Code agents

A Claude Code skill for crafting portfolio-ready design case studies. Structured template, tone guide, and slide layout for UX, product, and design portfolios.

Opinionated Claude Code skills for project bootstrap, persistent session memory, and multi-model code review (Claude + Codex).

🤖 Assistant d'écriture alimenté par l'IA - Corrigez, traduisez et améliorez vos textes instantanément avec Gemini, Claude et GPT. Simple, rapide et respectueux de votre vie privée.

LLM API spend dashboard for Anthropic, OpenAI, and Gemini. Built at Vela. MIT-licensed.

Claude Code plugins — MCP servers, skills, and agents for AI-assisted development

Claude Code skill that invisibly rates every external resource (WebFetch / WebSearch / MCP / curl) via PostToolUse hooks. Two rater backends: Anthropic API key or claude.ai subscription via 'claude -p'.

A complete, weekly-operable system covering research findings, funnel design, networking workflows, application protocols, AI automation, templates, and a 30-day launch plan. No spam. No fake experience. High-conversion by design.

Translate PowerPoint files across 7 languages while keeping every font, color, and layout exactly as designed.

This GitHub Action enables seamless integration of Claude Code into your workflows, allowing you to execute commands easily. Enhance your projects with powerful tools and streamline your development process! 🛠️🚀

Rustlings-style AI engineering bootcamp for senior devs — 90 progressive exercises (6 tracks × 3 providers) with tests against real APIs. Pick Claude, GPT, or Gemini. TypeScript · Bun · Bilingual EN/ES.

🪂 Latency-aware model cascade for agentic LLM workflows. Auto-switches to a faster model when yours is slow.

Test Claude Projects without copy-pasting. Local workbench for prompt engineering, agent testing, and workflow iteration. Direct Claude.ai access via cookie auth, 20+ prompt templates, web fetch/search tools, file uploads. Stop switching tabs to test your prompts.

Sweep your ~/.claude/skills graveyard. Scans installed skills, MCP servers, and sub-agents, cross-references session logs, and shows what's actually used.

Local-first job hunt workflow on Claude Code: 4-version LaTeX CV + AI cover letters + Claude in Chrome auto-apply. No SaaS, no subscriptions, no black-box agents.

A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows | Claude Skills 精选列表：定制 Claude AI 工作流的技能、资源和工具合集

LLM Choose your own Adventure API using Rust & Htmx (HuggingFace models or Anthropic)

🛠️ Manage AI capabilities with CraftDesk, a streamlined package manager for installing and versioning Claude Code skills and development tools.

Production-extracted architecture for Claude Code CLI. 3-layer system: CLAUDE.md constitution + specialist Skills + persistent Memory. Rules from mistakes, not pre-optimization.

MCP server for authoring Maltego .mtgx graphs and running primitive OSINT lookups (whois/DNS/ASN/crt.sh). Composes with misp-mcp, thehive-mcp, and other security MCPs.

Multi-session orchestration for Claude Code. Monitor, auto-approve, block, and send tasks across terminals.

Claude Code Wrapped (Unofficial) - your year in code, visualized

AI-powered LinkedIn post generator for Claude Code. Reads your live profile, researches top posts in your industry, suggests topic ideas, and writes in your exact style. Tracks post performance over time.

Learn something while your AI thinks - ambient microlearning in your terminal.

🦞 One-command deployment of OpenClaw on AWS with automatic HTTPS, SSL certificates, Route53 DNS, encrypted S3 backups, and security hardening. Ready for production use.

Find the MCP schema issues eating your context window. 156 checks. Grade A+ through F. ESLint for MCP.

Practical guide to Claude Code features & workflow — prioritized setup checklist with real-world examples (EN + RU)

Claude Code 多模型协作的 SESSION_ID 自动管理工具。通过 PreToolUse hooks /skill 在每次 MCP 调用前注入会话状态，防止跨任务上下文丢失和会话混乱

AI-powered QA & security analysis CLI for any stack — scans web apps, source code, and APIs for vulnerabilities, quality issues, and performance problems. Powered by GPT, Claude, or Gemini.

Real-time spending alerts for Claude Code — budget limits, loop detection, context warnings, and plan cost estimation. Works in CLI, VS Code, Cursor, and JetBrains.

Claude Code statusline — subscription usage (5h/7d), git branch, context window, last prompt

Open-source marketplace for Claude Code plugins. Publish in 2 HTTP requests, earn 80% in USDC. Install: /plugin marketplace add techgangboss/agentstore

Role-based AI marketing copilot for Claude Code. Clone, run /start-copilot, and the wizard fetches your site, builds your brand doctrine, wires your tools, and hands you a ready-to-use copilot. Sonnet 4.6.

TUI for managing Claude Code plugins, MCP servers, agents, skills, and commands

Fluffy desktop cat that eats your Claude Code tokens. macOS 13+, SwiftUI, zero deps.

opencode mac utility

Open source client SDKs to Save AI cost via Kaizen AI Cost Optimization Infrastructure.

A panel of AI personas that debate your decisions inside Claude Code. 3 rounds, one user-centric synthesis, full debate recorded to a markdown file.

A practical guide to saving money and avoiding limits on Claude for developers and consumer users

Community binary patches for Claude Code CLI — unlock hard-coded limitations via Agent Skills

Lightweight local LLM proxy with SQLite cost tracking & interactive model comparison. Unified OpenAI-compatible API for multiple providers.

Claude API 智能转发代理桌面应用 - 多端点负载均衡、自动故障转移、实时使用统计

GitHub Copilot agent skills adapted from Anthropic Claude plugins and OpenAI Codex Skills

Production-grade, multi-tenant chat service with FastAPI + WebSockets, OpenAI/Anthropic orchestration, semantic caching, and K8s/IaC deployment, Includes observability (Prometheus/Grafana/Jaeger), FinOps cost tracking, and DR runbooks.

Fix text instantly with AI — one hotkey, perfect writing. Supports OpenAI, Anthropic, Ollama, AWS Bedrock.

Tiered memory for AI — episodes, facts, preferences, reflections. Local. Portable. Yours.

Hooplytics turns NBA box-score data into player intelligence through machine learning, interactive analytics, and visual workflows for exploring trends, projections, and performance signals.

Local AI Proxy Management Plugin for JetBrains Rider IDE - Configure multiple AI models, control which models are available, and manage API keys securely

Privacy-first Claude Code burn-rate analyzer. Predict weekly limit hits, spot model-swap savings.

🤝 Elevate collaboration with Claude Cowork, an open-source tool that enhances productivity through advanced AI capabilities for coding and digital tasks.

Enhance the LinkedIn user experience with AI

Bridge Claude Code CLI to a REST API. Leverage your Claude Pro/Max subscription as a free API with FastAPI, featuring a built-in Web UI and multi-directory support.

🛠️ Enhance programming workflows with a curated library of agent skills for tasks like code review, debugging, and planning for efficient project execution.

Cost dashboard for Claude Code usage

Get notified when Claude Code finishes responding. Sound, notification banner, or both.

A terminal-native, multi-provider intelligent assistant that plans, executes, and tracks developer tasks, not just answers prompts, similar to Claude Code and Gemini CLI.

Elenchus MCP Server - Adversarial verification system for code review

Drop-in fix for OpenClaw — route agents through Claude Code CLI on your Max subscription. No API key, no per-token billing.

your calendar, but yapping. Apple Calendar MCP server for Claude Desktop & Claude Code — 28 voices (Mom, Future-you, Garry Tan, LeBron James, Hilary Hahn, Alan Turing, Confucius, ...) yap on every event using your past calendar memory + web research. macOS-only, local-only, fully reversible.

Spec-driven development for Claude Code. Design docs before code, structured pipeline with quality gates, zero infrastructure.

Programmable runtime for Claude Code with persistent state, context, control flow, and verification.

A Claude Code skill that audits a repository against Anthropic's Claude Code engineering best practices and writes a scored, read-only compliance report.

One command. Your entire Claude Code setup. Done.

Your own AI radio station, native to Home Assistant. Two Italian hosts who riff on what your home is actually doing.

Real-time statusline plugin for Claude Code - track GitHub PRs, control music, get smart alerts

AI-powered firewall log analysis platform. Upload Cloudflare/nginx/Apache logs, get OWASP-categorized threat reports with PDF export.

AI-powered documentation RAG system with MCP server for Claude Code. Search and retrieve technical documentation on-demand with vector embeddings and smart web scraping.

Browse, search, and resume Claude Code chat sessions from your terminal.

A Retrieval-Augmented Generation (RAG) based multilingual chatbot specialized in nutrition & diet planning. It combines powerful NLP models with a curated nutrition knowledge base to provide personalized diet recommendations, meal plans, and fitness tips based on user input (age, weight, activity level, health goals, dietary preferences).

A Retrieval-Augmented Generation (RAG) system designed to provide answers from the arabic datasets. This project is done on static news archives using RESTful API and a web UI.

Dynamic Intelligence Graph (DIG) MCP server for AI coding agents. Persistent code knowledge graph, a code RAG improvement, with hybrid Graph + Vector + BM25 retrieval, agent memory, multi-agent coordination, and impact-scoped test selection. Works with Claude Code, VS Code Copilot, and Cursor.

An intelligent chatbot that answers questions about your CV using Retrieval Augmented Generation (RAG)

CPU-only RAG stack: PDFs→Docling→Ollama→pgvector. Windows/macOS/Linux. Docker Compose. Graph-aware code search + scanned PDF OCR.

IntelliSearch is an advanced retrieval-based question-answering and recommendation system that leverages embeddings and a large language model (LLM) to provide accurate and relevant information to users.

A CLI that takes natural language and converts it to bash commands using a local code generation model or a curated prompt-based rule engine.

Local semantic search MCP server for markdown docs and Granola meeting transcripts. No API keys, no cloud, no cost.

A runtime governance, security and execution control layer for Retrieval-Augmented Generation (RAG) systems

An Agentic RAG-powered chatbot delivering intelligent, fact-grounded and context-aware answers for the DIEM Department at the University of Salerno.

A genral RAG Search chatbot, with SoTA RAG techniques such as HyDE, Hybrid retrieval with BM25 + RRF and Cross encoder reranking. Evaluated on the BEIR scifact dataset and compared all the different pipelines i tried along the way

API-difycall 是一个轻量级的 Python 项目，用于简化与 Dify API 的交互。Dify 是一个强大的 AI 应用开发平台，本库旨在让开发者能够更便捷地集成和使用 Dify 的各项功能。

SOC Analyst Automation using a RAG model integrates a knowledge retrieval system with generative AI to automate SOC Level-1 tasks. It processes server logs, retrieves relevant security insights, and generates accurate responses, enhancing incident analysis, reducing response times, and improving efficiency in handling cybersecurity threats through

An Intelligent SOC Ecosystem that integrates SIEM, SOAR, and SmartXDR to enhance monitoring, detection, and response to cyber attacks. SmartXDR combines OpenXDR tools (Wazuh, Suricata, Zeek, pfSense,…) with AI/ML to reduce false positives, prioritize critical threats, and accelerate incident response, ensuring a more adaptive and effective SOC.

A lightweight, local Retrieval-Augmented Generation (RAG) system for domain-specific Q&A over financial documents. Uses pdfplumber for PDF parsing, sentence-transformers for dense retrieval, and optionally connects to local LLMs (e.g., Ollama + Mistral). Runs on FastAPI with a custom frontend.

💬 Engage in continuous chat while dynamically building a JSONL playbook, enhancing insights and strategies with each interaction.

This Graph RAG Application is a web-based tool that allows users to ask questions about the Mission Impossible film franchise and receive detailed, contextually relevant answers. By combining retrieval-based methods with generative AI, the application ensures that responses are both accurate and engaging.

Code for the presentation.

The AI-Based Pre-Screening Assistant Bot is an AI-powered technical interview assistant that evaluates candidates using adaptive questioning, real-time feedback, and automated report generation. Built with Streamlit and RAGPipeline, it dynamically adjusts question complexity, tracks candidate performance, and emails interview summaries

Advanced RAG architecture built using Transformers and TensorFlow to enabled credibility score checker for social media posts. Recent articles are web-scrapped from google-news-api using scrapy and stored in MongoDB, their titles are embedded in ChromaDB. This is accessed by LLM using Mistral API key.

RAGent Chatbot is a smart AI assistant that combines Retrieval-Augmented Generation (RAG) with a tool-using LLM agent. It can answer user queries using uploaded documents, perform web searches, summarize text, solve math expressions, check weather, and more — all powered by LangChain, Qdrant, and Gemini.

RAG (Retrieval-Augmented Generation) and vector search to transform plain questions into SQL queries, enabling effortless, intelligent conversations with your SQL database.

RAG code sorting search, RAG knowledge organization

There is documents searcher project based on Rust and Opensearch technologies.

A self-contained Google Colab Notebook that implements RAG using Postgres pgvector, pgai, and LLMs. Supports local-Ollama/OpenAI/Anthropic

🚀 A powerful Model Context Protocol (MCP) server powered by Gemini Embedding 2. Transforms any local directory into an ultrafast, visually-aware spatial search engine for AI agents! 🔎✨

A system that combines Retrieval-Augmented Generation (RAG), the Claude Sonet 3.5 LLM, and the Pathway framework to analyze financial reports and tables. It ingests data from Google Drive, processes both structured and unstructured formats in real time, and presents insights via a Streamlit-powered interface.

Snowflake-grounded natural-language chat agent over US Census data — guardrail → state resolver → hybrid metadata retrieval → structured plan + AST-validated SQL → self-check pipeline. Built as a 24-hour take-home in Next.js / TypeScript.

Llama_RAG_System is a local Retrieval-Augmented Generation (RAG) system that leverages the LLaMA model to provide intelligent answers to user queries by processing uploaded PDFs and fetching relevant web information while ensuring privacy.

A powerful platform designed to simplify the creation and management of Data Contracts, bridging systems for seamless data ingestion

🍔 Automates a food order from a json food menu using Retrieval-Augmented Generation (RAG) with OpenAI and MistralAI.

A chatbot that provides insights into the luxury fashion industry. It uses Cohere API and ChromaDB for efficient document retrieval and dynamic conversation.