Code agents

Synapse: A background AI assistant that instantly answers any highlighted question and copies it to your clipboard.

An AI functional testing project

A unified standard for AI coding assistant configuration. One .ai-rules file that works with all AI tools - no more managing separate rule files for each assistant.

cogniG is a full-stack multimodal AI chat platform built with the MERN stack and powered by Google Gemini. It supports persistent threaded conversations, real-time web grounding, image understanding, code execution, and a modern real-time chat interface with animated AI responses.

BeeGen is an intelligent command-line tool designed to assist developers with everyday tasks, leveraging the power of generative AI.

Mobile-first frontend for TaskWizard — a smart AI-powered task breakdown planner. Built with Expo + React Native, connecting to a FastAPI + Ollama backend to generate actionable step-by-step roadmaps from any goal.

AI-powered Kubernetes CLI tool for analyzing, auditing, and troubleshooting resources.

Iron Man-inspired AI desktop assistant | Claude API · Voice I/O · Live System Monitor · Animated HUD | Python

The Internship Matching System is a web-based platform designed to facilitate the process of internship placement for Data Science and Artificial Intelligence students. The goal of the system was to bridge the gap between students, companies, and academic supervisors by providing a centralized and organized environment for internship applications

⚡ Enterprise B2B Transactional API. Built with FastAPI & PostgreSQL, featuring AI-powered intent extraction, robust concurrency control (pessimistic locks), and automated CI/CD to AWS.

RecipeScout is an AI-powered iOS recipe discovery app featuring Sage, an intelligent cooking companion powered by Anthropic's Claude Sonnet 4.5, built with SwiftUI and Swift 5. Experience context-aware conversations, time-based meal recommendations, smart meal planning, and auto-generated shopping lists. Showcases SwiftData, MapKit & MVVM design.

Modern AI assistant with a minimalist design and a smart model

This project is a Conversational AI application designed to interact with users using natural language. It can be used for chatbots, virtual assistants, or customer support automation.

UltraCodeAI is an innovative AI-powered IntelliJ plugin that transforms coding with seamless assistance. It supports local/cloud LLMs like Ollama, OpenAI, and Groq for context-aware prompts, auto code error analysis, and RAG-enhanced insights. Features includes tabbed UI for chat, diagnostics, and recommendations; hover explanations; design pattern

AI-powered personal OS with autonomous agents, progressive security, custom agent creator, and multi-channel messaging

Talk to AI — it talks back. Built with Whisper + Groq + FastAPI

A basic sample of the AI Travel Tool WordPress plugin.

Client d'assistant IA pour l'API Albert de la DiNum

♜ Deploy OpenClaw AI agents in one click. No credit card, no DevOps, no headaches.

青龍 Seiryu — AI 記憶與傳承模組。讓 AI 的記憶不再隨視窗關閉而消失。基於 LDRIT（生死遞迴智能理論）設計。

Open-source desktop IDE for Oracle 9i through 26ai — SQL editor, PL/SQL debugger, AI assistant, vector search and REST API builder. Apache 2.0.

Voice I/O MCP for AI coding agents — local TTS + STT, 10 tools with ToolAnnotations

🦞 Manage multiple AI agent teams working together in isolated workspaces for continuous, multi-channel assistance.

📝 Markflow is a modern web editor for writing Markdown documents and Marp presentations with real-time preview and export options.

An AI chatbot backend built with Rust, Axum, and Google Gemini API. Features a REST API server and an interactive CLI client.

A powerful Chromium extension that leverages the multiple AI APIs to assist with various text operations, image analysis, and PDF processing.

🎤 Real-time voice AI conversational agent with LiveKit, FastAPI & React. Features natural speech processing, streaming TTS, and intelligent turn-taking for seamless voice conversations with an AI travel assistant.

ИИ-консультант для сайта клиники. Ассистент консультирует по услугам, стоимости и расписанию врачей и записывает на приём.

Open Meet Sum is an AI assistant for physical meetings that automatically transcribes, summarizes, and analyses audio with human-in-the-loop collaboration. It's a self-hosted solution, supporting both local, model API endpoints and built-in transcription engines.

🧠 Enhance your AI coding assistant with a universal knowledge base and rules system, compatible with any project and editor.

An MCP server that automatically fixes broken Selenium test locators when UI changes occur, reducing test maintenance overhead.

🌱 智能提示词生成器 - 将想法转化为AI就绪的开发提示词 | AI Prompt Generator - Transform ideas into AI-ready development prompts

Govern and orchestrate AI coding agents — Claude Code & Codex automation with skills, approvals, notifications

AI-powered trading bot for crypto and stock markets. Leverages machine learning, real-time market data, and technical indicators to automate strategies, optimize risk, backtest performance, and support multi-exchange trading. Modular design for custom strategy development.

DevSphere is a Flutter & Firebase-based developer platform for sharing posts, solving coding queries, and earning XP through contributions. It features an AI-powered assistant bot (Gemini API) and a sleek, Material Design UI for both mobile and web.

A native VSCode extension for visualizing and tracking Kiro spec features and tasks directly within your IDE.

Robot In The Loop (RITL)

A professional AI coding assistant with a minimal TUI interface and seamless VS Code integration and context window

A virtual assistant for linux make out of glue. Whispercpp, vosk, speech dispatcher and Ollama.

abaritbot: AI assistant using RAG and openAI API.

Claude Code embedded in Zotero sidebar for research chat, local context, and workflow automation.

专为企业出差打造的智能小助手，帮你快速摸清差旅规则，轻松选合规酒店，省心安排全程行程。

AI chat in a sidebar. Use your own API keys. Works with ChatGPT, Gemini, and Claude.

model-agnostic, local-first ai coding assistant

Jarvis Assistant accelerates Google searches, presenting users with brief data snippets and relevant links. Utilizing web speech and text-to-speech APIs, it simplifies voice-to-text conversion for quick responses. Please note, mobile compatibility is restricted due to stringent autoplay policies.

A geometric memory database with importance-stratified shells, HNSW acceleration, and mass-weighted decay scoring. Zero to hero: SQLite → 10M+ records.

A rapid deployment template for building RAG-powered applications using Vertex AI Studio and Vertex AI Search.

AI Chatbot for College Enquiry Automation NLP Assistant.

Minimal, secure personal AI agent — Claude Agent SDK + Telegram + MCP

AI-powered observability dashboard for Proxmox. Visualizes your infrastructure as an interactive topology graph with a local LLM chat interface for real-time diagnostics.

Deliver production-ready Flutter UI components designed for AI coding assistants to create polished, user-friendly apps efficiently.

CLI-native state persistence for AI agents — tasks, memory, state, and queues. One binary per primitive. No setup. No infrastructure.

A general-purpose SQL tool for Strands Agents — supports PostgreSQL, MySQL, and SQLite via SQLAlchemy

A modern desktop application for managing and organizing AI prompts with dynamic variable substitution. Built with Python and Flet.

Persistent memory for AI agents using git refs. MCP server + Claude Code skill. No vector database, no embeddings, no daemon — branches are scopes, push/fetch is sync.

See what your AI coding agent actually did. Local audit of Claude Code session transcripts: leaked secrets, risky shell, unsafe edits, hook bypasses. Cursor + Windsurf adapters on the roadmap.

Static analysis engine that maps any codebase into ranked, token-budgeted context — offline, zero LLM cost

MCP server for MSSQL with dynamic per-request connection args (read-only by default)

Let your claude-code get second opinion and review cc execution results from Deepseek

Ground Control for Claude Code

Open Agent Skills for carbon emission factors, carbon accounting, and sustainability AI

Plugin for Claude Code and Codex that turns freeform briefs into validated, cross-doc-consistent PRD packages. Explicit uncertainty labels (TBD / Proposed / Assumed), 16 quality gates, multi-stack, multi-language.

A curated collection of CLI tools designed for AI agents — classified by domain, tagged, and reviewed. Productivity, research, project management, and more.

Vision AI "Cortex" for Agents. A Playwright-based MCP Server & API that captures screenshots with ground-truth DOM extraction and full auth state injection. Containerized.

MCP server for Invoice Ninja v5 API - manage clients, invoices, quotes via AI

SmartEdu AI V2 is a lightweight system that turns your study materials (PDF/DOCX/PPTX) into simple, meaningful multiple‑choice questions (MCQs). It uses a Retrieval‑Augmented Generation (RAG) pipeline built around Google Gemini for both embeddings and text generation, with a minimal in‑memory vector store for fast, local retrieval.

🧠 Persistent project memory for AI coding agents. Your agent never forgets, never drifts, never re-asks. Works with Claude, Cursor, Windsurf & more.

TraceCC gives AI agents a CLI-native long-term memory over their own session history. Searchable, scoped, and sized for context windows.

Real-machine, real-browser web perf measurement with ~99% iframe coverage. LLM-native + AI-agent-loop ready.

network-ready (sse) MCP server bridge. Search and Fetch web pages for AI agents using SearXNG. docker, k8s, nomad ready. 5Mb only !

Weekly security audits of remote MCP servers. OAuth 2.1, PKCE, DCR, token hygiene, and the spec gaps nobody's reading.

Study of Claude Code's agent harness internals — architecture analysis, token budget breakdown, offline ops guide, and a Rust reimplementation with 6 crates and MCP support.

Production-ready MCP server template with async PostgreSQL, OpenTelemetry observability, tool-level security, Docker and Kubernetes Helm chart. Zero to deployed in 10 minutes.

Serverless MCP (Model Context Protocol) connector for Google Contacts on AWS Lambda. Per-user OAuth 2.1 authentication with privacy-first design. Enables AI agents & LLMs like Claude to access Google Contacts via People API in real-time. Zero contact data storage. Works with Claude Web & Desktop.

A small web app for evaluating LLM outputs systematically. Define test sets, define agents, run them against an LLM-as-judge, compare the diff. Ship prompts with numbers, not vibes.

Working code for specific AI agent capabilities. Each tutorial shows the build, the failure mode you will hit, and the fix. Clone, run, adapt.

Evidence-backed execution harness for AI coding agents: plans, gates, artifacts, codebase memory, learning loop, and verified claims.

Reconnaissance for Roblox game devs and their agents — open-source MCP server + CLI for Roblox game analytics.

Comprehensive Claude Code agentic scaffold — workflow rules, auto-memory pipeline, FORGE feature loop, hooks, skills, and flavor packs. Extracted from a production SaaS codebase.

Claude Code skills for AI-assisted PRD execution — decompose requirements into atomic REQs, enforce brainstorming before coding, track status per-REQ, and maintain git discipline from first spec to final commit.

The agent-native document editor — docs, integrations, and agent skill files for Comment.io

ThemeContext MCP Server -- Up-to-date themes design token for LLMs and AI code editors

Control your running browser on macOS via AppleScript — for AI coding agents. No restarts, no special flags, full access to your existing sessions.

A curated collection of Claude AI skills that extend Claude’s capabilities for real-world use cases. Includes plug-and-play tools like AI code explanation with Mermaid diagrams, workflow automation, and developer productivity enhancements. Each skill is modular and easy to install within Claude.

High-performance semantic tool search for Claude Code. Save 97% tokens with intelligent MCP tool discovery using embedding, BM25, and regex search methods.

Thordata Firecrawl – Firecrawl-compatible web crawling & scraping API built on Thordata, turning any website into AI-ready Markdown/JSON/HTML/screenshots.

Claude Code skill for Solidity smart contract security audits - OWASP SCSVS/SCSTG coverage, Slither integration, 11 security domains. By Demeter Financial.

As the AI ecosystem shifts toward autonomous local agents (e.g., AutoGPT, Claude Computer Use, custom LLM tools), developers are amassing massive directories of "Skills"—snippets of Markdown (.md), JavaScript (.js), TypeScript (.ts), and Python scripts that give agents their capabilities.

Persistent SSH, SFTP, port forwarding, and Docker over MCP. A long-running daemon so sessions, tunnels, and PTY shells survive across Claude Code / Claude Desktop / Cursor / Codex CLI restarts.

MonkeysLegion-Apex is a provider-agnostic AI abstraction layer that unifies LLM interactions across Anthropic, OpenAI, Google (AI Studio + Vertex AI), and Ollama behind a single, type-safe PHP 8.4 API.

Production-grade Claude Code plugin: control your personal Telegram via MTProto (Telethon). 120 typed MCP-tools, 9 resources, 7 prompts, 6 skills, 4-layer PreToolUse safety net, channel-push & permission relay

SQL-like DSL for Chroma DB

Runtime guardrails for AI agents that enforce token budgets, loop limits, and tool rate limits locally.

Search AI podcast quotes by topic — find what Lex Fridman, Dwarkesh Patel, No Priors, and Latent Space guests are actually saying. Universal agentskills.io skill compatible with Claude Code, OpenAI Codex, Hermes Agent, OpenClaw, and any other agent that supports the open skill standard. Powered by podlens.net.

Self-learning memory for AI coding agents — MCP server

OpenStreetMap MCP server providing precision geospatial tools for LLMs via Model Context Protocol. Features geocoding, routing, nearby places, neighborhood analysis, EV charging stations, and more.

Fast, secure, client-side tool to bundle your codebase into a single text file for LLM context.

Deterministic /compact alternative for Claude Code. Compresses JSONL sessions 4-10% without LLM summarization. Zero hallucinations, full error preservation.