GitHub Picks

A self-hostable personal agent workstation on AgentScope with multi-channel chat, local LLM execution, and modular skills and memory for everyday automation.

A self-hosted web-to-RSS feed generator that extracts updates from webpages and normalizes them into RSS/Atom for monitoring, archiving, and reader integrations.

A self-hostable RSS/Atom generator that turns dynamic websites and platform content into feeds via route-based rules, with Docker-first deployment and an extensible rule library.

A single-route App Router starter that runs a Next.js-compatible API surface via vinext on top of Vite, designed for edge deployment on Cloudflare Workers.

An ACP skills repo for coding agents: package dataset, training, evaluation, and paper-publishing workflows as installable skill folders with SKILL.md and scripts.

An offline multi-party file vault: encrypt with age, split the key with Shamir threshold secret sharing, and recover locally in any browser bundle.

Turn an ESP32-S3 into a personal AI assistant on a $5-class chip: no Linux, no server, with local-first memory and Telegram chat.

A self-hostable visual workflow automation platform with custom code nodes and native AI capabilities for reusable integrations and orchestration.

A zero-server code intelligence engine that builds a local code knowledge graph, exposes MCP tools for search/context/impact, and plugs into major AI coding assistants.

A TypeScript workflow toolkit for Claude Code and Cursor: auto-inject specs into every session and run parallel worktrees for controlled multi-task development.

Turn paper method sections into fully editable SVG figures with iterative layout and style refinement for publication-ready diagrams.

A modern TypeScript AI framework from the Gatsby team, delivering native workflows, RAG, and evals for production agents.

An Electron-based desktop client for visualizing and managing AI agent skills, using symlinks to maintain a unified SKILL.md source across 21 major AI coding assistants.

The first native multi-agent orchestration plugin for Claude Code. Awaken 30 specialized AI agents with a single command for highly autonomous concurrent codebase refactoring.

The open-source Agentic Workspace blending a free-form canvas, multi-threaded AI chat, and RAG into an intelligent hub for creators.

A community-driven index of proven OpenClaw use cases, offering real automation configs to unlock your local AI agent.

A POSIX-compliant bash script to manage and seamlessly switch between multiple active Node.js versions on a single machine.

A living system-design handbook for interviews: core tradeoffs, common questions with sample solutions, plus memory decks for long-term retention.

A team-ready platform for LLM apps and agentic workflows: visual orchestration, RAG datasets, model routing, and observability, self-hostable with Docker and API-first.

A language-first directory of project-based tutorials that helps you build real apps from scratch for practice, onboarding, and portfolios.

A community-built directory of free public APIs, categorized by domain with Auth/HTTPS/CORS signals for fast integration scouting.

A runnable GenAI course repo: 21 lessons on prompting, RAG, function calling, agents, security, and fine-tuning, with Python/TypeScript examples.

An MCP-first multi-agent collaboration workspace that unifies agent team design, knowledge bases, and tool calling into reusable workflows.

A domain-first index of high-quality “build from scratch” guides across Git, databases, OSes, compilers, and networking.