Code agents

Analyze how you work → build automations that actually run. One skill per day for Claude Code, Codex, Cursor.

AI Skills Manager (ASM) enables team members to create, test, distribute, install, update, and remove skills from their projects and user space.

PAPPO is a patch-aware reinforcement learning algorithm and experimental RL framework for tool-using coding agents. It provides turn-level credit assignment, PPO training utilities, rollout extraction, critic baselines, benchmark runners, and reproducible evaluation pipelines for repository repair tasks.

A modular AI Agent framework designed for complex task orchestration and logic reasoning.

Prediction-market agent arena for AI agent evaluation, paper trading, practice rounds, contests, and leaderboard-based battle testing.

Dynamic workflow tooling for Codex: planner/replanner orchestration, Codex CLI process swarms, broker evidence, and benchmark reports.

IDE-agnostic deep-research framework for AI agents: maps a topic wide, commits to depth on purpose, adversarially verifies its findings, and synthesizes them into a backlinked, primary-sourced Obsidian vault. Works in Claude Code, Cursor, opencode, or any agent.

Open-source multi-agent AI algorithmic trading system for Interactive Brokers & MetaTrader 5 with consensus-based execution, risk management, and broker reconciliation.

A generic, batteries-included, async-first agent toolkit — configurable loop, tools, security guards, streaming, persistence, and MCP. Import as 'agentix'.

Multi-agent synthetic-audience evaluation — parallel eval agents that score content and code before ship

AI Agent Error Doctor: paste MCP / LangChain / CrewAI tracebacks, get root cause, exact fix, and verification steps.

AI-powered IDE featuring intelligent coding agents, auto-suggestions, quick edits, and modern developer tools for a faster and smarter coding experience.

Local-first governance framework for AI agents. Tamper-evident audit logs, pre-execution gatekeeping, kill switches. No tokens.

Set of skills and workflows to ensure humans and agents stay focused while vibe-coding.

The lightest CLI agent for Python. No heavy deps, no complex chains. pip install, set your API key, and run AI tasks anywhere.

Evolver is a dual-mode AI that evolves to become a better coding assistant. In 'Evolution Mode', it collaborates with you to improve its own source code. In 'Execution Mode', it uses its evolved protocol to solve programming tasks. Guide its development and test its growing capabilities in a unique human-AI partnership.

A lightweight, browser-based AI pentesting assistant that lets non-experts run security scans safely and intelligently

Token-aware analyst/worker workflow and token ledger extension for Pi Dev coding agents.

Codex plugin for visual fidelity gates in AI-driven UI implementation workflows.

Telegram bot from hell - Claude Code behind a Forum Topics UI

A predictable, terminal-native coding agent for Next.js, Nest.js, Prisma and Node.js projects.

MCP server for Botwallet — Give any AI agent a wallet via Model Context Protocol. FROST threshold signing, x402 paid APIs, spending guard rails.

LLM-powered, channel-native Discord agent for the POAP KINGS Clash Royale clan — event-sourced reactive engine, scoped public/leadership memory, and GitHub-backed poapkings.com publishing.

Autonomous coding agent as an SDK, IDE extension, or CLI assistant.Open-source AI coding agent with Plan/Act modes, MCP integration, and terminal-first workflows. Trusted by developers worldwide.

Full-screen live sports scoreboard dashboard skill for Claude Code

AI-powered tool for automated root cause analysis of CI/CD pipeline failures. Fetches logs from Jenkins or GitHub Actions, classifies errors using regex, semantic, and LLM-based methods, and emails structured incident reports to the right team. Supports both HTTP API and CLI modes. Self-learning for faster, smarter diagnostics.

AI Station Navigator is a modular AI workstation based on Claude Code. Install a ai skill in one prompt; execute a skill-flow in two. | AI Station Navigator 是一款基于 Claude Code 的模块化 AI 工作站。一句话安装技能，两句话运行工作流（skill-flow）。

🤖 An AI-powered DevOps agent implementing ReAct architecture to automate mobile release pipelines (Crash Check -> Perf -> Build -> Audit). Built with LangGraph & Ollama.

Kiro Power: Protect your codebase from prompt injection, enforce write-protected paths, and establish security incident response for AI-assisted development

The Claude Code plugin for Hades — Unity-aware AI infrastructure. Install via the marketplace; built from [TheArcForge/Hades].

通用的 AI 实验报告生成工作流：真实跑实验 → 前端可视化 → 规范截图 → md+docx 双交付。第一原则：实验真实跑通、数据不许编造。

It's a university final-exam review assistant skill.

A coding agent that edits real repos with workspace tools (read/write/search/run), produces JSON traces with token accounting, and renders runs on a live dashboard.

Patent Creator是一款Benchmark驱动优化的专利构建Agent

小红书自媒体编导 AI workflow：账号定位、选题策划、脚本创作、发布日历和内容复盘，可用于 Codex /OpenCLaw / Claude 等 AI Agent。

Graph-based runtime for building, running, and debugging LLM agents in Go.

Thread-scoped runtime contracts for Codex and Claude Code, powered by MCP, local SQLite, Web UI, and UserPromptSubmit hooks

A self-evolving scaffold for autonomous web projects. 9 workflows, hourly self-evolution, self-healing pipeline, feedback learning loop. The repo is the system.

Enable AI agents to share memory across tools and avoid repeating work when switching between tasks or platforms.

Agent Learns you, not the world.

A pip install defense layer that constrains AI coding agents through enforced protocols; not prompts. Pre-flight checklists, HMAC-signed session audits, shell command boundaries, 35 drift checks, and a document type system that prevents docs from becoming lies. Works with any agent: Kimi, Claude, Copilot, Codex, custom.

Code with your phone. Run AI coding agents (Claude, Gemini, Codex) on your machine, control from your phone.

A local-first cognition core: typed, evidence-tiered, provenance-tracked memory assembled into prompts with explicit epistemics. Zero core dependencies — Python + SQLite + your own model endpoint.

Universal context orchestrator for AI coding agents. Manage skills, memory, and rules across Claude Code, Cursor, Copilot, Windsurf, Gemini, Codex, Cline, and 15 more tools from one local dashboard. Zero dependencies.

Lightweight workflow guardrails for AI-assisted engineering.

Less admin, more games. AI agent tools for Codecks.io — CLI-first for token efficiency, 52 MCP tools for power users. Also a standalone CLI and Python API.

Powered by Deepseek/Qwen/Chatgpt/Gemini. Purely vision recognize and auto UI control AI agent.

A domain-ontology-driven agentic framework for LLM-based personal-finance reasoning across banking and personal-investments, with formal Action / Provenance / Constraint axes around the agent loop.

A cognitive runtime that gives LLM agents persistent state, identity, and learning across turns. Memory, beliefs, drives, self-evolution, skills, and affective state — engineered scaffolding outside the model.

🤖 AI-powered Digital Marketing Assistant — content creation, strategy, research & analytics via Telegram. Bilingual EN/ID, Notion integration, pluggable LLM, security-hardened.

The project uses Memory Based- RAG for healthcare queries, searching FAISS vector database for relevant answers. If no results are found, an AI fallback mechanism steps in. The AI Agent employs Selenium headless drivers, automation, web scraping, etc techniques to enhance search efficiency, ensuring accurate, real-time responses.

Native iOS app for your self-hosted Hermes agent — live chat, approvals, push, Live Activities. Pairs with a hermes-agent gateway you run.

A curated list of the best AI agent, orchestration, and LLM developer tool repositories

Developer-focused MCP server with 22 tools for code analysis, Python editing, JSON repair, imports, encoding, Markdown/PDF export, diffs, and regex testing

A worked example of an agentic job-search pipeline — the Claude Code skill I ran during my 2026 job hunt.

An agentic data platform for e-commerce analytics, combining data engineering pipelines, a serving layer, and multi-agent orchestration, with a clear path toward GenAI, MLOps, DevOps, and cloud deployment.

A curated, credited library of loops — repeatable AI-agent workflows for Claude Code, Cursor & Codex. Refactor until clean, test until 100%, hunt bugs until none remain.

Rust-first, local-first observability & debugging for LLM agents: capture, inspect, replay, diff, and export traces (OpenTelemetry-compatible).

A curated collection of research agents, skill libraries, autonomous research loops, paper-writing pipelines, MCP servers, and benchmarks built around Claude Code, OpenAI Codex CLI, and adjacent coding-agent CLIs for AI/ML research.

MCP-native shared memory for Claude Code agents — hybrid BM25+vector+RRF recall, cross-session continuity, cognitive scoring, knowledge graph. Self-hosted, $0/query. 30 MCP tools.

Codex skills for AI agent paper reading and minimalist academic presentation decks

A dangerous-capability eval for autonomous smart-contract vulnerability discovery: LLM agents (discover, verify, judge) scored on precision, recall, and cost against a labeled corpus and baselines.

Stripping/Compacting files to burn less tokens for coding agents.

GitHub-native framework for AI-assisted projects: role separation (Architect / Builder / Reviewer), universal handoff schema, surface-file synchronization, claimed-action verification, and deterministic enforcement via Actions.

Sistema multi-agente de ciberseguridad ofensiva/defensiva construido con LLMs. Orquesta 6 subagentes especializados (OSINT, pentesting, hardening, forense) sobre un laboratorio Docker aislado, integrando herramientas reales (nmap, Hydra, nikto) para generar reportes estructurados de hallazgos y remediación. Proyecto de aprendizaje.

Persistent memory and session handoff for AI agents — provenance-labeled context, gated writes that can refuse, hostile test suites. Manual + six working examples.

Youtube assitant using OpenAI, Langchain, and FastAPI - Using this API you can ask questions directly to your favorate podcast.

Chat-with-LLMs is your one-stop destination to try out and compare the latest large language models from leading AI providers.

🎬 RAG Chat with YouTube — A lightweight end-to-end RAG app built with FastAPI + LangChain + Streamlit. Upload a YouTube video URL, extract its transcripts, embed them using Google Gemini embeddings, and chat interactively with the video’s content. Perfect for exploring context-aware LLMs, video summarization, and semantic search

Simple AI search and summarising agent

An automated talent acquisition pipeline designed to streamline candidate screening using Agentic AI. This project uses LLMs to parse resumes and job descriptions, ranking candidates based on semantic alignment, with full observability provided by LangSmith.

Local-first autonomous coding agent — Claude Code style task execution, LangGraph, Ollama, zero cloud dependency

AI Review Summary for Restaurants

Aora is an application designed to leverage AI for advanced document handling and natural language processing. This repository contains both backend and frontend components to get the application up and running.

A lightweight RAG for embedding and querying codebases. This service allows users to download GitHub repositories, process their code, store it in a vector database, and query it using natural language to retrieve relevant code snippets. Perfect for building intelligent code search and analysis tools.

Aplicação Web Pessoal (SaaS) open-source. Unifica Finanças, Saúde (Bio-tracking), Produtividade e Agenda em um Dashboard de BI integrado. Construído com FastAPI, React 19 e Agentes de IA (LangGraph).

Reference materials for the Udemy course: Agentic AI Engineering on AWS

InternNova is an AI-powered internship and application management platform. Built with a microservices architecture, it features automated resume parsing, AI-driven candidate evaluation, and LaTeX-based PDF resume generation using LangChain and LLMs.

A free, self-hosted alternative to LangGraph Platform's Cron Jobs with the same API interface (compatible with langgraph-sdk).

Extract Amazon customer reviews of select products via a third-party educational web scrapper, analyze them with LLM, and display concise summaries using an interactive user interface.

Created AI-powered applications that can answer your questions based on a PDF document.

Agentic system built with LangGraph, LangChain, Gemini 1.5 Pro, Tavily API, FPDF & Streamlit — automates deep company research, performs intelligent web crawling, and generates structured PDF reports with citations and zero manual effort.

☄️ SlackBeam is a self-hostable slack bot that helps teams generate social media content for X (formerly Twitter) directly from Slack.

An intelligent pipeline that automates lead generation and contextual enrichment from raw CSV data. Real-time keyword filtering via SerpAPI, Contextual data tagging using Groq’s LLaMA3-powered LLM CRM-ready CSV outputs with seamless export support

QueryPilot -Production-ready multi‑agent Text-to-SQL API for Postgres. Schema‑aware LangGraph pipeline with ChromaDB + sentence‑transformers, Neon-backed DB, and full evaluation on real ecommerce & library schemas.

LangChain Practice Tasks using FastAPI and LCEL

Capture macOS dictation accurately without rewriting your words, keeping your input true to what you speak and avoiding common app issues.

This project focuses on developing a Retrieval-Augmented Generation (RAG) system tailored for Contract Q&A.

A AI-Based Ad Generating - Marketing Assistant.

🔮 Turn any AI-written code change into a gamified, interactive walkthrough, gaming experience

RadioRAG: Online Retrieval-Augmented Generation for Radiology Question Answering

🚪 Governance gate for AI agents. Enforce policies before deployment: request contracts, operational safeguards, identity boundaries, action budgets. CLI tool with YAML config, JSON/text output, CI/CD integration.

Trace and debug AI agent behavior locally with a step-by-step visual tool that stores data offline for clear inspection and faster development.

AI-driven prompt generation and evaluation system, designed to optimize the use of Language Models (LLMs) in various industries. The project consists of both frontend and backend components, facilitating prompt generation, automatic evaluation data generation, and prompt testing.

End-to-end system for transcribing clinical audio and predicting relevant ICD-10 codes.

Multi-Modal RAG: An AI-powered pipeline for extracting, chunking, and summarizing content from PDF documents using advanced chunking strategies and generative models. Includes support for text, tables, and images, with vector search and retrieval via ChromaDB.

Automate penetration testing tasks with an LLM-driven multi-agent framework designed for security assessment.