Hedge Fund project is an educational proof-of-concept platform that simulates an AI-powered investment firm by utilizing a multi-agent system. It integrates specialized "investor agents," modeled after legendary figures like Warren Buffett and Michael Burry, alongside dedicated functional agents that perform sentiment analysis, valuation, and technical analysis. Technically, the system functions by aggregating financial data and using LLMs to synthesize these diverse perspectives into cohesive trading signals, all managed by a centralized Portfolio Manager and Risk Manager.
This project is primarily aimed at developers, finance enthusiasts, and students who want to explore the intersection of generative AI and quantitative finance. It is currently trending because it provides a highly accessible, modular framework for experimenting with agentic workflows in a domain as complex as market analysis. By offering both a command-line interface and a web application, the project democratizes complex investment modeling while serving as a valuable learning tool for those interested in autonomous AI decision-making.
Grab your own sweet-looking '.is-a.dev' subdomain.
First seen: March 09, 2026 | Streak: 1d
Analysis
The `is-a-dev/register` repository provides a community-driven service that allows developers to register personalized `.is-a.dev` subdomains for their projects. Technically, the project functions through a GitHub-based workflow where users fork the repository and submit a pull request containing their desired DNS record configuration. Once the maintainers review and merge the request, the subdomains are automatically propagated, supported by infrastructure sponsored by Cloudflare's Project Alexandria.
This project is particularly beneficial for developers, students, and hobbyists looking to enhance their professional branding with a clean, tech-centric URL without the recurring costs of traditional domain registration. It has gained significant traction because it lowers the barrier to entry for personal portfolio sites and side projects by leveraging familiar version control workflows for DNS management. By fostering an open-source registration process, the repository offers a streamlined, accessible alternative to expensive commercial domain registrars.