TypeScript 排行榜

OpenRouter skill for AI agents: model discovery, multimodal chat, tool calling, routing, and starter templates.

Madlab is an advanced AI development studio designed to streamline the process of dataset management, model training, and evaluation. It combines a robust Node.js/Express backend with a powerful Python-based training engine and a modern React frontend.

A web app using Vision Transformers for quick and accurate diagnosis of plant diseases, aiding effective treatment and plant health.

OpenCode plugin that gives coding agents persistent memory using local vector database

Mood is an AI-driven journaling web app designed to help users track their sentiments and moods over time. It offers advanced sentiment analysis and question-based similarity searches, making journaling an insightful and engaging experience.

A simple yet powerful semantic AI search engine⚡️

Implementation of Retrieval Augmented Generation model in typescript with Gemini LLM

Capability-aware vision + paste extension for the pi coding agent. Delegates image analysis only when the active model is text-only; passes through natively for multimodal models (zero delegation).

MCP server that gives text-only LLM coding agents vision — analyze images via any multimodal model (mimo, Claude, Gemini, OpenAI-compatible). Works with Claude Code, Codex, Kimi, opencode, PI.

Production-ready microservices framework for AI inference over RPC. It provides a Gateway for client requests, an Orchestrator that schedules work, a Registry for model metadata, Workers that run inference, and a full observability stack (Prometheus, Grafana, Loki, Jaeger) — all wired together with Docker Compose.

The ultimate desktop app for tracking, managing, and validating AI models from Hugging Face, Civitai, OpenModelDB & more.

AI powered Google Calendar events summarizer built using Next.js, Supabase and Google Gemini

This is a repository to let you know the implementation of a basic RAG pipeline using LangChain in Supabase Edge Functions.

Persistent memory and identity protocol for AI systems with evidence-aware recall and inspectable memory.

No longer maintained, please see the TypeScript client

CLI, MCP server, and TypeScript library that extracts text, layout, and page images from PDFs for AI agents — when extraction goes wrong, it says so per page and says what to do next.

Build your own local-first digital lifeform: an AI companion with memory, soul, multimodal perception, proactive dialogue, and auditable execution.

🤗📝 HuggingFace assisted Obsidian plugin

A modern platform for competitive programming.

A Cosmos API starter project to analyze files and chat with LLM.