Code agents

The code for LexDrafter framework: a framework that assists in drafting Definitions articles for legislative documents using retrieval augmented generation (RAG) and existing term definitions present in different legislative documents.

Arm you with all the essential tools to integrate AI seamlessly into your apps, regardless of the coding language you're comfortable

[Under Review] ArcAligner: Adaptive Recursive Aligner for Compressed Context Embeddings in RAG

N8N Genie helps you to create N8N workflow by AI

Self-hosted RAG framework with RBAC, multi-LLM support, and natural language SQL over tabular data

SvelteKit and Svelte 5 done right. Runes, load functions, form actions, SSR patterns.

MCP server that integrates with Keycloak, allowing you to manage Keycloak users and realms through a standardized protocol. It uses the official Keycloak Admin Client to interact with Keycloak's API.

An intelligent task management assistant built with .NET, Next.js, Microsoft Agent Framework, AG-UI protocol, and Azure OpenAI, demonstrating Clean Architecture and autonomous AI agent capabilities

Universal protocol for AI agents to interact with any software — REST APIs, SaaS, desktop, CLI. No screenshots. No scraping. One intent.

OpenClaw skill for trading stocks, ETFs, options, and crypto via Alpaca's Trading API. Fully autonomous portfolio management.

This project is a modular Retrieval-Augmented Generation (RAG) system built with Google DeepMind's - Gemma 3 served locally using Ollama.

Offline Text-to-SQL Agent – Convert natural language questions into SQL queries with explanations. Fully open-source, runs locally, and features a Streamlit UI, multi-table support, and configurable SQLite databases. Built with LangChain, LangGraph, Ollama (CodeGemma 7B).

Multi-agent Claude Code you can actually control. Spawn specialist teams in tmux, watch them work side-by-side, steer when needed. Built on native Claude Code agents. No black boxes.

10 production prompt engineering patterns reverse-engineered from the Claude Code source leak. Python implementation. No proprietary code.

Robin: session-native agentic quant research for factor discovery, portfolio backtesting, and strategy promotion.

Open-source security gateway for MCP agents and tools. Inspect tool calls before execution, enforce policy, block risky operations, and emit audit-ready evidence.

🚀 A modern, full-featured web interface for Claude AI with advanced coding capabilities. Features multi-language support, terminal integration, file management, session handling, and MCP server management. Built with React + TypeScript frontend and Deno backend.

LegalEase AI is a document simplification tool built using Gemini API, Streamlit, and Hugging Face models. It allows users to upload legal PDFs and automatically receive simplified summaries, clause-level insights, and structured information designed for clarity and accessibility.

Dual-mode AI assistant (CLI + Telegram) powered by Perplexity AI. Fast, modular, and cross-platform.

Track Al coding assistants by GitHub issues

Infinite Agentic Looping for Agentic Claude Code UI Generation Use-Case

Real-time budget enforcement, cost tracking, and optimization for Claude Code

Automate Android devices with an LLM agent that takes natural language commands from messaging apps and runs device tasks autonomously

Claude AI가 매일 arXiv 최신 LLM 논문을 읽고, 한국어로 요약합니다.

A telegram bot that uses the OpenAI and/or the Anthropic API for an improved user experience, with payment system integrated for you to start making money! Please consider starring the repo if you use it!

Anthropic API React Native Client without polyfills

Local multi-provider gateway for using Claude Code with Gemini, GPT, Grok, and other models, with account rotation and monitoring.

Claude 3.5 Sonnet ComputerUse (Beta) for Win64

Connect Claude Code to your Obsidian vault — MCP server plugin with 20 tools, agents, and hooks for knowledge management

a collection of productivity skills for claude code.

Planning mode for Claude Code and Cowork. Claude pauses execution, clarifies intent, and compiles a reviewable plan before acting on complex tasks.

A multi-agent autonomous system for network threat detection (PyTorch), LLM reasoning (Ollama), and RL-based response mitigation.

Spring Boot backend implementing REST APIs, JWT/OAuth authentication, role-based access, mentorship workflows, content services, and AI-ready search over a MySQL-backed domain model.

This repository contains practical AI projects applying machine learning techniques to real-world problems.

EXPLAIN ANALYZE for RAG retrieval — inspect, debug, benchmark, and tune your retrieval layer

LLM-maintained personal wiki for Claude Code. Active librarian: ingest, synthesize, cross-link, remind.

TypeScript CLI that pulls a GitHub repo and merges all text-like files into one clean .txt or .pdf. Skips binaries, streams progress, writes to /out. Ideal for LLMs and RAG: feed an entire codebase as a single artifact so models can use the repository context seamlessly.

[EMNLP 2026] 🦀 The first autonomous hackathon agent stop assisting and start competing (🏆 Hackathon Champion Project).

A clean-room Go implementation of agentic coding harness patterns, derived from analyzing production AI agent architectures. Built for learning, extending, and teaching how to build coding agents like Claude Code, OpenCode, and Gemini CLI. Supports OpenRouter and Anthropic out of the box.

24/7 AI agent daemon for Android — 11 messaging channels, 30 opt-in AI tools, 25+ autonomous agent templates, OpenAI-compatible API server, offline on-device inference. Everything modular.

An Agentic PostgreSQL DBA— monitors, analyzes, and optimizes any PostgreSQL 14-18 database with LLM-powered actions

NixOS for autonomous AI coding — kernel-level sandboxing, atomic rollbacks, reproducible AI toolchain. One repo, multiple machines, zero drift.

OOPS: A Kubernetes ops platform for both humans and AI Agents. Deploy applications, manage multi-cluster, stream build & pod logs, and drive everything via UI or Agents.

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.

Riverse — A personal AI agent designed for your own devices. Persistent memory, offline cognition, grows with every conversation. River Algorithm. Local-first.

A 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.

About This sample showcases how Purview API can be integrated to audit and secure AI prompts and responses

A modular, multi-agent AI research and report generation platform. Enter any topic, and PolyAgent Research Intelligence orchestrates multiple AI agents to retrieve literature, analyze data, and generate a polished report. Built for researchers and AI/ML engineers, leveraging LangChain, FastAPI, PostgreSQL, advanced LLMs, and a Next.js front-end.

A comprehensive toolkit for building, deploying, and managing AI agents using LangGraph, FastAPI, and Streamlit. It provides a production-ready framework for creating conversational AI agents with features like multi-provider LLM support, streaming responses, observability, memory and prompt management.

Protect your AI from Prompt Injection

Multi-agent orchestration for VS Code Copilot, Claude Code, OpenAI Codex and Cursor

Agent-native image-editing SDK for Claude Code. 21 MCP tools + /decompose skill — semantic layer splits, L1–L5 cultural scoring, region inpaint. Powered by ComfyUI, Gemini, or mock.

Open-Source DLP for LLMs and Agents that provides Conversational Coherence

You've been pinched. Now get unpinched. Find out if PinchTab is running on your host before someone else does.

LogosDB is the SQLite for AI Agents.

一个基于FastMCP和Deepseek AI的智能GitHub助手，支持自然语言查询GitHub仓库信息。

Connect VS Code / Cursor to OpenClaw Gateway as a Node — 40+ IDE commands for AI assistants

Voice interface for OpenClaw with speaker recognition, voice-gated security, real-time barge-in, and multi-provider streaming TTS

Open-source team collaboration platform built for modern teams. Real-time messaging, channels, DMs, and AI-powered assistance. Built with Next.js 16, and Neon Postgres. An extensible Slack alternative with AI integration, perfect for developer communities and remote teams.

Combining a five-level AI framework with git-native memory overcomes session amnesia, enabling anticipation of problems weeks early. Production results: 2000x cost reduction, 10x+ productivity, shifting AI from reactive to predictive partnership through emotional intelligence, tactical empathy, and systems thinking.

A FastAPI and MCP server connected to Supabase table for managing, testing, and programmatically accessing LLM System Instructions, System Prompts, BOTs, Google Gems.

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

Top 50 Claude shortcut hacks for faster prompts 🌟 Star if you like it! 🌟

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.

High-performance LLM query cache with semantic search. Reduce API costs 80% and latency from 8.5s to 1ms using Redis + Qdrant vector DB. Multi-provider support (OpenAI, Anthropic).

🧠 Enterprise AI-Enhanced Development Platform with GraphRAG, LlamaIndex, Multi-Tenant Architecture, and Advanced Security & Compliance. Transform your development workflow with persistent memory, intelligent automation, and 99.9% uptime.

A high-performance AI agent built with Go

A.I.M. – Actual Intelligent Memory: zero-token exoskeleton for long-running Gemini CLI/Chat GPT Codex/Claude Code agents. External SQLite memory, GitOps guardrails, DataJack cartridges. Alpha, trenches-first.

Context-aware knowledge engine for AI assistants

🤖 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.

Enhance your Google AI Studio experience with a better sidebar, folders, tags, favorites, and library scanning.

AI Agent team collaboration platform — npm start, no Docker needed

AI engineering framework with quality gates, persistent memory, and multi-platform support. Works inside Claude Code, Cursor, Copilot, Codex, and Gemini.

Deterministic execution authorization for AI agents and automation systems

基于现代前端与 AI 技术栈构建的个性化 Notion 应用

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

Agentic Server for PostgreSQL

Agentic Identity & Agentic Security System

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

Claudeculator

在 TrafficMonitor 任务栏显示 Claude 订阅用量（5h/7d），请求前校验 Cloudflare 出口节点(colo/loc)，不对就跳过并通知。C++/WinHTTP，单 DLL。

A production-grade Multi-Tenant Retrieval-Augmented Generation (RAG) System built with FastAPI, Qdrant, and Streamlit. This system provides secure, isolated RAG capabilities for multiple organizations with advanced document processing, vector search, and LLM integration.

Source code graph RAG (graphRAG) for Java/Kotlin development based on jQAssistant

Long-term memory for AI.

A modern, RAG-powered AI chat application that integrates with Ollama for local AI inference. Chat with various Ollama models while leveraging your own documents for context-aware, intelligent responses.

CLI, MCP server, and Skill for safe local Codex session audit, cleanup, restore, and verification.

Open security architecture for autonomous AI agents - extending Zero Trust principles

A desktop app for Claude Code with multi-tab sessions, agent observability, and usage analytics.

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.

✨An AI-powered Chrome extension for Scratch 3.0 that acts as your copilot. Seamlessly generate entire games, inject blocks, and automatically load sprites, sounds, and backdrops from the Scratch library using Gemini AI directly within the editor.

A Digital Psychotherapist from the 1960s

RootTron: Your Unrestricted AI Cybersecurity Assistant. Engineered to provide raw, high-fidelity answers to any security query, from complex exploit logic

Large Language Model API interface

LyraNote 是一款以 AI 为核心的研究笔记应用，面向知识工作者做“可检索的个人知识库 + AI 写作/研究助手”。

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

CLI tool for building production RAG systems from Markdown, CSV, and PDF documents using hybrid search (BM25 + vector) with OpenSearch. Features MCP server, Slack bot, Web UI, multi-source ingestion (local/S3/GitHub), and multi-provider embeddings (Bedrock/Gemini).

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.

Stop your AI agent from generating Tailwind CSS v3 code. 20+ rules for v4 syntax, CSS-first config.

Agent asset management tool across projects and coding tools.

TypeScript SDK for self-custodial multi-chain wallets with MPC security, cross-chain swaps, and AI agent support. 40+ blockchains, no seed phrases.