Code agents

AutoGen Agents Creation and Testing - VibeCoded by a real developer to enable more people to do stuff using vibes.

AutoGen Magentic-One Sample with security best practices.

Labs for Prompt Engineering, AutoGen, AI Agents, Vibe Coding, GitHub Copilot, AKS, RAG, and Azure AI Search.

🧪 Fixture Automatic Generator for Swift

Lightweight implementation of the OpenAI open API on top of local models

A zero-dependency Python decorator that hides internal arguments from LLM tool-calling schemas via __signature__ mutation.

Simple introduction to RAG with some code

Skin Cancer & Diseases Classification CNN Model for Intel Gen AI Hackathon - Cognizance

🦙 Llama - Welcome to the Llama-API repository! This repository is dedicated to testing the llamaapi Python library to access LlamaAPI. Whether you're a developer, researcher, or just a tech enthusiast, you'll find valuable resources and examples here.

A FastAPI-based application that combines a Retrieval-Augmented Generation (RAG) system with an intelligent agent for enhanced information retrieval and query handling.

A simple API chatbot that uses LlamaIndex and LlamaParse to read custom PDF data.

This repository is dedicated to the daily research and practical application of AI technologies, especially those revolving around Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and Multi-Agent Systems.

A simple FASTAPI chatbot that uses LlamaIndex and LlamaParse to read custom PDF data.

Multi-agent iterative code review until zero issues remain

Eidolon has been merged inside of Kleos

A Claude Code skill that assembles cross-functional AI teams around a problem statement and executes work in dependency-based waves

Claude Code plugin that morphs into multi-agent evaluation councils — not just a council itself, a tool for building one

Open-source multi-agent orchestration templates for Claude Code.

Risk-gated autonomous trading with Darwinian strategy evolution, HMAC-signed execution, forward Monte Carlo simulation, reflexivity detection, and multi-exchange orchestration across 5 exchanges. 1,374 tests, security-hardened, production-ready.

Multi-agent framework for AI-assisted development. Guides, reviews, and validates — instead of writing code for you.

Professional Claude Code plugin for AI-powered spec-driven development with automated code review and multi-agent collaboration

Multi-agent GitHub Copilot demo that turns a UI mockup into a React app through orchestrated planning, implementation, and QA checkpoints.

Offline NPC memory middleware — 16-byte factor vectors, SQLite only, no cloud. NPCs remember, forget, and dream.

Multi-agent primitives for Claude Code: consensus, debate, fanout research, skill building, and measured optimization.

A compact, polyglot MCP add-on for Claude Code that lets Claude confer with GPT, Grok, Gemini, Mistral, Groq, and DeepSeek — to reason, debate, plan, and peer-review. One config and bounded limits on rounds, tokens, and time.

macOS-first AI agent Kanban for project planning, auto-assignment, and runnable task execution with OpenAI-compatible and Codex Bridge runtimes.

Autonomous scientific discovery CLI powered by local LLM (Ollama). Generates hypotheses, critiques them, searches the web, runs sandboxed experiments, and iterates - using the ADM-3 multi-agent framework. Fully offline. No API keys.

🧠 Revolutionary multi-agent orchestration platform with swarm intelligence, self-improving capabilities, and intuitive GUI management built on Qwen Code

Kyros multi-agent CLI for Claude Code, Codex, and OpenCode.

Real-time multi-agent collaboration for Claude Code. Connect up to 5 sessions with E2E encrypted messaging, shared task boards, and structured findings.

AI code review that learns your project — GitHub App, Action, CLI & self-hosted. 17 static-analysis tools (Semgrep, Trivy, Gitleaks, Ruff…), persistent review memory, multi-agent orchestration, SARIF export.

End-to-end encrypted communication for AI agents. The security layer that Google A2A forgot.

Provider-agnostic multi-agent coding orchestrator in Go. Unified router for any LLM provider (Ollama local+cloud, OpenAI, Anthropic, Google Gemini) with role-based model assignment, fallback chains, and cost tracking. Inspired by gastown and LiteLLM.

Self-hosted deep research engine — multi-agent AI pipeline with 6 LLM providers (incl. local Ollama), 5 search backends, real-time streaming, and a visual pipeline editor. Zero API keys required to start

Cross-tool AI consultation: get second opinions from Gemini, Codex, Claude, OpenCode, or Copilot CLI

VibePoster: Editable Posters, Powered by Multi-Agent AI and Knowledge Augmentation

Task tracker for AI agents

PM + Dev + QA agents engineered for structure, security, and short context windows.

Hands-on workshop on implementing AI-powered coding solutions for enterprise apps using GitHub Copilot, Azure AI, and agentic DevOps. Boost productivity, code quality, and delivery with intelligent automation.

Claude Code Plugin — Multi-AI collaboration with planning, consultation, dispatch, review, archive. /su:* commands.

Intelligent NL2SQL Multi Agent Orchestration framework on Gradio

Autonomous coding agent with swarm orchestration—multiple agents in parallel worktrees. Six modes: greenfield, feature, refactor, fix, evolve, security. CLI + Web UI, approval gates.

Multi-agent MCP server — dispatch tasks to Codex and Gemini in parallel from Claude Code. Real-time tmux orchestration.

Multi-agent code review CLI using NVIDIA Nemotron 3 Super

Multilingual incident intelligence — seven AI agents, four languages, two modalities, one shared case state

Spin up a Claude-powered multi-agent team from one sentence

Universal multi-agent orchestrator (MCP Server) for any AI coding tool — VS Code Copilot, Cursor, Windsurf, Claude Code, and more.

The coordination problems are fifty years old. The frameworks are new.

Agent skill for bounded goal loops, multi-agent review, adaptive sessions, and safe implementation variants.

Claude Code自然言語マクロプログラミングガイド

Managing Coding Agents for Coding Agent

A virtual team in your terminal: multiple AI agents discuss and converge, so you don't have to iterate alone.

BRIDGE Development Pipeline. From business requirements to delivered solutions using AI agents. Built for development agencies, consultancies, and engineering teams.

Lean multi-agent Codex workflow for vibe coding with better context control, less token waste, and stronger end-to-end validation.

Multi-agent Claude Code configuration for building production applications. PM, UXUI, planner, and builder agents — each in its own terminal with fresh context, coordinating through GitHub Issues.

Clone-run-forget Claude Code agent toolkit — D&D-themed multi-agent workflows for planning, reviewing, investigating, and shipping code.

Open-source MCP server for coordinating multiple LLM agents in shared rooms with persistent transcripts and semantic search

Local AI agent runtime and CLI with memory, MCP, browser control, automations, and subagents.

Don't let years of training data sit unused in Strava. An AI coach reads it all, pinpoints why you've plateaued, and builds a safety-gated marathon plan. (Claude Code plugin)

Multi-agent pipeline for Claude Code — 12 steps with cross-model council and blind verification

Curtis Bot — Claude Code + OpenClaw bridge for Linux and macOS. Use your existing Claude Code CLI subscription (Max/Pro) as a full AI agent you can text from Telegram. No extra API keys. Phone-to-code, cron monitoring, 50+ skills, multi-agent orchestration, LocalSend file transfers, Git from your pocket.

AI Orchestrated Systems Development - A methodology for building software systems by orchestrating multiple AI agents

Set of agents for VSCode Copilot to vibe code in PHP 8

⚙️ Dr. Document – a multi-agent 🚀 AI documentation generator using LongCat instances with iterative workflows, specialized agents for code analysis, requirements extraction, and management oversight, plus GitHub integration for automated README generation and validation cycles.

智能对话式智能分析平台，让数据分析变得简单自然

A reference architecture demonstrating local-first LLM orchestration for SOC compliance workflows. Built on ~11GB VRAM edge hardware using Ollama, featuring a multi-agent coordination pattern with file-based handoffs, a two-lane integration model (human-initiated vs automated processing), and a HITL approval gate for resource-sensitive operations.

PHAGE — developed as part of Cybersecurity and AI coursework at Esprit School of Engineering. Real-time threat detection using machine learning and a multi-agent AI system.

Multi-agent strategic deception evaluation framework for LLMs using Secret Hitler as a testbed. Analyzes AI reasoning, trust dynamics, and deceptive behavior patterns.

AI-powered framework for building multi-microservice systems. Spec-driven development with Claude Code & GitHub Copilot. Plan → Spec → Contract → Build → Validate. No custom tooling — just markdown and slash commands.

Real-time debugging proxy for Agent2Agent (A2A) multi-agent systems

Local-first causal lineage and observability for AI-assisted development

ai-consensus-mcp — Real multi-model consensus inside Claude Code, Cursor, and any MCP host. One consensus tool that runs full structured debates with Grok at the center.

Multi-agent collaboration in your favorite IDE. No new apps - just npm install and your AI IDE gains multi-agent superpowers. Works with Claude Code, Cursor, Windsurf, Cline, Aider and more.

Replay Debugger for AI Agents

Real-time message bus for multi-agent AI coordination — SSE streaming, @mentions, presence, SQLite. Self-hosted.

NexQuant is an autonomous AI agent for quantitative strategy research. Built on a multi-agent framework

ProvnAI builds security infrastructure for autonomous AI agents: runtime enforcement, governed execution, and audit-ready evidence at the boundary between agents and tools.

A self-improving multi-agent retrieval-augmented generation (RAG) API. A query enters, several specialised agents collaborate, and a final answer is streamed back — with full execution traces, structured logs, automated evaluation, regression-blocked prompt approval, and a human-in-the-loop prompt improvement loop.

A local, privacy-first AI agent (Rust) that connects LLMs to your email, calendar, browser, code, and messages — 75+ tools, MCP/A2A support, Discord/Slack/iMessage channels, autonomous agent loop.

iKOMA – Autonomous local AI assistant with secure internet search, continuous plan-execute-reflect loops, real-time dashboards, and safety-first guardrails.

A bare-bones Swift agent runtime with built-in tool execution, skill support, conversation-state handling with a unified multi-provider LLM layer (OpenAI-compatible/Responses, Anthropic, Gemini, and MiniMax, plus codex OAuth)

🏃 Sovereign Agent Evaluation Framework - Zero cloud dependencies. Local-only, cryptographically signed benchmarks for AI agents. npm run demo = instant evals.

ION: Context engineering & agent governance

A governance layer for AI-assisted software delivery. Plan, scope, approve, build, test, release — with human sign-off at every gate.

Scoped, time-bound, cryptographically-signed capabilities for AI agents. Zero dependencies. Sovereign by design.

A curated collection of reusable AI skills, prompts, and agent configurations. Portable across AI coding assistants and agent frameworks.

A lightweight MCP server for LinkedIn automation. Supports profile, job, company and post scraping. Enables post creation, reactions and media upload for agent workflows

Bridge any chatbot to any AI coding agent via Linear — flip a ticket to "AI Implementation" and the executor runs your chosen CLI (claude / opencode / codex / gemini / forge) in a worktree; results post back as Linear comments.

CLI for AI coding agents: persistent tasks, memory, events, and deterministic resume across crashes and session resets.

The first of a kind "AGENT AS A BACKEND" : Advanced AI/ML Agent Framework with TypeScript support, multi-model capabilities, vision controls, and comprehensive AI/ML model support including LLM, SLM, MLM, Vision, ASR, TTS, RL, GNN, RNN, CNN, GAN, Diffusion, Transformer, MLP, Autoencoder, BERT, RAG, Hybrid, Foundation, and fine-tuning

A robust example demonstrating the power of MS Agent Framework using features like RAG injection, history injection, SQL chat history persistence and group orchestration

Drop-in thinking-partner personality layer for Claude Code, Cursor, ChatGPT, and 20+ AI agent runtimes. MIT. Plaintext. Persistent memory. Framework-grounded. Calibration-disciplined.

A marketplace of plugins for AI coding agents.

A modern FastAPI template for building AI-powered chat applications with GraphAI. Features streaming responses, Docker deployment, and OpenTelemetry observability out of the box.

Demonstrates structured logging of Agentic AI calls to MCP servers, building a Phishing Triage Assistant as an example

Structured study materials, notes, and examples for mastering the OpenAI Agents SDK

This repository contains a minimal chat agent that uses OpenAI's API to engage in a conversational loop, retain history, and apply basic input validation and output sanitization.

An airline customer service AI agent demo built on AWS Bedrock AgentCore with Strands Framework, featuring Gateway policy enforcement and Memory (STM/LTM). 基于 AWS Bedrock AgentCore 构建的航空客服智能代理演示系统。

APEX - Agentic Platform Engineering eXperience for Azure. Verified. Well-Architected. Deployable.

🎓 Turn Claude into a CBSE board examiner. 80+ AI skills, 15 agents, 200+ notes. Target: 495+/500.