Code agents

Persistent memory MCP server for Claude Code — self-hosted, n8n + PostgreSQL + pgvector. No cloud required.

MCP security scanner by Helixar

Multi-agent LLM system for autonomous code generation, testing, and debugging with Docker sandboxing

"🚀 Full-stack Medical AI Chatbot using Retrieval-Augmented Generation (RAG). Built with FastAPI, LangChain, and Groq. Features automated CI/CD via GitHub Actions to Docker Hub and scalable vector search with Pinecone."

A high-performance reverse proxy that intelligently distributes requests across multiple LLM providers (OpenAI, Google Gemini, Anthropic Claude) and API keys. It provides seamless OpenAI API compatibility, advanced load balancing algorithms, real-time cost optimization, and enterprise-grade observability.

Tutor-Ai is a SaaS platform for teachers to manage class quizzes and grade student submissions using OCR technology. Built with Django, it features Llama-3 & Gemma:7b, Google Vision API integration for automatic grading, and is hosted on Google Cloud. It offers a secure, scalable, and user-friendly solution for educators.

Agentic -powered synthetic data generator that creates flowcharts using LangGraph orchestration. Features FastAPI integration, OpenAI LLM processing, and automated Mermaid diagram generation.

Code for an AI assistant that answers questions about coffee to demo instrumentation of GenAI apps with open-source Monocle.

AI-powered mock interview simulator with coding, tech, and HR rounds using FastAPI, LangChain, and MongoDB.

Chat over the git repository code built on LangChain, LangGraph, PGVector, FastApi, SqlAlchemy for frontend based on AI SDK

Your Multi-Model AI Development Assistant - Free, Intelligent, Autonomous

A multi-agent workflow orchestration tool (integrated with Swarm). By decoupling product workflows from code logic, it allows non-development personnel to orchestrate and debug workflows without modifying the code.

A Model Context Protocol (MCP) server for Discord-based AI agent-user communication. Enables AI agents to communicate with users through Discord instead of IDE chat interfaces.

[ACL 2025] Code implementation for the "LLM as a Broken Telephone: Iterative Generation Distorts Information" paper.

Devika is an Agentic AI Software Engineer that can understand high-level human instructions, break them down into steps, research relevant information, and write code to achieve the given objective. Devika aims to be a competitive open-source alternative to Devin by Cognition AI.

Autonomous agentic threat hunting playbook executor for SOC/DFIR pros. Runs YAML playbooks against forensic logs with local LLMs (Ollama) for intelligent correlation, triage, ATT&CK mapping, and automated reporting. Offline-first, DuckDB-powered.

Aisyah AI is a powerful Telegram bot built with Cloudflare Workers that combines multiple AI capabilities. It can browse the web, set reminders, speak, predict weather, analyze images, and understand voice messages. The bot maintains context in conversations through Redis, making it perfect for both private chats and group interactions.

Build a production-ready multi-agent quantitative analyst system where AI agents scrape market data, analyze trends, and generate investment reports. Uses FastAPI for orchestration, Streamlit UI, Azure PostgreSQL for logging, and Azure Blob Storage for archiving.

Persistent memory for Cursor IDE — like claude-mem, but for Cursor. Zero-config, no API key.

Your AI Assistant on ESP32-S3 natural language programming, camera vision, voice I/O, PC control. No computer needed after flash.

Welcome to the Groq Unofficial API! This API provides an interface for interacting with Groq's services in a seamless and efficient manner. Whether you're a developer, researcher, or enthusiast, this API empowers you to integrate Groq's capabilities into your applications and projects with ease.

一時の略称はSKL。War-chess game framework, for Turing-complete skill effects and 2-D grid map. Text-based user interface only. Logging system will be improved and will probably break the current APIs

Murf AI's 30 Days of AI Voice Agents Challenge

ai entertainment service for twitch streamers

QuantumPDF V1.3 enables intelligent conversations with PDF documents. Built with Next.js 15 and React 19, it uses Retrieval-Augmented Generation (RAG) to provide accurate, context-aware responses from your documents.

Unlock OpenAI's Computer Use in ANY region. A Codex++ tweak that exposes Codex Desktop's bundled OpenAI Computer Use MCP server as computer-use.

OTP Autofill in browser with AI (VandyHacks XI)

Build readable Codex desktop pets — row semantics, approval gating, deterministic packing, validator.

Community repo for clean Codex setup, reusable skills, hooks, and team-ready best practices.

This Python script provides a simple interface to transcribe audio files using the OpenAI API's speech-to-text functionality, powered by the Whisper model. The result is returned to the console as text or VTT (WebVTT) format.

Production-ready multi-tenant SaaS wrapper for LiteLLM with job-based cost tracking, credit management, and flexible pricing. Built on LiteLLM.

CodeStral-Code-Assistant is a chatbot designed to assist users with code-related questions. It provides code solutions, including descriptions, programming language details, imports, functional code blocks, and sample input/output.

A self-hosted AI platform — inference, tool use, browser automation, image generation, speech synthesis, transcription, object storage, agentic code execution, and more — behind a single OpenAI-compatible endpoint. One docker-compose up.

Building upon the NLP engine and knowledge base, we have developed a state-of-the-art conversational model. This model, trained on a massive dataset of customer dialogues, generates natural language responses that are not only informative but also empathetic and engaging. Furthermore, AI-DCSS integrates a continuously evolving knowledge base.

Full Stack AI Resume Builder App

LLM-IK: Solving Inverse Kinematics using Large Language Models

Advanced RAG System with Go featuring intelligent adaptive chunking, hierarchical document processing, semantic search, and flexible LLM integration

Local Responses API shim for Codex custom providers backed by DeepSeek/OpenAI Chat Completions

This project automates the process of generating comprehensive literature reviews from a collection of academic PDFs using OpenAI's GPT models.

Coeus is an A.I. Computing Assistant for MacOS that can answer just about any question you may have reading back the responses if you choose. It also creates realtime images using A.I., all by leveraging the OpenAI API.

OpenAI-compatible proxy server for GitHub Copilot

Free, open-source Azure OpenAI PTU calculator. Compare PAYGO, PTU, Spillover, and Priority Processing pricing with live Azure API data. Prevent 429s with built-in optimization tools.

MALLO (MultiAgent LLM Orchestrator) es un sistema avanzado de orquestación de múltiples agentes de Modelos de Lenguaje de Gran Escala (LLMs). Diseñado para manejar consultas complejas, MALLO utiliza una variedad de agentes, desde modelos locales hasta asistentes especializados y APIs de terceros.

🤩 📱 Portfolio de Apps creadas en el canal de SwiftBeta

Research project on AI usage for threat modeling and security review and using Anthropic Claude 2

Claude Code plugins that are better than NZT‑48

A collection of custom commands, skills, and gems for Claude Code

A macOS settings manager app for Claude Code - built with SwiftUI

Give Claude Code a memory, a workflow, and the ability to improve itself. 20 commands, 3 skills, 5 hooks, and a document structure for persistent AI coding sessions.

Transform Claude into your AI-powered productivity partner. Note-taking skill creates an AI-navigable second brain with conversational capture, intelligent search, and pattern recognition across all your work. Plain markdown, local-first, works in Claude Code and Claude Desktop.

Token counter for Anthropic

D&D 5e game engine plugin for Claude Code

Native Swift agentic loop for the Anthropic Messages API — run Claude as a coding agent in macOS/iOS/visionOS apps without Node.js or CLI dependencies

Zero dependency (Unofficial) Go client for the Anthropic API.

🍀 🤖 Spring Boot AI - Evaluation Testing

A modern web UI for semantic document search and management using Google Gemini File Search API.

DeepInsight 是一个企业级智能数据分析平台，通过自然语言查询实现复杂的数据分析和可视化。系统采用先进的 Text-to-SQL 技术，结合 RAG（检索增强生成）和智能硬件优化，为用户提供直观的数据洞察体验。

This is a multi-agent processing system with long-term and short-term memory+mcp+local tools+Agentic Rag. It uses the LLM locally deployed by ollma and PostgreSQL to store user's data, and the back-end uses grpc,gorm and gin to coordinate the output of the agent.

A TypeScript-based code knowledge graph indexer that transforms Git repositories into searchable knowledge stores for AI agents. Creates interconnected representations of codebases through AST parsing and vector embeddings.

Gebeta Sovereign Code Assistant is a local-first AI engineering environment that enables developers and teams to code, review, refactor, test, and execute agent workflows without exposing proprietary source code to third-party AI providers.

BleuNova AI Agent: Your ethical, hacker-proof personal AI companion. Self-hosted, autonomous, multi-modal (video, IoT, voice), with built-in continual learning, Grok-powered wit (optional), and zero-trust security — all local-first and open-source.

Agent skill that gives it hands in the browser. 25+ tools to navigate, extract data, execute scripts, intercept APIs — all in user's own Chrome with their login sessions. No passwords needed. 给Agent一双手，像用户一样使用浏览器，25+自动化工具，数据完全本地处理。

A Chrome extension that converts web articles to speech using built-in local AI models. No cloud services, no API keys – everything runs directly in your browser.

Your own cloud machine for Claude Code — with persistent memory. Self-hosted, open source.

AI-driven R&D workflow framework: 8-step SDLC, hard gates, @rules traceability chain. Bilingual (EN/ZH).

Minimal local-Qwen coding agent in a single Python file. ReAct loop, tool dispatch, atomic tools, no framework. Educational.

Knowledge agent for LLMs — online research + local accumulation, gets smarter over time. MCP-ready.

Decentralized agent memory for the Lightning economy. Nostr identity, L402 payments, MCP server.

OpenCode plugin providing autonomous development agents for continuous codebase improvement

Persistent Agent Runtime — self-hosted cognitive runtime for AI coding agents: semantic memory, knowledge graph, agent coordination, event-driven workflows, and autonomous self-maintenance via MCP

The flight recorder for AI agents. Tamper-proof, ISO 42001 + HIPAA-compliant audit trails for everything AI agents do on your system. File changes + shell commands + PHI detection + agent identity.

Discover the right CLI tool for any task — in plain English. MCP server for AI agents.

AgentOps for Claude Code. Monitors AI agent behavior during development: real-time error loops, drift detection, friction analysis. Claude gets self-awareness hooks + MCP tools. You get cost-per-commit, agent success rates, exportable metrics. Like DevOps, but for AI agents.

Greatly improve how AI coding agents handle complex projects. Task Trellis helps track requirements for projects, breaks them down into smaller manageable parts until you have trackable and assignable tasks with built-in workflow management, dependency handling, and progress tracking. Basically, it's like Jira for coding agents.

Hosted Amazon Seller & Vendor MCP server. Connect Claude, ChatGPT, Cursor, Codex, Gemini, GitHub Copilot to Amazon SP-API and Ads API data

A lightweight scaffold for safer, more structured agentic coding — helping developers give coding agents the right project context, guardrails, and workflows without locking into one tool.

30 classic strategy & management frameworks as Claude Code skills — /think auto-selects from TOC, TRIZ, Wardley, OODA, Systems Thinking, Blue Ocean, Design Thinking, First Principles, Porter, Drucker, BSC

An AI development platform that allows users to build custom AI models through an API, supporting chatbots, music generation, and coding tools to streamline creative and technical workflows.

Rust orchestration daemon for coding agents — polls Linear/GitHub/Markdown, creates isolated workspaces, dispatches agent sessions with EGRI self-improvement.

Local-first agent debugger with replay, failure memory, smart highlights, and drift detection.

The Cowork Agent for Everything — trainable advertising AI + 14 platform MCP servers + agent skills. Based on minimind (42k stars). Train from zero in 2 hours.

Secure sandbox runtime for AI agents

Local-first multi-agent platform built on DeepAgents. Gateway, Agent Worker, and Web UI for orchestrating autonomous AI agents.

AI Travel Assistant is a powerful AI-powered tool that helps users plan their trips effortlessly. It integrates flight search, hotel booking, and sightseeing recommendations to generate a structured travel itinerary using LangChain, Apify, and OpenAI

RAG chatbot applilcation with fastapi and docker

Public intelligence done by artificial intelligence: an LLM-based OSINT tool designed to perform deep web searches by orchestrating multiple web agents

Demo code and presentation materials for the talk "Bug Bounty Hunting with AI Agents" at Basel One 2025.

Docker image for a self-hosted LiteLLM AI gateway proxy. Unified OpenAI-compatible API for 100+ LLM providers. Features auto-config on first start, virtual key management, spend tracking, and persistent data via Docker volume.

Full-stack RAG template: FastAPI + LangChain LCEL + Next.js 14. Multi-KB retrieval, hybrid search (dense+BM25/RRF), FlashRank reranking, SSE streaming, RAGAS evaluation & JWT auth. MySQL + Chroma + MinIO.

AI-powered Design Authority — 5 specialist agents evaluate architecture decisions and deliver structured rulings in under 60 seconds

An AI-powered agile team for any software project. Ship with the discipline of a senior team — even when you're building alone.

A web application that analyzes food and creates a recipe for cooking it.

ARI — Artificial Reasoning Intelligence. Personal AI operating system with 7-layer architecture, three-pillar cognition (LOGOS/ETHOS/PATHOS), constitutional governance, and tamper-evident SHA-256 audit trails. Local-first. Multi-agent. TypeScript.

A comprehensive, vendor-agnostic framework for consistent AI-assisted development workflows - standardized instructions and commands that work seamlessly across Claude, Gemini, Copilot, and local AI models. See also: https://github.com/JacobPEvans/claude-code-plugins

A tool for unifying instructions, skills, and MCP servers for various coding agents.

Simple Code Analysis MCP server, language agnostic with code indexing and search capabilities.

A comprehensive Node.js Model Context Protocol (MCP) server for JasperReports Server REST API v2. This server enables AI assistants and developers to perform all major JasperReports operations including authentication, resource management, report execution, job scheduling, and administrative tasks through standardized MCP tools.

A2SPA — a security protocol enforcing cryptographic authorization at execution time for agentic AI systems.

Production-ready Python 3.13+ CLI/API system with Adaptive RAG, multi-engine TTS, OpenRouter key rotation, FastAPI backend, and Next.js dashboard

Prompt skill + renderer that adds generative UI to any LLM chatbot. No frontend refactor needed.