GitHub agents

Command Line tool for OpenAI's ChatGPT service

Community MCP server that exposes Coroot incidents and health summaries as read-only tools for AI assistants (not an official Coroot product).

🌊 VibeCode: The AI development terminal powered by Claude 3.5 & GPT-4. Just type what you want to build in plain English → get production-ready code instantly. 10x faster development. Zero configuration. ⚡ Try it: npm install -g vibecode

NanoClaw, ported to the GitHub Copilot SDK. Same containers, channels, skills — any Copilot model.

A modern, feature-rich SSH terminal application built with Electron and React. KEMENT combines traditional SSH functionality with AI-powered assistance to enhance productivity and streamline remote server management.

🤖 AI-powered chat specializing in explaining, refactoring, debugging and converting short code snippets.

When your complex requests confuse AI This tool transforms vague, multi-goal prompts (e.g., "create a study plan that balances learning, exercise, and hobbies") into unambiguous "action charters" for AI. It detects conflicting objectives in your instructions, clarifies priorities, and ensures AI outputs stay locked on your true intent.

MCP server for VOICEPEAK text-to-speech synthesis

AI-powered assistant that listens to your calls and provides intelligent, knowledge-based answers — completely invisible to screen sharing.

Autonomous AI Agent for Windows - Your intelligent, always-on AI assistant with screen understanding and task automation.

Deploy OpenClaw (open-source AI assistant) on Azure with Telegram support — Bicep IaC, one-command setup, ~$25/month

Turn a YouTube URL or a thinker's name into a two-voice podcast — every quote checked verbatim, rendered locally by Kokoro TTS.

Multi-backend AI CLI & OpenAI-compatible API server (Claude, Codex, Gemini)

Claude Code session handoff skill - preserve context across sessions with failed approaches tracking, handoff chain, and quality validation

A collection of self-improving Claude Code components. The /learn command extracts patterns from docs and code to permanently enhance your skills.

Python wrapper for the OpenRouter API

Consistent developer experience for Claude Code. Sprint tracking, config scoring, auto-fix, and behavior verification out of the box.

Every front-end GUI client for ChatGPT, Claude, and other LLMs. With repository stars⭐ and forks🍴

A scriptable and powerful UI-Chat-Application for chatting with most Gen-AI LLMs

Complete AI-assisted scientific research workflow — literature review, interactive citations, article writing, LaTeX export and presentation. Powered by Claude Code inside VS Code.

Simple, ergonomic, async, Rust client for Anthropic’s Messages API

Type-safe prompt management with automatic optimization for LLMs. DSPy-style optimization, A/B testing, multimodal support, and more.

An all-in-one adapter for talking to different LLMs. Supports switching between chat models

Generate Anthropic Claude tool use schemas based on type annotations and function docstrings.

MCP server for human-in-the-loop surveys, A/B preference tests, ratings, and rankings. Get real human feedback inside Claude Code, Claude Desktop, Cursor, Windsurf, and any MCP client — powered by Datapoint AI.

Use a LLM (local served, Anthropic, OpenAI) to chat, discuss/summarize your documents, youtube videos, and so on.

Desktop widget for tracking OpenAI, Anthropic, and OpenRouter usage, quotas, and rate limits.

AI-powered PR reviews using your own LLM API key (Anthropic, OpenAI, Gemini)

🤖 AI-powered Microsoft Word Add-in — Integrates Claude AI for smart writing, document analysis, Track Changes, and specialized legal tools.

🗞️ Daily curated AI news from Anthropic, OpenAI, Google Gemini & GitHub — trilingual (中文/日本語/EN), dark/light mode, zero dependencies

Production-ready guides for building AI agents with Claude Agent SDK in Python and TypeScript - complete coverage of official docs plus advanced patterns (subagents, hooks, batch processing)

Open-source toolkit for working with LLM APIs. invalid token opencode Provides a unified interface for integrating, testing, and automating workflows with models like Claude, GPT, and others. Supports streaming, async execution, and multiple providers. Built for developers who want flexible, scalable, and vendor-independent AI integrations.

Knowledge engine for AI agents — persistent memory, vault, and brain that learns

A Python implementation of the VETTING (Verification and Evaluation Tool for Targeting Invalid Narrative Generation) framework for LLM safety and educational applications.

Anthropic prompt generator. Giving a task description string (e.g. Write me an email) and optional prompt variable string list (e.g. [COMPANY_NAME]. If empty Claude will pick variables, it'd generate the prompt template including possible prompt variables (e.g. <recipient> {$RECIPIENT} </recipient>). Python 3.10+/poetry/VSCode/.env/osx

Community Plugins for Firebase Genkit.

Book Management App with Spring, Java, Angular, PostgreSQL & Flyway

An OpenAI/Gemini/Anthropic API helper in C

AI pretends to be paper/textbook author, you can ask it questions about the paper as a whole, specific parts of it right in the PDF viewing app (e.g. Apple Preview) using annotations and see the replies there.

Keep you informed about your OpenAI/Anthropic API usage costs

Frontend to OpenAI and Anthropic's LLM APIs with Markdown formatting. Focus on simplicity, extensibility and customizability.

A product knowledge base powered by Pinecone API and Anthropic AI Copilot

HumanEval 模型评估工具

A simple, elegant Python library and Mini SDK for AI models with powerful features. Built for developers who want to integrate AI into their projects without dealing with complex API setup. Supports Google Gemini, OpenAI, Anthropic, and any custom provider via the Adapter Pattern.

A reverse proxy for pools of local/remote AI models.

Unified AI API proxy server - GitHub Copilot, OpenCode Zen, Google Antigravity, AWS Kiro, Factory AI Droids

Streaming PII proxy for LLM chat. Pluggable detector, per-session vault, and cryptographic provenance-anchored reversal (PASP) that closes the false-attribution attack every other streaming library silently has.

Interactive study of Claude Code's architecture — bootstrap flow, tool system, 44 hidden features, subsystems map, and code archaeology from the March 2026 source leak

Flooky is a privacy-focused AI assistant designed for natural, intelligent conversations. Powered by Anthropic, it offers context-aware responses, memory features, and a clean, user-friendly interface.

Patina - High-performance terminal client for Claude API

Slash commands for Claude Code that analyze, validate, and optimize your AI agents. Rate across 8 pillars, find issues, auto-fix problems.

A sophisticated multi-model AI agent framework with intelligent task routing, extensible plugin architecture, and advanced resource optimization.

This is a mock service for multiple AI services.

🤖 Production-grade autonomous customer support agent using Claude AI & MCP achieving 100% first-contact resolution. Built for Claude Architect Certification (Scenario 1) - demonstrates agentic architecture, tool design, and reliability patterns.

Your personal open-source talent agent — an AI pipeline that analyzes your GitHub history and recommends active OSS projects where your skills fit best, with a concrete first contribution for each.

A macOS-first CLI for managing Anthropic/Claude Code environment profiles with one-command switching, Keychain-backed token storage, and zero-friction setup.

Use Claude (Anthropic) as your Odoo 19 AI provider — agents, tool calling, RAG, and web search.

Slack-ClaudeCode Vanguard

Skim: A MCP server for Claude Code — skim large outputs, return only schema. Save context, save tokens.

AWS Summit 2024 Jakarta --- ObservabilityAI: Memanfaatkan Amazon Bedrock Untuk Memantau Kinerja RESTful API Golang

A model-agnostic Message Control Protocol (MCP) server that enables seamless integration with various Large Language Models (LLMs) like GPT, DeepSeek, Claude, and more.

Real-time Claude.ai/Codex subscription awareness for AI coding assistants. Surfaces your live Session 5hr and Weekly 7day utilization, forecasts when you'll hit the limit, gates expensive operations before they run, and measures real per-task cost — all without leaving your machine.

Self-hosted, OpenAI-compatible LLM gateway in a single Go binary. Routes to OpenAI, Anthropic, Gemini, and local Ollama with failover, two-tier caching (exact + semantic), per-key rate limits, and per-customer spend caps.

Personally curated and maintained collection of Claude Code plugins

Persistent memory for Claude Code Channels via Telegram, powered by Supabase and MCP.

A RAG-based framework for constructing scientific knowledge graphs.

RAG Q&A system

🧠 AI Memory Proxy: LLM with persistent user memory using PostgreSQL + pgvector. AI-driven fact extraction, semantic search, single API call optimization.

This is a comprehensive large model service platform designed to facilitate rapid deployment and application of large model services in small and medium-sized enterprises. The platform mainly includes large model service and application modules, data management modules, and development documentation modules.

Structured Turkish Constitution dataset in Markdown and JSON for search, legaltech, NLP, and RAG applications.

旋转机械故障诊断AI 智能体

Use LLM/AI agent for Web scraping (collection data) and analysis data with deep research

A self deployable LLM application with our innovational IC framework (a RAG method)

This is standard mini–RAG Application from scratch

An AI-driven Hacker News aggregator providing automated Chinese translations, structured summaries, and RAG-based Q&A to help users efficiently access technical insights.

Universal document-to-markdown and section splitter for HTML, URLs, and PDFs.

DSCode is a free, comprehensive learning platform for mastering Data Science, AI, and Machine Learning. With 445+ curated problems across 16 topics including Python, ML, Deep Learning, NLP, Computer Vision, Gen AI, RAG, and AI Agents, DSCode helps you build job-ready skills through hands-on practice.

One-click conversion of arXiv papers to Markdown with perfect LaTeX formula preservation

Browser extension that stores your browsing history in ChromaDB and retrieves URLs with natural language descriptions. Powered by LLMs, RAG, and vector embeddings.

A modular, multi-model AI assistant UI built on .NET 9, featuring RAG, extensible tools, and deep code + database knowledge through semantic search.

A comprehensive Pre-RAG prototype dashboard for document parsing, multi-method chunking, vector embedding generation, and hybrid search exploration. Built with React and powered by in-browser ML models.

Chat with your PDFs using local AI models Process PDF documents and have interactive conversations with their content. Everything runs locally - no data leaves your machine.

Demonstrates the core aspects of RAG, built using NextJS and Supabase

Open source AI inference server with Model Marketplace, Document RAG, and OpenAI-compatible API

LLM App to demystify and summarize Terms and Conditions agreements

AI Agent SDK designed for Go developers

ShopGenie is an AI powered shopping assistant. It harnesses the power of LLM and RAG for finding a product easier than ever. This repository is the main application for the project.

Java ONNX Embedding & Retrieval-Augmented Generation (RAG) Engine

Framework for Retrieval-Augmented Generation (RAG)

Exploring Fine-Tuning for In-Context Retrieval and Efficient KV-Caching in Long-Context Language Models

Complete open-source data platform with Airbyte, Dremio, dbt, and Apache Superset - Documented in 18 languages

RAG-Based Research Assistant

Dynamic Few-Shot Prompting is a Python package that dynamically selects N samples that are contextually close to the user's task or query from a knowledge base (similar to RAG) to include in the prompt.

AI-powered debate assistant using Groq, Gemini APIs, and SearchXNG for intelligent argumentation. Built with RAG (Retrieval-Augmented Generation) architecture to source academic research and data. Features real-time web search integration and upcoming Model UN debate simulation mode.

A CLI tool for personal RAG that retrieves data from Notion, Obsidian, Apple Notes, etc., stored in Qdrant and exposed as an MCP server.

EntRAG - Enterprise RAG Benchmark

Local RAG system with realtime auto ingestion of documents and notes and exposed via MCP to be used with Local or Cloud based LLMs