Real-time transcription using faster-whisper

All parts of Claude Code's system prompt, 16 builtin tool descriptions, sub agent prompts (Plan/Explore/Task), utility prompts (CLAUDE.md, compact, statusline, magic docs, WebFetch, Bash cmd, secur…

A comprehensive observability solution for monitoring Claude Code usage, performance, and costs.

一个类似于Notebook LM，以用户自有知识为中心的 AI 工作空间，帮助你思考、研究与写作。更方便，更轻量，更懂你！

Native and Compact Structured Latents for 3D Generation

Demystify AI agents by building them yourself. Local LLMs, no black boxes, real understanding of function calling, memory, and ReAct patterns.

An open source implementation of an AI agent that generates slides in google slides

An Automatic Prompt Optimization Framework for Large Language Models

🎨 Ready-to-use DeepSeek-OCR Web UI | Modern Interface | 7 Recognition Modes | Batch Processing | Real-time Logging | Fully Responsive

The memory-first coding agent

The most customisable and low-latency cross platform/shell prompt renderer

minion's implementation of Claude Code

👷‍♂️Minion is Agent's Brain. Minion is designed to execute any type of queries, offering a variety of features that demonstrate its flexibility and intelligence.

OSINT Framework

A high-performance API server that provides OpenAI-compatible endpoints for MLX models. Developed using Python and powered by the FastAPI framework, it provides an efficient, scalable, and user-fri…

A manager for AI coding agents that works with Claude Code, Cursor, Gemini, Codex, and Qwen.

Start a server from the MLX library.

FastMLX is a high performance production ready API to host MLX models.

🌍  Spec-compliant and production ready JavaScript GraphQL server that lets you develop in a schema-first way. Built for Express, Connect, Hapi, Koa, and more.

Build mcp server using Claude to query a GrapgQL database

Professional Claude Code skills marketplace featuring production-ready skills for enhanced development workflows.

"Paper2Slides: From Paper to Presentation in One Click"

The Sphinx documentation generator

The official source for MDN Web Docs content. Home to over 14,000 pages of documentation about HTML, CSS, JS, HTTP, Web APIs, and more.

Adding guardrails to large language models.

The only production-ready open-source AI guardrails platform for enterprise AI applications with user-defined scanners and custom model training support.

A lightweight integration tool connecting Dify’s low-code platform with OpenAI’s APIs for seamless AI-powered solutions.

OpenAI-compatible HTTP LLM proxy / gateway for multi-provider inference (Google, Anthropic, OpenAI, PyTorch). Lightweight, extensible Python/FastAPI—use as library or standalone service.