TypeScript 排行榜

The open-source, self-hosted alternative to NotebookLM.

FiftyOne Plugin for searching images by audio clip using ImageBind and Qdrant

Dsh-visual-plugin.Give your text-only model eyes: forward user images to any OpenAI-compatible vision model and see the results in a Web UI right panel

Claude Code hook toolkit that gives vision-blind models a text description of pasted/tool-produced images.

A slim, local-LLM-first AI coding assistant. TUI, Web UI, and desktop app. Runs air-gapped with Ollama, vLLM, or any OpenAI-compatible endpoint.

GPU orchestrator with vLLM sleep mode

An interactive CLI tool that leverages Ollama, ChatGPT, Gemini, Claude, Mistral and other AI.

The most capable Calibre MCP server — full read/write tools plus multilingual semantic search over your whole ebook library or a single book. For Claude & any MCP client.

A personal AI knowledge assistant powered by RAG, semantic search, and document understanding for context-aware answers.

Exploring what HN is really thinking

AI Legal Defense System with 805,000+ legal documents covering the entire US legal system. Features 31 specialized Slack commands, voice support, session memory, and smart caching. Built with Agent OS + Claude-Flow + Claude Code.

Local‑first MCP server for multi‑repository semantic code search with Qdrant and llama. Turns your entire workspace into private context for AI coding assistants like Claude Code, Codex, Cursor, Copilot, Antigravity and Windsurf.

Persistent local memory engine for OpenClaw — replaces default memory-system with a full context lifecycle: hybrid vector recall, automatic compaction, and domain-adaptive gating over LibraVDB

Experimental web console for real-time multimodal AI interactions (voice/video) using Gemini 2.0 Live API and NijiVoice. Next.js (TypeScript, Tailwind) frontend and FastAPI backend communicate over WebSocket for low-latency streaming.

A serverless invite-only AI-powered chat bot on Telegram.

TokenFlow is an enterprise-grade, token-aware load balancer and AI gateway for vLLM. It prevents GPU OOM crashes using Redis-backed admission control, semantic caching, and dynamic token routing. Built in TypeScript for extreme bare-metal performance.

Open-source, self-hosted LLM chat application, featuring local-first data storage and real-time streaming responses.

VS Code extension to connect to local LLM inference servers (Ollama, llama.cpp, LocalAI) via OpenAI API compatible endpoints.

Automated comic cataloging tool that identifies issues directly from cover images using a vision-language model, then cross-references results with the Grand Comics Database and the ComicVine API to generate structured, high-confidence collection data with minimal manual entry.