Code agents

Guide: from fragile multi-agent app to prod ready with orra - code and resources.

🛡️ Open-source LLM security library for Python. Protect your AI apps from prompt injection, data leakage, and harmful outputs in 3 lines of code.

Langchain最实用的基础案例，可复制粘贴直接使用。The simplest and most practical code demonstration, you can directly copy and paste to run.

SwiftDocAutomator is an AI-powered tool that streamlines the generation of clear and concise documentation comments for Swift code, following Apple and Swift best practices.

Debug RAG pipelines with just 2 lines of code

Go Based Lightweight RAG / LLM Tool with CLI + API

This repository contains the code snippets used in "LLM Prompt Engineering For Developers"

Demonstration of LLM integration into a lex bot using Lambda codehooks and a Sagemaker endpoint.

Runtime-first agent harness for official coding CLIs, chat transports, background tasks, and controlled write-back.

The open standard for agentic software verification: query business rules, assess release risk, and execute autonomous testing workflows.

Securing Agentic AI Developer Day shows developers how to take an agentic AI reference workflow to production securely.

Hub for TIBCO Flogo® Resources

Your agentic API security engineer. Built by the community, for builders who care about security but don't have unlimited time or budget. Point it at your API docs it hunts down the deep vulnerabilities that actually get you breached.

Exposes Azure DevOps functionality via MCP: Boards, Repos, Pipelines, Artifacts, Test Plans, and Wiki tools for AI agents.

CLAPP: CLASS LLM Agent for Pair Programming

A Laravel library for the n8n.io self-hosted API

Kairos: An autonomous development supervisor powered by Context Engineering. It provides a living memory and a contextual constitution for your projects to prevent AI context loss.

模块化 AI Coding Skills 仓库，覆盖开发工具、自动化、Obsidian 与视频处理场景

Reactonaut is an online React code editor with an AI assistant. If you are new to React front-end development, start with Reactonaut!

Never lose context again - persistent memory management system for AI-powered workflows across multiple tools

SuperEZ-GPT Builder: jQuery/GPT AI Content Building Assistant

AI code indexing tool for analyzing JS/TS code structure and generating structured code maps

Simulation of job offers and CVs with real-time processing, classification, and analytics using Kafka, Ray, Spark, and Databricks. Includes a Flask-based recommendation system and Tableau visualizations.

An LLM agent to query any github repo - Ask questions, features, gaps, improvements

The Bus-Mama is a bus tracking mobile application for the transportation of the students of BSMRSTU. It helps the students of our university by showing the available route, bus, and their exact location.

Don’t read swagger. Just chat.

A simple but useful chatbot based on gpt-3.5-turbo and whisper-1.

A personalized chatbot designed to answer queries related to a specific company's products and services, using a predefined knowledge base and an API for text generation.

.NET Farmework Library for Facebook Messenger Bot

A Practical Guide to Developing a Reliable FAQ Chatbot with Reinforcement Learning and Human Feedback using GPT-2 on AWS

Discord AI bot with a hybrid command system, imagination generation, free LLM model, mention recognition, smart message handling, channel-specific responses, GPT integration, secure credential management, & web access for unparalleled functionality.

Local-first RAG platform — Ollama + Qdrant + Redis + MinIO. No cloud, no API keys, runs entirely on your machine.

A Signal chatbot to broadcast Tor bridges in countries where Tor relays are blocked/monitored

🤖 A fully functional Google Gemini Clone built with React.js and the Google Generative AI SDK. Features real-time chat, history management, and Context API integration.

ChatGPT-Python is a software that allows you to talk to GPT-3 with a web interface using the openai api

selfhosted chatgpt like service using openai apis (with APIs + Frontend and Session Storage)

Synced from GitLab - Deploy your own Serverless Discord bot integration to quickly interface with OpenAI's ChatGPT Completion API (gpt-3.5-turbo / gpt-4)

When an audio message is received, the bot downloads the audio file, converts it to a numpy array, loads the Whisper model, transcribes the audio, and sends back the result as a text message. The bot uses the Matrix Client from the mautrix library to interact with Matrix.

A sample interactive storytelling narrative chatbot application using ChatGPT API, powered by gpt-3.5-turbo, OpenAI’s advanced language model, built using Next 13, the React framework.

A social media bot integrated with ai

Build the chat backend to communicate with the GPT-3 API and store conversation infomation on the server.

This is a Telegram bot for checking the balances of crypto wallets. It checks the balance of addresses in blockchains (Ethereum, Binance Smart Chain, Polygon, Avalanche, Fantom)

A Node.js based Bot API for Nextcloud Talk

Python Mini Projects by Chirag Joshi | Python | 20+ beginner-to-intermediate projects with full documentation

PWA chat with Gemini Nano running locally in Chrome using Prompt API, no server, no API key, works fully offline.

Reduce your LLM costs by 40-70% automatically. Routes prompts locally, compacts context, tracks real savings.

The operating system for Claude Code. Memory, accountability, journaling, knowledge graphs, pattern recognition — one install, every session compounds.

A provider-agnostic Jupyter lesson on context priming, task decomposition, and workflow crystallization using Anthropic, OpenAI, or Google — from goal image to executable code in 5 steps.

VS Code extension to manage Claude Code sessions, MCP servers, skills, commands, hooks, and agents from your sidebar. Works on Cursor, Antigravity, and all VS Code-based IDEs.

Discord bot that knows a lot about Pokemons :)

A Node.js RESTful server for a Retrieval-Augmented Generation (RAG) system using ChromaDB and Ollama!

Multi-user RAG chat in Azure powered by Neon Serverless Postgres. Try the live demo using the link

A modular, multilingual, and multimodal Retrieval-Augmented Generation (RAG) system tailored for the financial analysis of Public Investment Fund (PIF) annual reports.

RAG-based Web Scraping

minRAG is a RAG system that starts from scratch, pursuing the ultimate simplicity and power. It consists of no more than 10,000 lines of code, requires no installation, and can be launched with a double-click

Code for the paper [SIGIR'26]“Towards Mixed-Modal Retrieval for Universal Retrieval-Augmented Generation”

Test code was written for research and verification of some Python libraries.

A game of pong made by MetaGPT and ChatGPT Code Interpreter

The Sovereign Code Execution Engine for AI Agents. Run untrusted code safely locally or in the cloud using Docker, Firecracker, or Wasm.

Arbor — The Agentic RL Sandbox. Checkpoint-native. Branch-safe. Self-hosted.

This repository contains sample code demonstrating how to implement a verified semantic cache using Amazon Bedrock Knowledge Bases to prevent hallucinations in Large Language Model (LLM) responses while improving latency and reducing costs.

The "Cloudflare for AI Agents". 7-layer security interceptor, real-time observability dashboard, and automated reliability testing for MCP and AI tool chains. Prevent hallucinations, prompt injection, and destructive tool calls.

T20: Multi-Agent. Orchestrator-delegate model. TAS. Goal -> plan -> delegate. Agents: Gemini family. Autonomous, traceable. Logs sessions. CLI. Usage: `t20-cli "goal string"`. Artifacts of high value.

A 100-day journey building AI-powered agents using Python, TypeScript, and LLMs to automate real-world tasks

Uncensored Language Model using FastAPI and Wizard Vicuna 30B (PoC)

Automated Unit Test Generation with AI

The Solidity Smart-Contract Advisor is a cutting-edge tool designed to extend the capabilities of traditional language models in understanding and advising on Solidity smart contracts

基于 LangChain 的 CLI Agent 框架，采用 ReAct（Reasoning + Acting）模式。支持 OpenAI、Gemini、Qwen、DeepSeek、Kimi 等多种 LLM 提供商，提供流式响应、会话持久化、工具扩展、Token 追踪、消息压缩等特性。通过vibe coding进行简单的配置和工具添加，即可快速搭建通用或垂类 Agent，无需深入框架底层

Code repo for paper "KERAP: A Knowledge-Enhanced Reasoning Approach for Accurate Zero-shot Diagnosis Prediction Using Multi-agent LLMs"

19 AI agents for Claude Code that run your full sprint cycle: strategy, spec, architecture, plan critique, build, review, QA, security, privacy, and shipping. Four sprint modes including a mobile chain for React Native. Open-source plugin, zero dependencies.

Vouch compiles human-owned intent into obligations, links evidence artifacts to those obligations, and produces deterministic release decisions for agent-written changes.

Search for music tracks using natural language prompts or video content via the Harmix AI API. Use when the user asks to find music, search for songs, discover tracks, needs music recommendations based on mood/genre/tempo/scene, or wants to find music for a video, video soundtrack, or music that matches video content

Glass-box agent execution engine. Deterministic, forensic audit trails, EU AI Act compliant. The PyTorch for Agents.

Neovim plugin for AI-assisted coding: Claude CLI & Codex CLI backends with MCP-powered editor control

Track Al coding assistants by GitHub pull requests

Codex CLI development framework that transforms product ideas into production-ready software through structured workflows and seamless Codex CLI integration.

Extended Claude Code framework based on SuperClaude.

Use Gemini on Discord, with highly customizable features. Using Thread to Create Personal Conversations with AI.

CipherGPT is an advanced SAAS chatbot AI meticulously crafted using the MERN (MongoDB, Express.js, React.js, Node.js) stack coupled with TypeScript and the OpenAI API.

SympCheck Helper is a modern healthcare consultation chatbot that leverages the power of DeepSeek V3 API and Supabase to provide intelligent health-related assistance. Built with cutting-edge technologies, it offers a seamless and intuitive experience for users seeking health information and support.

Chatbot app for creating charts with React, FastAPI, and OpenAI

OpenAI Discord is a AI-powered bot for Discord that leverages the OpenAI API. It enables users to interact with ChatGPT and DALL-E in a natural and efficient manner.

AIChatAssist is a intelligent chatbot powered by OpenAI ChatGPT API. The bot engages in natural language conversations with users.

EduBot is a powerful RAG (Retrieval-Augmented Generation) chatbot that utilizes the latest SOTA models to provide a seamless and interactive learning experience.

A very simple java library to interact with Claude's API

MCP server for Storybook - provides AI assistants access to components, stories, properties and screenshots. Built with TypeScript and Model Context Protocol SDK.

Store all your LLM Interactions

PathRAG System - A Path-based Retrieval-Augmented Generation implementation with knowledge graph visualization and Ollama integration for enhanced question answering.

A Flutter toolkit for local and cloud LLM apps. Run GGUF models on Android and iOS, connect to OpenAI, Gemini, Claude and others through one unified API, and build fully local RAG pipelines. Supports streaming, multimodal vision models, and mobile-first AI workflows.

Fine-tune a local LLM on your own app's data in 15 minutes. Runs entirely on-device, zero cloud after training. Apple Silicon + CUDA.

A Python hypergraph library with provenance and SQLite persistence.

CLI remote control for Unity Editor. Zero dependencies, single binary. AI agents can play, build, test, and screenshot your Unity project — no Python, no setup, just curl.

Give every AI agent persistent memory of your team's knowledge. No vector DB, no RAG — just Git + BM25 + 114 tokens per session.

Autonomous issue resolver

Dhara — The Agent Protocol Standard. Minimal, secure, language-agnostic coding agent harness. Built from India 🇮🇳 for the World 🌏

The only true Desktop agent that can do actual job, Create your company AI brain and departments

AI OSINT Security Analyzer is an intelligent platform that leverages AI to perform autonomous investigations across various intelligence sources. With features like multi-source integration and real-time threat intelligence, it ensures comprehensive security assessments. 🛡️🔍

Source repo for the blog post Stop Stuffing Your System Prompt: Build Scalable Agent Skills in LangGraph

End-to-end ELT pipeline for 160K+ Skytrax airline reviews: Airflow orchestration, BeautifulSoup scraping, S3 staging, Snowflake warehouse, dbt star schema transformation, Terraform IaC, GitHub Actions CI/CD