Code agents

A curated timeline of real AI agent security incidents, breaches, and vulnerabilities (2024-2026). Every entry sourced and dated.

Missing Xcode Tools Documentation

World's First Autonomous Open-source Pretrained AI Employees Platform

Learn to build, test, and deploy production-ready AI agents with this complete "From Zero to Hero" training course for the Google Agent Development Kit (ADK).

An ntfy MCP server for sending/fetching ntfy notifications to self-hosted or ANY ntfy.sh server from AI Agents 📤 (supports secure token auth & more - use with npx or docker!)

Detect shadow AI agents by monitoring network traffic and classifying process-to-domain pairs.

A minimal AI coding agent runtime. Pure bash + awk, zero runtime dependencies.

A skill to refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files into a compact routing entrypoint plus focused docs/ reference files.

Voice-first macOS menu bar app: dictate, voice-edit clipboard, read aloud, AI chat with Google/Trello tools, and live meeting notes. Bring your own keys (Gemini, GPT, Grok) or run offline with Whisper.

Runtime-neutral AI execution bridge for Claude Agent SDK, Codex app-server, and Agent Client Protocol (ACP).

Lightweight, secure Linux sandboxes for untrusted processes. Runs in the browser and on the server.

Skill de Claude Code para crear automatizaciones (agentes de IA) en Cloudflare desde cero, en español sencillo. Por Horizontes IA.

OpenStudio is a browser and desktop DAW built with React, Web Audio API, and Electron. It brings the core beatmaking workflow into one app: browse sounds, build patterns, arrange clips, mix tracks, and export the final track to WAV or MP3. The built-in AI Agent helps shape melodies, drums, instruments, mixer settings, and FX.

MyKG Knowledge Graph Engine: Turn raw files into knowledge graphs with induced ontology

Schema-as-code memory for AI agents in Obsidian: typed cards, entity dedup, link repair, update-in-place, and Ebbinghaus decay. Plain Markdown you own — a Claude Code skill.

transformers pytorch t5 text-generation arxiv:2109.00859 arxiv:2207.01780

Open-source bridge to use Kimi AI inside Cursor. Connect Kimi models to your AI coding workflow with fast setup, clean configuration, and reliable local tooling for code generation, refactoring, debugging, and agentic development.

EloquentJS monorepo — Laravel Eloquent for Node.js

Local-first CLI for coding-agent context handoff. Transfer and resume sessions across Claude Code, Codex, Cursor, Cline, Kimi, Antigravity, OpenCode, and Pi Agent.

Free, MIT alternative to paid Django schema review. Blast radius on every PR, schema drift, N+1 across functions, ER diagrams, MCP server. No DB, no Django boot, no Pro tier.

Context7 documentation lookup skill for AI coding agents. Lightweight REST API wrapper with no MCP context overhead.

1,486 real web design systems, extracted into machine-readable specs. An MCP server for AI coding agents — so what they build has taste, not just working code.

Open-source agent execution-recovery controller for coding and tool-using AI agents.

oh-my-codex (omx) — Orchestration layer for OpenAI Codex CLI. Async Claude Code delegation (no timeouts), structured workflows (autopilot, TDD, code review, planning), persistent state & memory. Like oh-my-zsh but for Codex.

Omnia Vault - the all-in-one project brain: an Obsidian LLM wiki, Graphify code graphs, a living plan that triages new videos against itself, and a Claude Code ⇄ Codex relay. Everything your project knows, in one clonable vault.

OwlMail is a self-hosted, AI-native email testing gateway for developers, CI pipelines, and coding agents. Capture, inspect, wait for, validate, and route application emails through REST, Webhooks, WebSocket, and MCP.

Tu asistente personal, directamente en tu ordenador. Habla contigo por voz, gestiona WhatsApp, atiende llamadas, consulta la web y recuerda lo importante. Una inteligencia artificial diseñada para trabajar de forma local, privada y autónoma, sin depender de la nube.

Context-efficient project search and bounded code analysis for Claude Code & Codex & Pi & OMP. and remote MCP clients, powered by ripgrep with stable cursors, source inspection, and structural evidence.

WeChat group & official-account AI knowledge digest — agent-friendly (Codex/Claude Code), Windows/macOS/Linux

Offline video material retrieval platform for semantic search, subtitle search, Agent API, and AI-assisted editing.

AI-agent skill for reproducible, validated GIS analysis — from authoritative data discovery to interactive maps, on an open-first geospatial stack (OSM, Overture, STAC, DuckDB, PostGIS, QGIS, MapLibre).

Windows 多账号 AI 内容生产工作台｜项目/CSV 任务、可恢复调度、执行意图门禁、原会话定位、产物绑定下载、本机受控 Agent 接口（--local-control / CLI / MCP）

A composable library of skills and rules for AI coding agents. Covers repo memory, long-horizon execution, multi-agent coordination, TDD, security review, and delivery automation.

With OpenCode, we can generate code for you in a variety of programming languages. Whether you're a seasoned developer or just starting out, OpenCode is the perfect place to get the help you need.

This project applies the core knowledge from the LLMOps module, including the design and implementation of the API Layer, Inference Layer, Observability Layer, Cache Layer, Guardrails Layer, Routing Layer, and the Data Ingestion Pipeline.

Agentic AI Use Cases with pgvector, Aurora PostgreSQL and Amazon Bedrock

Chat with any website using FastAPI, Next.js, and the latest LangChain version for seamless integration.

A Jupyter python notebook to Execute Zapier Tasks with GPT completion via Langchain

Whiskey AI lets you create autonomous AI agents without code. Connect APIs, automate Solana actions, launch tokens, run workflows, scrape data, monitor markets, post on Twitter, and trigger actions instantly. Build complex automation with simple natural language—no coding needed.

AI 文献检索与综述 Agent：支持多源检索、代码仓库定位、开放 PDF 下载、证据链与中英双语报告。

Creates an Langchain Agent which uses the WebUI's API and Wikipedia to work

Code for paper "Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent System"

한국어 STT 출력의 CER, WER, CRR, 키워드·개체명·코퍼스 평가를 제공하는 Python 패키지

Acid Reflux for your Ears!

🎓 课表解析 · 点名预测 · 逃课方案 · 反馈学习

Production-grade API to give your AI agents long-term memory without the boilerplate.

Code for running the implementations proposed in: Westny, T., Oskarsson, J., Olofsson, B. and Frisk, E., "MTP-GO: Graph-Based Probabilistic Multi-Agent Trajectory Prediction with Neural ODEs", IEEE Transactions on Intelligent Vehicles

Micro SaaS AI Starter with Next.js 14, React, Tailwind, Prisma, Stripe & GeneratedBy API

A comprehensive collection of 24+ specialized Claude Code sub-agents for enhanced software development workflows.

LLM agent to automatically set up arbitrary projects and run their test suites

Workshop "Build a Retail Copilot Code-First on Azure AI": attendee and presenter resources.

Unified Claude Code workflow: Superpowers + Beads + Templates. 413+ specialist agents on-demand.

Agent Fusion is a local RAG semantic search engine that gives AI agents instant access to your code, documentation (Markdown, Word, PDF). Query your codebase from code agents without hallucinations. Runs 100% locally, includes a lightweight embedding model, and optional multi-agent task orchestration. Deploy with a single JAR

Clawdbot skills for agentic coding workflows - ACFS stack, cloud CLIs, and dev tools

oh-my-codex (omx) — Orchestration layer for OpenAI Codex CLI. Async Claude Code delegation (no timeouts), structured workflows (autopilot, TDD, code review, planning), persistent state & memory. Like oh-my-zsh but for Codex.

AI Agent Orchestration Kanban Board — Route tasks to Claude Code, Codex CLI, and Gemini CLI with role-based auto-assignment and real-time monitoring

A persistent, local-first AI development daemon built in Elixir/OTP. AST-level code intelligence, Property Graph, runtime BEAM introspection, and semantic search — all via a 80+ endpoint REST API.

Give AI agents safe access to your database.

System monitor with offline AI (82 intents, 9-layer routing) that learns YOUR PC. TURBO optimization, thermal baselines, voltage SPC, ghost driver detection, 373 process definitions. optimization features, 11 months solo. No cloud, no API, your data stays local. MIT licensed. - Marcin HCK Firmuga - Build in Public (3 days series every week)

首款支持 CLI 化操作的微信公众号编辑器 — 让你的Agent直接写出精美推文

Two technical workshops from GenAI Hackathon Cairo 2025: build LLM apps with RAG & tools , and create a coding AI agent from scratch (Python).

Migrate Claude Code skills and Agents to Open AI Codex native skills and agents. Semantic mapping preserves original behavior, classifies migration risk (MECHANICAL / MANUAL / REFACTOR), validates structure, and tracks progress end-to-end. No manual rewrite required. Keep what you built. Run it in Codex CLI. Experimental.

Zero Code Studio 是一个工程化 AI 代码生成平台，基于 Spring Boot、LangChain4j、LangGraph4j，支持工具调用、Workflow 编排、任务计划规划、三层上下文压缩、SSE 过程可视化、定点修改与一键本地部署。

Open Vibe turns Claude Code, or your agent of choice, into the ultimate SaaS-building assistant, helping you understand the systems behind a production-ready SaaS while building your own app idea.

Universal MCP to LSP bridge - expose Language Server Protocol capabilities as MCP tools for AI agents

MCP server that gives AI coding agents (Claude Code, Cursor, etc.) full control over Unreal Engine 5.7 projects — headless builds & tests, Blueprint editing, actor manipulation, procedural mesh generation, and UE API documentation lookup.

Nylas CLI is a unified command-line tool for Nylas API authentication, email management (GPG signing/encryption), calendar, contacts, webhooks, timezone utilities, and OTP extraction

12 agentic skills for analog IC design — architecture, sizing, verification, cross-model review, knowledge graph, and self-evolution. Works with or without EDA.

Skills for agentic coding CLIs: output you can ship with minimal review, on work you can tell was worth doing.

Tired of paying for frontier AI models? Break free with this guide to 100% local, private LLM code generation on Apple Silicon. Optimized for 24GB+ Macs, it uses Ollama + Cline to build a disciplined, free agentic workflow. Learn to write system rules, configure custom Modelfiles, and run strict two-layer test suites.

Starter kit for building an agent harness, the map, guardrails, and feedback loops that let AI agents ship software reliably.

Open-source, self-hosted OSINT investigation platform: turn documents into a live, investigated entity graph. Autonomous agent, graph analytics (centrality, communities, pathfinding), keyless-first tool belt.

Interviews you, then scaffolds a self-running agent loop. Cross-harness (Claude Code / Codex / Hermes / OpenClaw).

Extension for the pi coding agent that intelligently routes each turn to the right LLM tier (high/medium/low) based on task intent, session budget, context size, and custom rules.

Pluggable extension packages for the Pi AI-agent runtime. Each package exposes LLM-callable tools via MCP — covering IM workspace integrations (Lark, DingTalk, WeCom), browser & computer automation, persistent memory, telemetry, task scheduling, image generation, web access, security policies, and more.

Claude usage widget for Windows

Use your OpenCode Go subscription in the Codex app. Local Responses-to-Chat-Completions bridge for all 13 OpenCode Go models.

Perseus Vault — durable, encrypted, time-aware memory for AI agents. One Rust binary, one file, local-first, MCP-native, MIT.

transformers safetensors qwen3_next text-generation conversational license:apache-2.0

A statistically-sound agentic build framework that employs agentic loops to create code artifacts (whether a script, a skill markdown file, etc). Crucially, it splits verification data into the classic data science-like dev, validation, and final test sets to avoid overfitting.

A tiny Rust gateway for running coding agents across model providers safely.

Planr turns product intent into a durable task graph that Codex, Claude Code, Cursor, MCP clients, and humans can share without losing ownership or evidence.

Self-hosted web viewer for Claude Code session transcripts — read, search, replay, and audit every session you have ever run

Visual Studio .NET extension that provides a better interface for Claude Code, Codex, Cursor Agent, Open Code, Devin, PI, Antigravity and Reasonix. Image/file paste, diff viewer, actions when AI ends work, usage tracking, session history and much more!

Open Source Legal AI assistant for MS Word as Plugin - contract review, playbooks, drafting, and legal research task-pane add-in.

The agentic node editor for live visual effects

Lossless storage and search for AI agent sessions, across every agentic client.

Keep Claude Fable 5 in the chair all day without draining your usage limit — token-frugal multi-agent orchestration plugin for Claude Code: tier routing (Sonnet 5 does the work), Requirements Ledger, enforced guard hooks, automatic teammate reaping

全网首个中文字体专业知识包：可商用中文字体库（授权三级分类）、场景×气质选字矩阵、中英混排与排版规则。让 AI 选中文设计字体不再甩给你一堆 Inter / Chinese font selection agent skill: license-safe free commercial CJK fonts, scene-based selection matrix, CJK-Latin pairing rules. Works with Claude Code / Cursor / Kimi / Codex.

transformers safetensors qwen2 text-generation code qwen-coder

Code for Agentic ESOpt: Fine-Tuning Long-Horizon LLM Agents with Minimal GPU Requirements

[RESEARCH PREVIEW] The open & extensible cybersecurity harness - by the Swiss Applied AI & Cybersecurity Research Lab.

Talk to your Claude Code agent out loud. Hold a key, speak, and it answers in a real voice about a second later, with all its tools and its own personality. The hearing and the voice run on free local models, no API keys.

Multi-Agent Handoff Inspector: analyze multi-agent handoff records, score context completeness, surface coordination bottlenecks, and render a review dossier.

Turn Claude Code into a senior software architect that orchestrates a team of specialist agents and audits itself. An 8-phase skill with TDD verified by mutation, phased decomposition, an event-driven PR pipeline, and quality gates with teeth.

A local AI gateway for AI agents, unifying your subscriptions and API providers with smart routing and on-device privacy protection.

One session. Two commands. Full team. Zero meetings.

Python Streamlit web app utilizing OpenAI (GPT4) and LangChain LLM tools with access to Wikipedia, DuckDuckgo Search, and a ChromaDB with previous research embeddings. Ultimately delivering a research report for a user-specified input, including an introduction, quantitative facts, as well as relevant publications, books, and youtube links.

A Telegram bot that proves you don't need a body to have a personality. Works with any OpenAI-compatible LLM; agentic tools, MCP, RAG over your files, memory, vision, voice and image generation.

A PyTorch Implementation of japanese chatbot using BERT and Transformer's decoder