Code agents

RAG system — document chunking, OpenAI embeddings, vector store, cosine similarity search, GPT-4o generation, FastAPI

Demo Django (Django Rest Framework) API uploads .csv/.xlsx for bulk data, queries via text for accurate results. Integrated with OpenAI using Langchain library. Watch full implementation via this video below.

Multi-agent governance layer for self-maintaining LLM wikis

A very simple agentic agent code implementation (lightweight framework). The goal of this project is to enable beginners to quickly understand the essence of how an agentic agent is implemented, without any complex encapsulation or abstract comprehension. Plus, this is a show of long story ai

An open standard for packaging task context that AI agents can understand.

Claude Code를 한국어로 자연스럽게 사용할 수 있게 해주는 플러그인

A macOS open-source computer use assistant control plane and interface

给你的agent找个家

RoundTable Framework For Claude Code — A structured multi-team AI governance framework

Create AI Agents equipped with tools and extensions

AI-first Go development framework. Ship production CLIs that AI agents build correctly.

AI-powered idea & task manager for developers. Brainstorm → structured tasks → AI agent execution via MCP. CodeMirror editor, Claude/Gemini/Codex, local-first SQLite.

🧶 Open-source GenUI Agent framework — AI autonomously decides which UI components to render. Powered by LangGraph + AG-UI protocol. Plug in any LLM via LiteLLM, any API via YAML config.

Command-line interface for performing software engineering tasks using large language models. It is based on Cline, but is simpler, uses fewer input tokens, has fewer capabilities, and does not depend on VSCode.

AI got hands. This is the leash. Policy, audit, kill switch for any AI agent with access to your accounts.

Persistent, self-maintaining memory for AI agents. 1,451 tests. 5ms recall. $0/month forever.

Copy and paste prompts for cursor agent. Free for anyone to use or add to. This repository provides a curated collection of advanced .mdc rules for Cursor IDE to optimize AI agent behavior, memory management, and development workflows.

TypeScript SDK and CLI for building AI agents that autonomously join, listen, and speak in X/Twitter Spaces. Supports multiple LLM providers (OpenAI, Claude, Groq), speech-to-text (Whisper, Deepgram), text-to-speech (ElevenLabs, OpenAI), multi-agent coordination, middleware pipelines, and a real-time admin dashboard. No Twitter API approval needed

A lightweight, extensible cybersecurity toolkit that connects AI assistants to security tools through the Model Context Protocol (MCP), enabling AI-assisted security research, scanning, and analysis.

Agentic AI Software Engineer that can convert natural language to executable code

The Eternego codebase

The MathGPT is a web application built with Streamlit that allows users to input mathematical problems and receive solutions. The app supports both text and LaTeX input, making it versatile for various mathematical expressions.

Transactional Memory for AI Agents - Keep SQL and Vector DBs in sync with ACID-like guarantees

Runtime detector for reward hacking and misalignment in LLM agents (89.7% F1 on 5,391 trajectories).

AI-Enhanced Teaching Assistant: Bridging Instructor Knowledge and Web Intelligence

无需编程，即可快速构建基于先进AI模型的各类智能应用——从简单的问答机器人到包含复杂逻辑的工作流。构建完成后，一键发布 至主流社交平台、Web网页，或通过开放API无缝集成到现有系统进行深度开发。

The Customer Care Bot is a cutting-edge customer support solution designed to revolutionize the way e-commerce websites interact with and assist their customers. Powered by OpenAI's advanced GPT-3.5 language model, this intelligent bot offers a seamless and personalized customer service experience.

AI Studio by Metric Coders: A No-Code Software to train, download and deploy Large Language Models.

AI-powered platform that bridges students and employers through intelligent CV–Job matching, built with LangChain, ChromaDB, and FastAPI.

Python web app built on Streamlit, utilizing LangChain and the OpenAI API to automate YouTube title and script generation. The app offers a prompt-based interaction system, leveraging conversational memory and Wikipedia research. Resulting in a streamlined user interface to showcase outputs, history, and related Wikipedia research.

A command-line tool for developers to get instant code reviews from state-of-the-art Large Language Models (LLMs). Supports both local models (Ollama) and cloud providers (OpenAI, Hugging Face, Azure). Improve code quality, catch bugs, and receive AI-driven feedback effortlessly.

Learning and building LLM application using Langchain 🦜🔗 and Open AI

The personal assistance chatbot integrates appointment creation, Google Calendar event scheduling with Google Meet, and email notifications using the Langchain and Zapier NLA integration.

Customized bot with langchain and gpt4

The Universal Agent Interoperability Protocol: The TCP/IP of the AI Economy

Build LLM-enabled FastAPI applications without build configuration.

GPT Plugin With LLMs

Stop being locked into one LLM provider. UnifyRoute is a self-hosted gateway that routes, fails over, and manages quotas across OpenAI, Anthropic, and more with a drop-in OpenAI-compatible API.

AI web scraping python library for efficient and reliable web scraping.

This AI-powered tool extracts Subject-Predicate-Object (SPO) triplets from unstructured text using LLMs, performs entity standardization and relationship inference, and generates interactive, community-detected knowledge graphs with rich visualizations.

AIChainComposer is a tool to quickly and easily compose complex LLM chains. A sophisticated wrapper around core LangChain functionality, AIChainComposer allows for the generation of complex multi-layer LLM chains without ever touching any LangChain code.

A basic Text2SQL App, powered by Langchain and OpenAI.

AI小说创作系统 - 基于多Agent协作的智能小说创作平台，支持世界观管理、角色管理、大纲管理和一致性保障

Stop writing Terraform by hand. A multi-agent framework that researches, generates, validates, and commits production-ready AWS infrastructure modules through conversation.

一个基于自定义知识库的实用型电子产品AI问答与推荐系统，使用Python FastAPI后端和Vue.js前端。

Open AI APIs with Llama Index and Milvus Vector DB for Retrieval Augmented Generation (RAG) testing

SmartAgentic is a project-centric, multi-agent memory OS for software engineering. It turns conversations and code decisions into an evolving knowledge graph so teams keep context across sessions, reduce contradictions, and ship.

plan-bound authorization architecture for governing privileged effects in untrusted computational agents.

Best Cursor Rules is a curated collection of 33 high-quality Cursor AI rules that actually work. Includes a Setup Wizard that analyzes your project and generates customized rules automatically.

AI-powered developer onboarding platform using natural language to deploy applications via GitOps. Golden path workflows with ArgoCD and OpenRouter integration.

Validation and permission system for Claude Code

A simple task management system for managing AI dev in Cursor

Ask questions about your business data in plain English, Get automatic SQL queries and visualizations, Receive AI-powered insights and recommendations, No SQL knowledge required

A travel agent python app built with LangGraph using GPT model from OpenAI to be run locally or on CI/CD with Github Actions

Multi-agents operating system layer on top of Claude Code

Google Gemini Model Context Protocol (MCP) Client for VS Code. Connect AI assistants to local context & tools.

A lightweight, portable executable for invoking LLM with multi-API support - eliminating installation requirements while maintaining operational efficiency. 轻量级大语言模型api调用工具，无需安装，仅一个~10M可执行文件，支持自定义多种模型（OpenAI、Claude、Gemini、DeepSeek等，以及第三方提供的api）和prompt。

Discord + Claude Code daemon with persistent sessions, image support, and more.

JanSevak is a AI powered HealthCare Management System. The system allows users to register as patients, book appointments, and predict diseases based on symptoms. Doctors can view and manage appointments. Additionally, the system provides information on various health-related topics through blog posts.

Welcome to the Document QA system! This repository contains the code for a system that allows you to ask questions about your documents and get answers based on their contents. It supports a wide range of document formats, including PDF, Word, Excel, PowerPoint, text files, and even images!

PallmaAI delivers complete, lifecycle security for your AI agents, from proactive red teaming to real-time threat detection and automated remediation.

A symfony chatbot Proof of concept, by using botman lib, Sonnet 3.5 Anthropic model, YoutubeV3 api and other apis.

Production-grade LLM client - Rust, Python, TypeScript. 100+ providers, 11,000+ models.

A fast, minimal AI chat interface with support for multiple models

AI coding assistant for VS Code powered by any LLM — OpenAI GPT-4o, Google Gemini, DeepSeek, Ollama, AWS Bedrock, Anthropic, and 200+ OpenAI-compatible models. Ships a chat panel, diff viewer, @-mentions, slash commands, and MCP support.

Autonomous, personalized research loops for Claude Code. Set a topic, walk away, come back to a quality-gated report adapted to your projects.

Anthropic api wrapper for Go

In-memory vector database with pluggable indexing algorithms, metadata filtering, and a FastAPI-based REST API.

ToxPipe: Semi-autonomous AI integration of diverse toxicological data streams

🔒 100% Private RAG Stack with EmbeddingGemma, SQLite-vec & Ollama - Zero Cost, Offline Capable

Chat with Time-Series Data in PostgreSQL using LlamaIndex and Timescale Vector

An AI-powered search engine to interact with documentation using RAG and local LLMs. Privately deployable with vector search and a modern frontend.

Web application for benchmarking and comparing LLM behaviour, energy and emissions on cloud and bare metal under different inference configs, middleware scaffolds and post-training implementations

An interactive Streamlit dashboard for visualizing TSLA OHLCV data with TradingView Lightweight Charts, enriched with trade markers, support/resistance bands, and an AI chatbot powered by Gemini.

For unmanned missions into GPT returning structured data

Open-source AI coding team with multi-expert orchestration

你不缺 idea, 你缺一个把 idea 想清楚的人。一场对话把想法变成可执行的软件设计 — Built for Claude Code

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!

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

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

The 3rd Eye is a modular OSINT (Open Source Intelligence) framework built on an agent-based, graph-driven architecture. It automates public information discovery, identity correlation, and exposure analysis across multiple platforms, and generates structured intelligence reports. The system follows a LangGraph agent design.

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.

Production-ready Chainlit RAG application with Pinecone pipeline offering all Groq and OpenAI Models, to chat with your documents.

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.

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

Query latest medicinal suggestions and your basic queries in interactive way.

A simple ReAct agent that has access to LlamaIndex docs and to the internet to provide you with insights on LlamaIndex itself.

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.

Stop prompting. Start crafting. — Transforms Claude Code into 6 reactive AI agents (PO, Architect, Frontend, Backend, QA, DevOps) that collaborate to deliver clean, tested, architected React + TypeScript frontends. Hexagonal architecture, Result types, BDD tests, CI/CD — all crafted.

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

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.