Code agents

AI-Powered Multi-Agent System for Smart Kitchen Renovation. Built with Vertex AI, ADK, MCP Toolbox, and Gemini 2.5, this project simulates intelligent collaboration between agents to optimize kitchen renovation tasks.

Master Edition: A resilient, self-healing Multi-Agent AI Operating System. Features autonomous task orchestration (Navigator, Curator, Evaluator), Glass-Box observability, and a custom Circuit-Breaker auto-failover pattern (Gemini 3.0 → Llama 3/Qwen) for guaranteed 100% uptime.

4th.GRC — A policy-driven Agentic AI governance and orchestration platform integrating PolicyEngine, Skill Registry, RAG Safety Envelopes, Constraint Evaluators, and evidence-based compliance automation.

Evidence-native finance mission control that turns raw exports and docs into a Finance Twin and CFO Wiki, then answers finance questions with decision-ready evidence packets.

prompt to SQL, NoSQL and GoogleDrive task executing agent

A self-healing AI orchestration layer that enforces deterministic validation and security over LLM pipelines to prevent hallucinations and unsafe outputs.

A multi-agent restaurant food ordering system using Semantic Kernel, A2A and Azure OpenAI. Includes a backend agent server, customer chat API, and sample UI for natural language food orders. MIT licensed and open for contributions.

Workflow-oriented Kubernetes MCP for AI agents. Deploy, diagnose, and operate clusters with less manual kubectl.

An agentic AI travel planner using local LLMs (Ollama), tool orchestration, preference-aware scoring, and human-in-the-loop booking handoff.

The repair layer for AI agents. Validates and fixes malformed API calls in <30ms before they crash your production systems.

Equip AI agents with internet access to gather real-time data from restricted or hard-to-reach online sources.

One-Click AI Agent for Java Unit Testing

A structured workflow process for Claude Code with slash commands

A headless terminal emulator built for native Windows OS, that keeps `isatty()` returning `true` for spawned processes while staying either completely invisible or hiding in system tray. Run any TTY enabled app such as Claude Code CLI, Gemini, Codex, or any TUI app without a console.

CLI that runs builder, validation, and independent reviewer agents in a bounded loop for local AI coding workflows.

An intelligent coding agent that understands your codebase, fixes bugs, refactors code, and explains architecture.

The agentic DebtGuardian codebase for the IPN project TechDebtOps

Structured academic protocol for learning AI and Reinforcement Learning using general-purpose LLMs with rigor, verification, and reproducibility.

Open protocol for runtime budget and action authority over AI agents

Distributed systems for automated proposal generation. Orchestrates LLM agents for requirement extraction, semantic inventory matching, and competitive pricing analysis

News about any topic, already digested for you📰

This n8n-workflows project is a collection of workflow automations built using n8n. Each workflow automates tasks such as data collection, processing, integration with APIs, notifications, and scheduled operations.

Kodama for Claude Code — Reliable session memory & smart restart for the Claude CLI

AI Agent Security: Otonom yapay zeka ajanlarının ve MCP protokolünün güvenlik riskleri. Excessive Agency, tool poisoning ve Meta'nın "İki Kural" (Rule of Two) savunma çerçevesi.

A compact language for AI workflows. One symbol (@) separates AI logic from code. Includes an AI-readable spec and a pure-Python runtime (kzl)

Sample app to be tested by Agentic AI Mobile Tester

A collection of resources documenting my research and learning journey in AI System Security.

High-performance FastAPI-based agentic RAG system with Ollama LLM integration and comprehensive tool calling capabilities - v1.0.3.21 Production Ready

Repository to provide specialised sub-agents and skills for various AI platforms as a CLI tool

A Model Context Protocol (MCP) server implementation designed for AI agents to monitor and interact with Linux servers (Ubuntu, CentOS, RedHat, etc.). This server provides comprehensive system information including CPU, memory, disk, network, and process data through both MCP protocol and HTTP REST API

WordPress plugin that allows you to "expose" wordpress debug logs to Agent LLMs avoiding manual copy and paste.

CLI for managing tmux sessions running AI coding agents

All reasoning is stored in git. No external server. No database. No account. No hosting. Any developer on any system pulls the latest commits and gets the full reasoning history. Any future AI agent reads it before modifying shared code. It works through GitHub, GitLab, Bitbucket, or any internal git host at Google, Amazon, or anywhere else.

Your personal AI CTO: Automates the journey from developer to intern by auditing code, suggesting gap-filling projects, and tracking 'Hirability Scores' through a modular agentic workflow.

Verify claims using AI agents that debate using scraped evidence and local language models.

AI agent credential broker — temporary, task-scoped tokens with automatic revocation. Free for internal use

LangSQL is an AI-powered SQL assistant that allows users to interact with databases through natural language, transforming plain English descriptions into structured SQL queries.

Spackle lets you expose your MCPs, hooks, tools, and builds to Claude across projects with zero futzing or configuration.

Python sustainability climate-change biodiversity restoration multi-agent-system generative-ai agentic-ai ibm-granite ibm-adk groq-api.

A starting point for building custom agentic LLM applications using Open Source tooling and models. Incorporates Ollama, Open WebUI, Langchain, Streamlit, Chroma, & PGVector using Docker and Docker Compose and optionally Codespaces.

AgentArticle is an AI-driven application that streamlines content creation by combining web scraping, NLP, and AI tools to produce high-quality articles for LinkedIn and other social media platforms. It integrates APIs and Selenium automation, making it perfect for professionals, content creators, and marketers.

This automated snapshot taker uses Caldera/Blockscout API and GitHub workflow

🍕 One Pizza Team [AI Agents Team ] | Claude Code Agent Squads

AI-powered odds intelligence and agentic AI infrastructure for sportsbooks and odds feed providers. Real-time odds monitoring, anomaly detection, feed quality auditing, custom AI agents, Agent-to-Agent protocol, and Agent Reputation Network.

Agentic Telegram bot for Home Front Command security alerts — LangGraph, 4 LangChain tools, wartime deployment

A research-grounded course on writing high-quality Claude Code skills — 9 modules, 14 universal patterns, deployable assess-skill and write-skill, and a terminal reader. Based on analysis of 8 production repos and 6 peer-reviewed papers.

An agentic command line tool.

Claude Code agents move any MongoDB collection into Exasol, discover patterns, and publish a live data app — one prompt, end to end.

Agentic AI threat modeling using the lets-threat-model-core Docker container. This action produces Markdown, optional JSON, and SARIF reports—seamlessly integrating security assessments into your CI/CD pipeline and supporting GitHub Code Scanning.

This repository contains LangGraph tutorial code for building complex LLM-powered applications. It showcases practical examples of using LangGraph to manage multi-step workflows and stateful logic with language models.

AI-native SDLC: stages, roles, skills, rules & sdlc CLI for Cursor/Claude—traceable delivery, repo-grounded design, regression-aware tests. GPL-3.0.

Jolo — not exactly YOLO but close enough. Program like it's 2026!

Agent-to-Agent AI Integration: AWS Security Analysis with AI21 Maestro & Strands Agents

The secure, autonomous alternative to and OpenClaw for macOS & iOS. Features end-to-end encrypted cross-device remote control. 打造比OpenClaw更自由、安全的專屬 AI 代理。

A research instrument for studying personality drift in LLM agents. Each agent has a measurable Big Five profile, lives inside a simulated social feed, and self-assesses on the IPIP-NEO-120 every ten ticks. Drop in an API key and a seed file to run your own experiment.

Deterministic firewall for MCP agent tool calls. YAML policies, hash-chained audit, blast-radius scoring, multi-cloud cost intelligence.

A UI component for visualizing and validating MCP Server Cards, and for testing MCP server capabilities using the server card definition.

agentic urban heat analysis from satellite capture to thermal evidence, hotspot ranking, and planning recommendations

Agentic AI Orchestrator and coding agent for business-as-code platforms, services, and data. Focused on streamlining development for startups and small business who want to own their own cloud.

This is the fully autonomous ai agent build with OpenAI Agents SDK

A real-time, zero-trust governance layer that sits between AI agents and the outside world.

Explore practical workflows and best practices for building and managing AI agent infrastructure in engineering teams.

System of record for AI tool risk: inventory, policy enforcement, approvals, and audit-ready evidence.

Open protocol and CLI for installing autonomous AI behaviors into any code repository.

Proxilion is the security layer for the agentic workforce. It turns managed AI agents into governed users by enforcing strict cryptographic boundaries on every API call to SaaS like Google Workspace, Salesforce, or Atlassian.

Multi-agent modular workflow system to perform in-depth research on any prompt.

A proactive AI assistant using Qwen-Agent to learn your writing style and manage Google Calendar & Gmail.

Walkie Talkie AI Assistant for Claude Code

A Python framework for N-agent collective learning using Tsetlin Machines and synthetic data sharing, supporting zero-shot sensor onboarding and LLM-driven feature extraction.

The Essential MCP Toolkit for Developers

Plain-English playbook for AI-assisted development: how to prompt, structure work, verify output, and ship safely

ClaudeRoam — Your Claude Code config, anywhere. Across Macs. Across accounts. Without the copy-paste.

An intelligent MySQL AI Agent system that translates natural language into SQL queries and provides insightful responses — powered by Streamlit, LangChain, Gemini, and MySQL.

Agent is built with the help of Firecrawl for MCP tools, Gemini for LLM's.

Benchmark for evaluating safety of AI agents in irreversible financial decisions (crypto payment settlement, consensus conflicts, replay attacks, finality races).

Hoomanity is a Bun-powered ACP relay that lets you use your existing coding agents, or run your own local agents, from Slack, Telegram, and WhatsApp with persistent sessions and tool approvals.

10xSRE is an Agentic AI SRE that autonomously investigates production incident(s) by reasoning over your observability data (Metrics, Events, Logs, Traces, Incidents) and identifies root cause(s) in real time, enabling faster incident resolution and continuous system reliability.

Kommt noch

Companion repo for Vibe to Live: Building and Deploying Production Agentic Apps

TypeScript framework for building production-ready LLM systems. RAG, agents, workflows, evaluation, multi-model orchestration, OCR, MCP, Fine-Tuning, and more.

The cross-platform core design tokens for Vibe Coders

Before there was CLUADE CODE - I wrote this similar tool. Leverage LLM-API to translate high level YAML requirements into function/unit-tested applicaiton

SimEthica - testing ethical obligation with artificial agents

Agent-first runtime tooling for Spring Boot: execution graphs, governed overlays, and reviewable remediation drafts for coding agents.

🐳 Run Claude Code safely in isolated Docker containers with persistent projects and easy setup on macOS using Justfile automation.

A SQL question-answering tool based on LLM

Research and Course material based on AI Security Research

Enables small function calling models to find and use 484,000 local source code tools from many open source repos

MarkItDown is a Python tool that converts various document formats to Markdown. This Docker image provides a portable, easy-to-use containerized version that works out of the box.

👾 Self-Healing AI Terminal Assistant — 100% local, offline-capable, privacy-first. Multi-tier LLM (llamafile/GGUF), auto-fix with FixNet consensus, 80+ commands. No cloud, no API keys needed.

Forensic git-history learning diagnostic for AI-assisted developers. ICM specialist that turns commit history into evidence-backed study plans and HTML reports.

Comprehensive, actively maintained n8n skills for AI assistants. 10 specialized skills, community fixes, and weekly updates synced with n8n releases.

🤖 AI-powered Git commit message generator that creates meaningful, standardized commits using OpenAI's GPT models. Supports Conventional Commits, Gitmoji, and custom formats. Streamline your Git workflow with AI-generated commit messages that follow best practices. Features: ✨ Conventional Commits support 🎨 Gitmoji integration 🌍 Multiple langua

Intelligent document chat assistant for teams using RAG, Google Gemini, and ChromaDB. Dockerized PERN stack application.

Mission Control for multi-agent AI systems. Real-time orchestration, live metrics, and complete visibility. Built with LangGraph, FastAPI, and Next.js.

⚡ 最轻量的桌面 AI 客户端 | 多模型自由切换 | 流式响应 | 本地隐私 | 开箱即用

Local dashboard to manage Claude Code — skills, agents, teams, commands, hooks, settings and CLAUDE.md in one place