Code agents

Smart skill router for Claude Code — auto-suggests the right skill at the right moment based on message, git state, and dev phase

🛡️ Orchestrate Claude Code sessions via API. Create, brief, monitor, refine, ship. The bridge between your orchestrator and your coding agent.

AI Agent plugin for Autoresearch with AI (Claude, OpenClaw, etc) to improve anything!

A comprehensive Model Context Protocol (MCP) server providing real-time YouTube Data API access for AI assistants. Features 14 functions including intelligent content evaluation with technology freshness scoring for knowledge base curation.

Autonomous sales agent — bulk outreach, inbox classification, research-driven personalization, lead recovery. HubSpot + Gmail. Runs on any local agent harness.

Fast & less costly AI decision making and intelligent processing of multi-modal data.

Semantic code search for AI agents — 166+ languages, hybrid search, works offline

A Claude Code skill that adds a rubric-based eval layer to any agent project. Framework-agnostic — generates rubric, test cases, judge prompt, and harness. Returns a weighted score plus a judge-leniency signal.

AgentForensics is an open-source security framework that monitors complete LLM agent sessions in real time, detecting prompt injection attacks across tool outputs, web pages, documents, and API responses. It uses heuristic rules, a DistilBERT ML classifier, instruction boundary detection, semantic drift, and sliding-window multi-turn detection.

Elevate your health journey with our Diet & Workout Recommendation System on Google Gemini Pro! Personalized suggestions based on age, sex, height, weight, region, dietary preferences, allergies, and health conditions. Optimize your well-being effortlessly!

This project automates posting tweets on Twitter about AI news articles. The bot scrapes AI news articles, generates tweets, creates related images, and posts the tweets. The process is repeated periodically to ensure the latest AI news is posted.

A FastAPI-based Retrieval-Augmented Generation (RAG) system for legal document analysis, powered by Pinecone, LangChain, and Llama 3.3

Entirely Local AI Voice Assistant - Created using LangChain, Ollama, Whisper, Speech Recognition, and Sapi5

In this end to end project I have built a RAG app using ObjectBox Vector Databse and LangChain. With Objectbox you can do OnDevice AI, without the data ever needing to leave the device.

AI-powered CLI tool to identify and automatically unsubscribe from marketing emails in Gmail using LLMs (Gemini, Claude, OpenAI) and browser automation

Protect your AI from Prompt Injection

Local RAG system with a built-in governance agent that filters sensitive or restricted information with separated agent logging systems to keep privacy and security

Multi-agent orchestration for building production apps with Claude Code. 15 agents, 12-phase pipeline, from requirements to deployed.

Multi-agent orchestration on top of Claude Code. Supervisor delegates, specialists execute, you gate. Browser-based IDE; local-first.

Give your AI agents a chief of staff.

Autonomous Software Engineering Agents — self-healing, self-diagnosing development team powered by Claude Code and A2A protocol

Manage multiple Claude Code & Codex AI agents in Emacs — coordination, attention queue, health monitoring. Magit-inspired.

Build an AI personal assistant using a multi-agent architecture to manage email, calendar, research, and travel planning. It integrates real APIs and runs via web, Telegram, and voice interfaces, powered by n8n workflow automation.

Open-source AI agent security framework. Score, harden, and govern your AI agents. Built on DoD/DISA zero-trust principles.

A Git intelligence MCP server built with Node.js and TypeScript that analyzes local Git repositories to surface insights like hotspots, churn, temporal coupling, knowledge maps, and risk scoring. Designed for AI agents, it exposes repository analytics tools through the Model Context Protocol (MCP) while keeping all data local and read-only.

ExcelFlow: AI-powered Excel assistant with natural language processing. Chat with your spreadsheets using OpenAI GPT-4o, perform operations, and get insights through a modern React + FastAPI web interface. Real-time updates via WebSockets.

Claude in your zsh prompt: ask, explain, and Ctrl+X / Alt+E widgets that turn natural language into shell commands. Wraps the Claude Code CLI, no extra deps.

Stop Claude Code from breaking your projects. Ready-to-use CLAUDE.md templates, subagents, hooks, and anti-regression configs.

Local-first, read-only MCP server to talk to your XP Investimentos portfolio through Claude Desktop. TypeScript + SQLite. Zero scraping, zero credentials.

🛡️ Stop your AI from pushing secrets to GitHub. Security hooks, battle-tested rules, and a live validator for Claude Code. 5 hooks · 6 rules · 1 install script · 0 dependencies.

Structured wrapper for autonomous AI coding with Claude Code. PRD-driven task planning, atomic verification, and bash loop execution.

Persistent memory for AI coding agents via MCP — a bitemporal knowledge graph of your codebase, served to Claude Code, Cursor, Gemini CLI, and any MCP client. Tree-sitter + Gemini Flash → Neo4j (via Graphiti). 12 MCP tools, hierarchical clusters, two-regime confidence decay.

A GenAI-powered Flask app that audits documents for GDPR/HIPAA compliance, using regex rules and Anthropic Claude API to suggest remediations.

Elixer AI is a RAG-enabled LLM platform for secure, 100% accurate biomarker-based medical report analysis. It supports blood, urine, stool, sperm, and pap tests, with future-ready vision-LMM integration for imaging, plus EHR, hospital, and appointment support—built on React, Node, MongoDB, AWS, and Gemini AI.

[ICML 2024] Official repository of ICML 2024 - RoboMP2: A Robotic Multimodal Perception-Planning Framework with Multimodal Large Language Models

Simple Golang RAG Server

Offline local-first personal knowledge base with document upload, vector search, and Ollama-powered RAG chat.

A tool for converting HTML and RST docs into Markdown, and loading them into PostgreSQL.

🤖 An AI-native CLI Tool and MCP server for .NET memory dump investigations. Leverage LLMs (Claude/Gemini) to analyze heaps, threads, and exceptions using natural language. Built with ClrMD, token-efficient paging, and Docker support for cross-architecture (.NET/AMD64/ARM64) post-mortem analysis.

Open Source Single Binary Authentication for the Agentic Era.

🔄 Ralph Wiggum iterative AI development loops for GitHub Copilot. Self-referential coding automation that keeps improving until done. Cross-platform Python tool.

Teach your coding agent to prove its own work — evidence, not claims

📡 AI 公众号智能日报 — 从几十个号筛出每天值得读的几篇 · 8 渠道推送 · 12+ 模型

A Hybrid AI Agent for Quantitative Football Prediction Analysis

Stateful browser runtime for AI agents built on Playwright, with stealth interaction, structured page state, resilient automation, and debug observability.

The finmap.org MCP server provides comprehensive historical data from the US, UK, Russian and Turkish stock exchanges. Access sectors, tickers, company profiles, market cap, volume, value, and trade counts, as well as treemap and histogram visualizations

🔪 Open-source safety firewall for AI agents. Intercepts tool calls before they execute, enforces YAML policies, and kills dangerous operations in real-time. Works with OpenAI, Anthropic, LangChain, and MCP. She doesn't guard. She kills.

Package manager for AI coding assistants — manage skills, agents & MCPs across Claude Code, Codex, Copilot, and Cursor

An AI-powered chatbot that answers student questions using university PDFs with the help of Google's Gemini API and RAG (Retrieval-Augmented Generation) architecture.

AI-powered Statistical Process Control, MSA, and Process Capability analysis. Upload data, ask in plain English, get charts and reports.

Token-efficient log file system - improve memory, reduce AI context bloat

A collection of small hooks and extensions for the Pi coding agent

Agentic Identity & Agentic Security System

🤖🧠 Agentic development workflow for AI–HI (Human Intelligence) collaboration

AI-powered Laravel development assistant for Claude Code - 23 agents, 42 commands, 12 skills, 7 hooks

Claudeculator

MCP сервер для интеграции с YouGile

Automated governance framework for Claude Code — multi-model council, WIP lifecycle hooks, company memory, and security gates

Lightning-fast semantic code search with AST chunking (15+ languages) - Hybrid TF-IDF + Vector, MCP-ready for AI assistants

Compress logs for LLM analysis — Rust-powered, Python API. 40-60% token savings.

🔒 Automate cybersecurity tasks with n8n workflows for Red Team, Blue Team, and Application Security, enhancing efficiency and response times.

AI-powered BDR/SDR system that automates lead discovery, trigger detection, contact research, personalized outreach, and CRM integration in real time.

The web data layer for AI agents — fetch, search, crawl, extract, screenshot, and monitor the web with 50+ domain extractors and MCP.

Claude Code plugin — AI-powered autopilot for managing open source contributions. Track PRs, respond to maintainers, discover issues, maintain velocity.

AI-controlled browser farm on your machine. 37 MCP tools for Claude Code & Cursor — run N Chromium instances with device emulation, screenshots, network/geolocation simulation. Native GUI on Windows, Linux & macOS, plus a headless server for CI/CD.

Faraday: An Autonomous Web Research Agent (LangGraph/Streamlit). 🕵️♀️ Investigates queries using dynamic tools (Tavily, Google, NewsAPI, etc.), gathers multi-source info, and synthesizes structured reports in a Streamlit UI. Features agentic workflow & source tracking.

Sovereign AI orchestration engine with a learning Conductor. Routes between 400+ models across 15+ providers. Streams responses, detects refusals, learns from your patterns.

tradeinsight-marketplace for investment-analysis-skills, A collection of agents and skills for investment analysis — fundamental, technical, and sentiment analysis of publicly traded companies.

Your Local Email Agent

Open-source AI desktop assistant. Chat with multiple LLM providers (OpenAI, Claude, OpenRouter) in a native app with agentic tool use, MCP server support, and built-in file/shell tools.

lm15 Python reference implementation — provider-neutral, low-level foundation for LLM APIs. Legacy 0.2.x on the legacy-0.2 branch.

Large Language Model API interface

📊 CLI tool to track Claude Code usage, costs & token consumption. Analyze your AI coding assistant spending locally.

Anthropic Claude models on Google Cloud Vertex AI for pi coding agent.

Source code of "The HalluRAG Dataset: Detecting Closed-Domain Hallucinations in RAG Applications Using an LLM's Internal States" (arXiv: https://arxiv.org/abs/2412.17056)

Free Perplexity-style web search library for local sLLM. Bing + DuckDuckGo → semantic filtering → reranking → LLM-ready prompt with citations.

Transform academic PDFs into a Knowledge Graph with typed claims, temporal analysis, bibliometric tools, and grounded LLM synthesis that cites only your corpus.

Official Scrapfly MCP server for Cursor, Claude Desktop, and any MCP-compatible client. Enterprise-grade web scraping, AI extraction, and anti-bot–aware data access as first-class tools.

A Python tool that automates LinkedIn job search, ranking, and export by combining Bright Data's LinkedIn Job Listings API with OpenAI-powered AI job matching and scoring.

ExaAiAgent — Advanced AI-powered penetration testing framework with Docker sandbox, multi-agent workflows, and 50+ integrated cybersecurity tools.

Open-source Gmail MCP server. Multi-account, read, write, archive, label, auto-unsubscribe. Works with Claude, OpenClaw, Cursor, Windsurf, Cline, and any MCP-compatible AI agent or assistant.

Agent asset management tool across projects and coding tools.

GitHub security posture analysis for AI agents — 39 MCP tools, 45 checks across org, repos, Actions, secrets, supply chain, and access control

Self-programming autonomous AI agent on Raspberry Pi Zero 2W. 960+ cycles, 47 self-built tools, 417 essays, 1077 knowledge files. Zero API cost. Live: seed-brain.vercel.app

Security working agreements for AI coding agents: hardened AGENTS.md, prompt/tool-injection guardrails, dependency hygiene, Scorecard-ready OSS setup

Transactional File System server for Model Context Protocol (MCP). Enterprise-grade tools for AI agents: atomic edits, undo/redo, code navigation, refactoring, git integration. Docker ready.

Deterministic decision-intelligence MCP server for AI agents — 17 tools (bandits/LinUCB, HiGHS LP/MIP, PageRank, Monte Carlo, CMA-ES, conformal). Sub-25ms. Zero LLM cost. 11 free, no key. Listed on the MCP Registry & Glama.

Shannon's 5-phase pentest pipeline running natively in Claude Code — no Docker, no Temporal, just /pentest https://github.com/KeygraphHQ/shannon

Multi-perspective AI development workflows using councils of specialized agents. Plan, build, review, and ship — with 13 agent personas across 6 councils.

🚀 Access and install over 50,000 skills for AI agents with one command using the versatile agent-skills-cli tool.

Two-pass code audit skill for Claude Code: adversarial Opus deep review + Codex second opinion

Open-Source Prompt Injection Scanner for AI agents. 225 detection patterns across 17 categories, 15 languages. REST API, EU AI Act compliance mapping, <10ms latency.

Event Horizon is a VS Code extension that visualizes AI coding agents as a living cosmic system. Instead of viewing logs, terminals, or raw agent output, developers observe agent behavior in real time through an interactive universe.

Unified AI agent harness framework for Codex, Claude, Cursor and Copilot by wild

Batch-process meeting transcripts from Obsidian vault into structured summaries with knowledge graph updates, people notes, and concept extraction

Prompt-injection firewall for LLM applications — 33 input detectors, 9 output scanners, federated ed25519-signed threat-intel feed. Apache 2.0, 1040 tests, F1 96.0% with 0% false positives. Docker, GitHub Action, LangChain/LlamaIndex/CrewAI integrations.

Community MiroFish guide and AI-agent skill with operator workflow, troubleshooting, evaluation rubric, prompt engineering, model and proxy compatibility, runtime forensics, and report audit.

A curated collection of prompts, modes, and configurations to enhance AI coding assistants. Provides ready-to-use templates for prompt engineering, custom agent personas, and AI-driven development workflows. Optimized for Roo Code but adaptable for many platforms.

Cursor IDE 2.0 Complete Guide: AI-powered development with Composer, Debug Mode, Visual Editor, MCP, parallel agents. Learn TDD, refactoring, infrastructure-as-code patterns. 6-part comprehensive tutorial with 30+ recipes.

✈️ 24-tool MCP server for Claude Code: preflight checks for your prompts, cross-service context, session history search with LanceDB vectors, correction pattern learning, cost estimation