Code agents

Local traffic control for multiple Codex chats on your Mac: missions, lanes, approval packets, and optional Telegram remote.

The Silence of Intelligence — A comprehensive analysis of Anthropic CEO Dario Amodei's philosophy on Scaling Laws, AI safety, and the future of humanity. / Anthropic CEO ダリオ・アモディの思想を体系化したOSS書籍。スケーリング則の本質とAIの未来を解き明かす。

Personalised Travel Itinerary Generator using RAG + LLMs

AI-powered code generator for Arbitrum Stylus, SDK bridging, dApps & Orbit chains — 19 MCP tools with RAG

A Model Context Protocol (MCP) server written in Go that empowers AI agents and Large Language Models (LLMs) to seamlessly interact with Kanboard. It transforms natural language commands into Kanboard API calls, enabling intelligent automation of project, task, and user management, streamlining workflows, and enhancing productivity.

emotional AI Companions for personal relationships

macOS Seatbelt sandbox CLI for developers. Protect credentials (SSH, AWS, GPG) from malicious npm packages, supply chain attacks, and untrusted build scripts. Deny-by-default filesystem isolation. Perfect for Claude Code agentic workflows with --dangerously-skip-permissions.

A CLI secrets store & dispatch tool built for AI agents. Authy stores encrypted secrets locally and dispatches them to agents with policy-based scoping, short-lived session tokens, and audit logging. No server required.

OpenAI Codex SDK written in Elixir

Claude agent sdk for Go(lang)

AI-powered Python CLI tool that automates the entire software development lifecycle using the Claude Code SDK. From specification to deployment, Claude Code Builder

Fast vector search in PostgreSQL

Agent skills distilled from the hard-won lessons of world-renowned programmers, in the spirit of "97 Things Every Programmer Should Know"

SFLO — Simon Factory Lights Out: a gated pipeline protocol for building software with AI agents

Enterprise-grade prompt engineering toolkit: Distilled best practices, production-ready meta-prompts, and a professional AI agent that transforms simple requirements into battle-tested prompts.

A community-driven repository of AI workflows, prompts, agents, tools and experiments from the WatchTower builders community.

Swift API Design Guidelines Agent Skill for AI coding tools that support the Agent Skills open format. It provides practical, structured guidance for API naming, argument labels, terminology, documentation comments, and conventions, with a workflow-driven `SKILL.md`, focused reference modules, and plugin/workflow support for team adoption.

Skill for AI agents to be a Valyu Search Expert

A lightweight and intuitive Node.js client for the Paxsenix AI API.

Spotlight for AI. A frictionless, pure AppKit macOS HUD that brings ChatGPT, Claude, and your other favorite LLMs directly into your workflow.

🧬 Build your own conversational AI in minutes (or seconds) with this customizable chatbot template, utilizing modern technologies like Next.js, Tailwind CSS, RAG, Pinecone, and powerful LLM/GenAI APIs (with chunk streaming!) including OpenAI, Fireworks AI, and Anthropic AI. Time to unleash your creativity and transform ideas into reality! 🚀

An overview of popular reranking models and architectures for 2 stage RAG pipelines

Extract a person into an AI agent — through an 8-week therapist-style interview, not a form. The open-source alternative to $4K AI clone courses.

AI Video Engine — Turn structured data into videos. JSON timeline → Scene components → HTML/MP4.

HackAI Morocco is a 4-day AI hackathon that brings together students from across Morocco for an unforgettable experience filled with innovation, challenges, and learning. This unique event combines technical excellence with creative problem-solving in the field of artificial intelligence.

Welcome to my Cybersecurity Homelab, where I experiment with ethical hacking, penetration testing, network security, AI Agent automation and system hardening. This repo documents the architecture, software stack, configurations, and automation scripts used in my self-hosted cybersecurity lab.

AI-Powered Development Framework for Claude Code — 70+ commands, 25 agents, 381 skills, quality gates

Installable AI coding workflow for risk-based routing, scoped sub-agents, and evidence-backed completion.

Demonstration of AI review of existing functional annotations

A high-performance, memory-efficient inference server for diffusion models (image/video generation), compatible with the OpenAI client

AI-powered voice recorder with transcription, summarization, RAG search, and Obsidian-compatible export. Record your day, let AI organize it.

A web-based analytics and visualization dashboard for data generated by entireio/cli

ESP32-S3 virtual pet with built-in WiFi security auditing, BLE peer interaction, Telegram control, and a full browser simulator.

🐙 AI-powered presentation builder with a conversational agent, live Marp preview, and lightweight presentation on your browser.

Agent Engineering experiment, practices, codes, specs...

Блог про AI-агентов, вайбкодинг и паттерны Claude Code

End-to-end behavioral testing skills, bare system prompts, and any agent runtime — run real scenarios in an isolated git sandbox, capture the full tool-call trace, and assert it against declarative YAML.

Whitebox & Blackbox red-teaming framework for LLMs & Agentic AI apps. It analyzes your app's source code to discover tools, roles, and guardrails, then generates new attacks chains across several categories and adapts over multiple multi turn rounds to find vulnerabilities

Text-to-SQL with GraphRAG on Knowledge Graph Semantic Representation of SQL Databases

Transform any HTTP endpoint into an MCP server. Aggregate multiple MCP servers, manage configuration profiles, and serve them through a unified gateway with multi-tenant isolation.

AI-powered Xiaohongshu (小红书/RED) automation — publish, search, engage, analyze. MCP + CDP.

Generates executable Proof-of-Concept for any bug in any project. AI agents discover and reproduce vulnerabilities — verified, not hallucinated.

A free GLM-4 AI chat client. Bypasses CORS via local Node.js proxy, supports context memory & streaming. / 免费 GLM-4 AI 对话客户端。基于本地 Node.js 代理解决跨域，支持上下文记忆与流式响应。

🦞 Clawverse — Build your pixel island, visit friends, collect everything. Built entirely by Genspark AI — 100+ autonomous coding sprints, 17,500 lines of code, zero human-written code.

Persistent cognitive memory for AI agents — drop-in MCP server for Claude Code, Cursor, Windsurf. Temporal decay, contradiction detection, knowledge graph, autonomous consolidation. Backed by the YantrikDB Rust engine. Install: pip install yantrikdb-mcp.

Hermes port of Karpathy-inspired LLM coding guidelines — SKILL.md + examples.

TSCG — Deterministic tool-schema compiler for LLM agents. 50-72% token savings, 50 tools in 2.4ms. Phi-4 recovers from 0% to 90% accuracy. 459 tests, zero dependencies, MIT.

DESIGN.md for Terminal UI — curated TUI design systems for AI coding agents. Source-code-level research from Claude Code, Lazygit, btop, k9s and more.

A collection of reusable AI agent prompts for development workflows.

Bitrix24 AI Agent skill: webhook/OAuth, events, retries, safety guardrails, and ops patterns

An AI-powered career agent built with LangGraph-based multi-agent workflows. Given a job description (JD) and candidate materials, it performs JD analysis, resume generation, interview Q&A simulation, and skill gap identification.一个基于 LangGraph 多 Agent 协作的求职辅助系统。给定岗位 JD 和个人背景材料，自动完成 JD 深度分析、简历定制生成、模拟面试问答、缺失技能信息等任务。

🐦‍⬛ SMTP for AI agents. No middleman.

454 standards-grounded Claude Code skills for every PDLC role. 8 roles, 57 plugins, 173 commands. Grounded in SWEBOK, TOGAF, OWASP, ISTQB, NIST, AIPMM. Every skill includes LLM error mitigation anti-patterns.

MCP server for .NET debugging — 34 tools for breakpoints, inspection, exception autopsy, code analysis, and more. Built on ICorDebug.

Skill pack that turns any coding agent (Claude Code, Codex, AGENTS.md-compatible) into a senior production engineer — FastAPI, PostgreSQL, Docker, deployment, security, observability.

🫛👣 FAVA Trails — Git-native, curated memory for AI agents via MCP. Draft isolation, promotion gate, thought lifecycle hooks, memory curation protocols, supersession chains.

Agent-native design skill: ordinary prompts -> verified HTML-first prototypes, decks, dashboards, motion demos, and export-ready visuals.

Self-hosted AI knowledge base with hybrid semantic search (pgvector + FTS + RRF), MCP server, multi-provider LLM inference (Ollama, OpenAI, OpenRouter, llama.cpp), multimodal ingestion (vision, audio transcription, speaker diarization), and knowledge graph. Rust + PostgreSQL.

The most complete Mailchimp Marketing API MCP server: 227 tools across campaigns, audiences, reports, segments, automations and full e-commerce, with multi-account support and runtime-security guardrails (read-only, dry-run, audit, per-tool risk metadata).

Round-robin proxy for multiple Claude Max subscriptions — multiply your Claude Code throughput with automatic OAuth token rotation and transparent request routing

把 Termux 里的真实本地 Codex 运行时做成 Android 手机上的触摸优先体验。

AI harness for and with Eclipse IDE with the focus on offline LLM with llama.cpp. Build with LangChain4J. Supports Ollama, LM Studio, llama.cpp, unsloth or cloud providers like with OpenA API, Anthropic Claude, Google Gemini, Mistral, GitHub Copilot. Contributions are highly welcome!

Local OpenAI & Anthropic compatible API server backed by ChatGPT/Codex OAuth credentials. Python, TypeScript, and Rust.

The complete toolkit for building AI agents in JavaScript. Lightweight core, React & Terminal UIs, autonomous runtime, tools, skills, memory, RAG and observability. Plug-and-play from chat UI to full agents.

A composable framework for building reliable LLM agents on a harness you fully control. The same code runs the agentic loop on every model tier, local 4B to frontier with tool-call healing, verification, and durable crash-resume, on a typed 12-phase engine where every step emits an event you can hook into. Effect-TS, MCP-native, MIT

One OpenAI-compatible endpoint for all your AI providers

cmux MCP server — 42 tools for terminal agent lifecycle management. Spawn, monitor, and orchestrate Claude, Codex, Cursor, Gemini, Kiro agents. Thinking-state detection, chunked input, layout management.

Agentic sandbox enumeration: find security issues, and seed escape automation.

An open-source AI agent platform for orchestrating, and collaborating with multiple AI agents. Connect seamlessly to GitHub Copilot CLI, Claude Code, Codex, and any ACP-compatible agent.

108 agents, 15 skills, smart model config, and interactive CLI for OpenCode — npx @weisser-dev/awesome-opencode

Declare the outcome, skip the logic. The developer-first infrastructure engine for structured, multi-turn AI conversations with built-in safety, async follow-ups, and native compliance

Type-correct, brand-aware HTML deck builder for Claude Code. Pitch, sales, launch, keynote, all-hands. PDF and PPTX import.

Open-source agent skills library for building SaaS, marketing systems, creative assets, and frontend design workflows

This is a framework intended to help developers build applications in VBA that interact with OpenAI's large language models like GPT4, DALL-E and ChatGPT

Tiny Node.js CLI that prints banked Codex reset credit expiry dates from local Codex Desktop auth.

An 8-stage AI vulnerability-discovery agent.

The trust layer for people and AI. Portable identity, context, and authorization that travels.

Make every model a CodeX engine through an OpenAI-compatible Responses API gateway

VL-JEPA inspired pipeline — compress images/text locally via Ollama, send compact payloads to any LLM API. Cut token costs by ~80%.

Spec-first rails for agent-assisted repository workflows.

OpenTelemetry instrumentation plugins for JavaScript-based AI coding agents. Collect traces, tool calls, and LLM metrics from Claude Code and OpenClaw — zero code changes required.

Real-time meeting & audio transcription for Windows (system audio + mic) — live captions via Deepgram, AI summaries via OpenAI. Tauri 2 + React.

⚡ The ultimate collection of 136+ OpenCode Skills (Codex Subagents port) featuring auto-sync and 1-click deployment.

trmnl.com template writer agent's prompts and skills

Massive multi-source academic literature search for Claude Code — one skill fans out subagents across 20+ scholarly databases (arXiv, Semantic Scholar, Crossref, OpenAlex, PubMed, …), merges into a deduplicated ranked corpus, and acquires the original PDFs.

Open & nano reimplementation of Sakana Fugu. A repo-native, multi-agent coding loop powered by 9+ LLMs (isolated via Claude Code) and an independent Codex reviewer. Lightweight, bounded, and self-improving (Self-Harness)—no coordinator training required.

OpenMontage: 100% Free Local AI Video Production System using Ollama and FFmpeg

AI agent for JetBrains IDEs: debugger, refactorings, and symbol navigation via IDE — fewer tokens, more precision

Connect a personal Zalo account to the Hermes Agent gateway via zca-js (unofficial Zalo API). Cross-platform plugin: macOS, Linux, Windows.

Compile an AI agent's repeated workflows into deterministic, auditable routines that replay for free, with a fallback to the agent.

Agent skills for Odoo addon development and OCA module migration

去 AI 味设计系统库 · 6 美学家族 × 64 套设计系统 · 复制一段提示词粘给任意 AI 就出片不飘 · 含在线预览站 | Anti-slop design systems for any AI — 64 curated design systems across 6 aesthetics, copy-paste prompts, live demo.

Graph memory for AI agents — decisions, context, and session history that survive across every conversation. Works with any LLM.

AI Game Developer for Unreal Engine — MCP plugin (C++ editor plugin + .NET bridge), unreal-cli, connects Unreal Editor to AI agents via ai-game.dev or a local MCP server

Self-contained Codex skill for ad-hoc development sessions on session branches.

transformers safetensors gguf qwen2 text-generation code

transformers safetensors qwen2 text-generation code codeqwen

transformers safetensors qwen2 text-generation code codeqwen

基于 FastAPI + Vue 3 构建的智能客服系统，具备 RAG（检索增强生成）与 AI Agent 核心能力，可为企业提供高效、可扩展的智能客服解决方案。

Declare the outcome, skip the logic. The developer-first infrastructure engine for structured, multi-turn AI conversations with built-in safety, async follow-ups, and native compliance