xxxily/hello-ai

It's not AI that takes away your job, but the people who master the use of AI tools. The most deadly attack is a dimension-reducing strike: destroying you has nothing to do with you - from "The Three-Body Problem". 中文说明： 抢走你工作的不是AI，而是掌握使用AI工具的人。 降维打击最为致命：毁灭你，与你何干《三体》

What it solves

Hello-AI addresses the "information overload" developers face when searching for high-quality open-source AI projects on GitHub. Instead of relying on manually curated lists that quickly become outdated, it provides an automated, AI-driven system to discover and organize the most relevant AI resources.

How it works

The project uses a pipeline of automated scripts and Large Language Models (LLMs) to maintain its directory:

  1. Discovery: A crawler mines GitHub topics and searches for repositories with a minimum star threshold, adding new finds to a pending queue.
  2. Evaluation: An AI agent processes the queue in batches, using an LLM to analyze the project, assign categories/tags, generate summaries, and rate the quality. Poor quality projects are filtered out.
  3. Storage: Validated projects are saved into a core JSON database.
  4. Rendering: A VitePress-based frontend dynamically generates navigation and Markdown pages based on the database, automatically purging stale projects based on a recency threshold.

Who it’s for

  • Developers looking for the latest and most active open-source AI tools and frameworks.
  • Users who want a curated, auto-updating map of the AI landscape without manual research.

Highlights

  • Autonomous Maintenance: Uses AI agents for 24/7 discovery and quality assessment.
  • Dynamic Categorization: Categories are not hard-coded; the AI routes projects to categories based on current database trends.
  • Automated Lifecycle: A complete closed-loop from GitHub crawling to static site generation.
  • Flexible LLM Integration: Supports various OpenAI-compatible providers including OpenAI, MiniMax, DeepSeek, and local setups via Ollama.

Related

  • Project
    AmintaCCCP/GithubStarsManager

    An AI-powered manager for GitHub stars that uses semantic search, AI categorization, and release tracking to turn a pile of starred repositories into a structured library.

  • Project
    openkursar/hello-halo

    An AI workstation that enables autonomous AI agents to operate a local browser, terminal, and knowledge base to automate complex workflows 24/7.

  • Project
    AIDotNet/OpenDeepWiki

    An AI-driven knowledge base system that converts Git repositories and local directories into structured documentation, searchable wikis, and MCP-enabled chat assistants.

  • Project
    tingaicompass/AI-Compass

    A comprehensive AI learning ecosystem that organizes resources, tutorials, and engineering examples into a structured path from basic theory to frontier applications.

  • Project
    Intrect-io/OpenSwarm

    An autonomous AI agent orchestrator that manages a pipeline of AI code workers to resolve issues from Linear or local trackers and manage pull requests.