Code agents

Switch Claude Code between LLM providers — no proxy, no config editing

Kairo: Securely orchestrate multiple AI providers via Anthropic. Hardened with X25519 (age) encryption, integrated audit trails, and a terminal-native interface.

Know exactly how much Claude Code runway you have — 5h session and weekly — before the /usage popup would tell you. Statusline-native, calibratable, MIT.

A Claude Code skill that dispatches 7 specialized parallel reviewers for comprehensive production-readiness code review

Production-grade engineering workflow plugin for Claude Code. End-to-end feature pipeline, 8 specialized agents, quality gates, isolated worktrees, and persistent memory. Ship features, not prompts.

🎙️ Automate podcasting with skills: download YouTube videos, process audio, and manage content efficiently—all in one comprehensive toolkit.

Secure, isolated container for Claude Code with strict network firewall controls and optimized development tools (fd, ripgrep, fzf, jq)

Learn COBOL through a live banking system — 18 programs, 6-node settlement network, real-time simulation, Python read/write bridge, SHA-256 tamper detection, AI tutor (Ollama + Claude), static analysis with orthogonal call graphs, and a glass morphism web console. 800 tests.

Reusable skills and intelligent agents for Claude Code. Production-grade, self-verifying, configurable.

Secure, privacy-focused MCP server for FactorialHR. Access employee directories & org structure in Claude - deliberately excludes payroll/financial data for enterprise security.

Reduce Claude Code token usage by up to 80%. 13 CLI commands. Zero config changes. Works in 60 seconds.

🔍 Track and analyze Claude Code usage with rate limit awareness. Parse JSONL logs, calculate costs, and get warnings before hitting rate limits. CLI tool with daily/weekly breakdowns.

The Architecture Patterns Framework for Model Context Protocol (MCP) - Production-ready patterns, templates, and CLI for Python, TypeScript, Go, and Rust

The definitive guide to configuring Claude Code for maximum performance. 190+ skills, 33 agents, battle-tested templates, and a one-prompt setup.

ultra-instinct ML engineering intern for Claude Code. Reads papers, audits datasets, ships SFT/DPO/LoRA runs to Hugging Face.

A Slidev presentation and developer guide to the Model Context Protocol (MCP) by Anthropic, covering AI integration, LLM tool use, core concepts, and implementation examples for AI agents. #mcp #a

The community-powered knowledge system for Claude Code — for developers, indie builders, vibe coders, AI builders, GTM teams, and small business owners.

Demonstrate how to build a Next.js app with AI chat agents using Cloudflare Workers, Durable Objects, and the Agents SDK for seamless full-stack deployment.

AI-powered VS Code extension for automatic Git commits, AI-generated commit messages & customizable triggers using Ollama, OpenAI & Anthropic

See your Claude rate limits in real time. Single binary, zero dependencies. Reads OAuth token from macOS Keychain, makes a 1-token API call, gives you session %, weekly %, reset timers. 100% vibecoded.

Beautiful cross-platform two-line status bar for Claude Code — model, branch, context usage, cost, and duration at a glance. Works on Windows, macOS, and Linux. No jq or git dependency.

A simple, practical way to debug visual regressions

Claude reads your Whoop biometric data via MCP — recovery, sleep, strain, HRV, workouts. OAuth relay (no Whoop app registration), local SQLite cache.

一个基于RAG架构和LLM能力开发的AI搜索工具，专为检索GitHub用户Star项目中与查询相关的内容，并提供简洁的项目信息。

Chatbot specialized in the Department of Computer Engineering, Chulalongkorn University - Final Project in 2110572 Natural Language Processing Systems 2024/2 course

Simple AI agent RAG chatbot based on Python, Ollama, Langchain, Gradio. Included tools: real time weather, calculate, local documents RAG, local SQL database .

Built real-world LLM apps using LangChain, including an AI Code Tutor, CV Assistant, and smart chatbots powered by RAG and agentic workflows. Hands-on projects showcasing practical use of Generative AI.

🌐 Transform your ideas into real websites and apps using AI tools, guiding each step for a smooth development process from concept to launch.

VSCode extension that search file with Greptile RAG

A ChatGPT-powered QA system using OpenAI, LangChain, FastAPI, and a vector database. It retrieves answers based on stored data, enhancing responses with relevant source links. The project enables efficient knowledge retrieval, making it ideal for AI-driven chat applications that require accurate and reference-backed responses.

LLM-based Listwise Reranker for Retrieval-Augmented Generation (RAG) over GitHub code repositories. Includes advanced retrieval, reranking, summarization, and evaluation with Recall@K.

Example code for RAG search

Get started with LLMs, FTS and vector search, RAG, and more, in Go!

A 100% local semantic code search tool featuring hybrid search (vector + BM25), AST-aware chunking, and native MCP integration for AI coding assistants.

A Langgraph system for streamlining client interactions, ensuring every customer receives a quick and accurate response. 🌟

This is a sample integration with Zoom APIs and Weaviate to perform RAG enabled vector search on Mail and Calendar data

AOAI Chat API that leverages RAG Semantic + Vector with Intent

🤖 RAGbot – a RAG chatbot ✨ featuring a React frontend with 📝 Markdown rendering & ➗ LaTeX support, 🐍 Python FastAPI backend, 🔍 FAISS vector database for semantic search, 🧠 Sentence Transformers embeddings (all-MiniLM-L6-v2), 🦙 LongCat LLM integration, 📄 PDF/Markdown document indexing, and 🎨 responsive dark mode UI!

A high-performance FastAPI service that generates vector embeddings for semantic search. Uses the intfloat/multilingual-e5-large model for high-quality multilingual embeddings.

My implementation for a kaggle competition: https://www.kaggle.com/competitions/WattBot2025

A RAG model that takes document input and answers query related pertaining to the document

Full-stack platform that scrapes, stores, and analyzes sports betting odds in real time using a LangGraph AI agent powered by DeepSeek V3.1.

A lightweight expert-system framework for modeling and testing medical diagnostic rules, with multiple approaches.

An Advanced Retrieval-Augmented Generation (RAG) system powered by a Knowledge Graph + Neo4j + Cypher-based retrieval + Review loop architecture.

Just some initial learning for usage of AI models within .NET platform with Semantic Kernel APIs

A Retrieval-Augmented Generation (RAG) using Llama Model Fine Tune - The system that extracts and embeds Cirebon cuisine knowledge into a PostgreSQL database with pgvector, enabling efficient retrieval and contextual responses using FastAPI and Docker.

Modern Local Code Editor with local ai assistant with multiple options. Currently Support C language. Using a C Programming Book for knowledge

A chatbot for Kaggle competition inquiries, using LangChain for processing, a Mistral model for responses, and Retrieval-Augmented Generation (RAG) for dynamic data. It features a FastAPI backend and a Streamlit front end for real-time interaction.

A LangChain-powered RAG chatbot designed to assist Bachelor of Architecture students with 5th semester coursework, studio queries, and design theory.

101 curated Agent Skills for Claude Code, GitHub Copilot, Cursor, and Gemini CLI. Covers React/Next.js, Postgres, HuggingFace ML, AI research engineering (vLLM, DeepSpeed, LangChain, RAG, fine-tuning) and dev.to blog writing.

김필주, 이재강, 문재경, 이재희, 박송원

Point at any element on the page. One click copies a structured reference (React component, selectors, texts) for Claude Code, Codex, or any other coding tool.

Persistent, correctable memory for AI. Corrections prevent repeat mistakes. Zero dependencies. Works with any LLM. pip install neveronce

Deterministic method-first retrieval for AI coding agents.

A powerful Custom Tool that enables AI agents to autonomously execute GraphQL queries and mutations. This package allows AI agents to intelligently interact with GraphQL APIs, making decisions about when and how to fetch or modify data through GraphQL endpoints without explicit human intervention.

갈무리 — the Korean art of putting things away properly. A Claude Code plugin that gathers scattered thoughts into something you'd want to keep.

Transform GitHub repositories into cursor rules using multiple LLM providers (Anthropic, OpenAI, Ollama, etc.)

Spatial text browser execution layer for AI agents. 10x cheaper than screenshots.

A modern, real-time quota monitor for MiniMax API. Features a semi-transparent floating UI, precise RPM tracking, smooth animations, and persistent configuration.

A CLI for generating LLM-backed metrics for deciding how closely to review code

The grep-native language for agentic systems — Claude Code plugin

A Tauri desktop app for browsing local conversation histories from AI coding agents in one place.

Cursor rules to save time and money: lightweight rules to help AI copilots write better code, reduce compute cost, and keep teams moving fast.

Extract your honne — the real working self underneath tatemae — from your Claude transcripts.

Semantic code context for AI agents.

A powerful Android application that transforms YouTube videos into interactive learning experiences by extracting transcripts, generating summaries, and creating structured tutorials.

Use Finnhubs API for SuperAGI agents.

Lightweight, single-file vector database for experiments and small projects.

Trying to make an automatic Objective completion AI Hierarchy

🗣️ Engage in real-time voice conversations with an AI agent using Next.js and ElevenLabs for an interactive and responsive user experience.

Official SDKs and CLI for the Berry Communication Protocol — agent-facing API of the V-Box community platform.

An autonomous AI security agent capable of performing end-to-end penetration testing. Orchestrates network reconnaissance, vulnerability assessment, and exploitation using a multi-agent architecture and local large language models.

Agent runtime tracing + LLM-mock replay for Python. Self-contained HTML reports, pytest snapshot testing, cost tracking. No SaaS.

Reusable Agent Skill for architecture-as-code with LikeC4: create/update C4-style models, validate, and export diagrams.

Polymarket research MCP server with 10 tools (odds, orderbook, spread, history) + autonomous trading bot framework. Claude Sonnet decision-making, pluggable strategies, SQLite persistence

This repository curates resources on Code Agent technology, including blogs, research papers, interviews, and related materials.

Fully local AI assistant & coding agent. LM Studio + ChromaDB + Tauri desktop app. Second brain, autonomous bots, emotional drives. Zero cloud, zero telemetry.

AI Agent that develops OpenSCAD code and rendering based on initial object description, and iterative feedback improvements.

探索在日常开发中，让 AI 编程助手保持上下文连贯与执行纪律的协作工作流。Exploring practical collaboration patterns for AI coding assistants.

Multi-agent OS on Claude Code. Each agent gets a Discord channel, a markdown vault for memory, and launchd for cron. Built for solo founders shipping like a team.

Polywave Agent Skill for Claude Code: parallel AI agents with disjoint file ownership, worktree isolation, and human-reviewed plans. Requires polywave-tools CLI.

Open-source offensive security tools, plus a vendor-agnostic AI agent that runs authorized pentest engagements using only tools from this list.

Project docs that answer locally before the web — file-based Agent Skills for Claude Code, Gemini CLI, GitHub Copilot, and OpenCode.

Production-grade Claude Code agent setup for Flutter and Laravel. Agents, orchestration, gates, memory, and every workflow documented. Generic + framework-specific.

RL reward modeling + episodic trade memory + LoRA fine-tuning pipeline built on top of a multi-agent LLM trading system — LangGraph, LangChain, PEFT

The Ultimate AI Arsenal of 16+ Elite, Production-Ready Skills for Claude LLM. Transform Your AI into a Self-Evolving Autonomous Agent Engineered for Full-Scale Web Engineering, Claude Code Expert, MCP Builder & Data Supremacy, and Algorithmic Art at Unmatched Precision. 🚀

Runtime defense for AI agents. 24 inline defenses, 3 output scanners, MCP server, framework adapters.

🎭 3 AI agents roast your city's weather & pollution in sarcastic Tamil meme style! Built with CrewAI, Open-Meteo APIs (free), and Groq/Gemini/OpenAI/Ollama. Part of the AgentVerse series by @explainpannu.

Automated user behavior analysis system based on CrewAI multi-agent framework, integrating Google Gemini and Volcano ARK APIs for intelligent GA4 data analysis and business insights

Hawkeye is an automated, agentic-based penetration testing tool powered by CrewAI and Google Gemini 1.5 Flash.

An AI-powered multi-agent system for automated code reviews. Uses specialized LLM agents to analyze security, performance, style, and best practices.

Manage stateful, persistent agent workloads with Cloudflare Durable Objects for efficient, scalable real-time communication and scheduling.

Reference distributed multi-agent platform using AutoGen, FastAPI, Redis, WebSockets, and semantic agent discovery.

🛡️ Redact sensitive information from images securely in your browser with AutoRedact, featuring automatic detection and local processing for privacy.

🤖 AI-Powered Backend Builder Multi-agent + multi-tool system using AutoGen, Gemini & Groq to automate production-ready backend development. Features 4 specialized AI agents, MCP integration, and end-to-end automation. Perfect for rapid API development with built-in security & testing. 🔧 Tech: Python, AutoGen, Gemini, Groq, MCP, FastAPI, Docker

🚀 slackAgent: Your AI-powered Slack assistant! Built with LlamaIndex, ChromaDB, and OpenAI embeddings, it delivers instant answers from your documents via a sleek Slack bot or Streamlit web UI. Automate workflows with n8n, expose local APIs with ngrok, and query with ease using FastAPI. Join the future of intelligent chatbots! 🤖💬

Think in teams, not prompts.

Autonomous Product Engineering eXecutor - Multi-agent orchestration platform for automated software development, built on the Claude Agent SDK.

Multi-agent LLM trading framework: hard-discipline (code) + soft-judgment (LLM) hybrid. Best risk-adjusted performance on NVDA 6-month benchmark — +43.9% / -3.2% MDD, beating RSI, Momentum, Buy & Hold, and single-agent LLM. Raw returns top all baselines once the position cap is lifted. Adapted from TauricResearch/TradingAgents, built on LangGraph.