Code agents

The authorization kernel for AI agents. Block, allow, or escalate agent tool calls with YAML rules — deterministic-first, LLM fallback.

🚀 Build AI Agent Teams as Production-Ready APIs. Orchestrate CrewAI agents with FastAPI for enterprise-grade AI services. Leverage Groq's lightning-fast LLMs to deploy collaborative AI workflows at scale.

A YAML-driven multi-agent simulation platform for economic and social systems. It combines LLM-backed agents, market microstructure, relation graphs, and world events behind a FastAPI API and a React client.

USB-portable offline AI assistant. AES-256 encrypted history, Turkish-tuned LLM (Trendyol), RAG over PDF/DOCX. KVKK uyumlu, %100 offline.

PandaGenie's official modules source code

AI SEO platform created with nuxt

AI code editor + terminal coding agent, built in Rust. Works with any LLM via OpenRouter, OpenAI, Anthropic, or Ollama. 20MB native binary, 20 themes, real terminal, git, agent sidebar with tool calling.

让 Claude Code 住进你的微信——收消息、发文件、定时问好、远程审批

🥋 Claude Code plugin that teaches programming while you vibecode — contextual explanations, micro-quizzes, and belt progression. Free & open source by Dojo Coding.

Browse, search and download AI agent skills

Minimize LLM tokens from Python objects, code, logs, diffs, and more. Zero deps. Ultra-Lightweight.

Agent Skill: Self-improving learning system - detects friction, proposes improvements | Claude Code compatible

Credential isolation for AI agents. Local-first transparent proxy — your agent never sees your API keys.

A Python-based logical reasoning system combining rule-based engines with Large Language Models (LLMs) for business automation. Supports deduction and hypothesis testing, partial fact completion, and automated fact retrieval via documents or chat. Features include explainable reasoning, workflow integration, and customizable knowledge bases.

A FastAPI-based Retrieval-Augmented Generation (RAG) system for legal document analysis, powered by Pinecone, LangChain, and Llama 3.3

A multi agent healthcare assistant system implemented using Python and Langgraph. The agents include icd10 code extractor, SOAP document generator and medical image report generator. This project uses one of the latest LLMs, MedGemma model.

Claude in your zsh prompt: ask, explain, and Ctrl+X / Alt+E widgets that turn natural language into shell commands. Wraps the Claude Code CLI, no extra deps.

Iterative artifact refinement with investigation-first judge board - constructs problem-specific judges that read the code, understand the problem, and propose evidence-based improvements

AI agent CLI for spec-driven feature loops with Claude Code and Codex. Scans your stack, generates specs, and runs autonomous implement-test-fix cycles.

AI agents that think must never act. Open-source security framework with composable modules for safe autonomous AI.

Son of Anton, reimagined as a web app — Node + WebSocket + node-pty + xterm.js, zero Electron.

A local CLI agent that connects to databases and answers data questions using natural language and SQL.

Persistent memory, architectural decision enforcement, pre-execution safety hooks, and session handoff for Claude Code. MCP server plugin for AI coding agents.

Verdict-first output for AI coding agents. Tiny prompt + installer for Claude Code, Codex, Gemini, Cursor, opencode, and 30+ agents.

65 plugins that turn Claude Code into an autonomous development team. 24 agents, 34 skills, 5 hooks. Includes 12-plugin anti-hallucination suite. One-line install.

Local-first CLI to read, compare, and hand off sessions across Claude Code, Codex, Gemini, and Cursor agents. Checkpoints, cross-agent messaging, zero npm deps.

O Trebuchet Framework é uma infraestrutura robusta para a criação, execução e orquestração de Agentes de IA autônomos, projetada especificamente para hardware local. Diferente de soluções que dependem exclusivamente de APIs na nuvem, o Trebuchet prioriza a privacidade e o desempenho local utilizando llama-cpp-python para inferência de LLMs e chroma

Independent framework to test, benchmark, and evaluate LLMs & AI agents locally.

[LEGACY] Use the Codex models included with a ChatGPT Plus/Pro subscription inside LangChain/LangGraph.

dbx-unifiedchat is a custom agent stack with an app interface for NL2SQL cross-domain chat on Databricks as a Databricks Solution.

Chrome browser extension that helps AI Dungeon creators rapidly build multiple choice scenario branches using AI and other useful tools~

Lossless local memory for Claude Code. The full, unabbreviated version. Every tool call, every file edit, every thinking block — stored verbatim on your machine. Persistent memory without tokens.

🔒 Automate cybersecurity tasks with n8n workflows for Red Team, Blue Team, and Application Security, enhancing efficiency and response times.

Odoo MCP Server - Model Context Protocol server for Odoo ERP integration. Supports Odoo 14-19+ with JSON-RPC and REST API.

Claude Code plugin with 22 AI recruiting skills. Source candidates, detect hiring signals, screen resumes, draft outreach, track pipelines. ATS-integrated. Free and open source.

AGENTIC · INFRASTRUCTURE — Every agent you run, working from the same brain. Open-source framework with a native shared Second Brain.

papersflow-mcp is PapersFlow’s production MCP server for literature search, citation verification, related-paper discovery, and authenticated research workflows across Claude, Codex, Gemini, and other MCP clients.

카카오톡 MCP 서버 — Claude Code에서 카카오톡 대화를 읽고, 보내고, 요약합니다

Describe your workflow. Automate your world.

TokenPack packs long documents, codebases, PDFs, and folders into compact, evidence-dense LLM context using local embeddings, evidence scoring, and budget-aware selection.

Source code of "The HalluRAG Dataset: Detecting Closed-Domain Hallucinations in RAG Applications Using an LLM's Internal States" (arXiv: https://arxiv.org/abs/2412.17056)

Transform academic PDFs into a Knowledge Graph with typed claims, temporal analysis, bibliometric tools, and grounded LLM synthesis that cites only your corpus.

Official Scrapfly MCP server for Cursor, Claude Desktop, and any MCP-compatible client. Enterprise-grade web scraping, AI extraction, and anti-bot–aware data access as first-class tools.

Open-source Gmail MCP server. Multi-account, read, write, archive, label, auto-unsubscribe. Works with Claude, OpenClaw, Cursor, Windsurf, Cline, and any MCP-compatible AI agent or assistant.

iKanban 是面向 OpenCode V2 的独立前端应用

Multi-agent AI consultation framework for Claude Code via MCP — get second opinions from OpenAI, Gemini, Qwen, DeepSeek

Orchestrator plugin: composes planning-with-files, DESIGN.md, memory routing, agent teams, and session handoff into one contract for any modern coding agent. Cross-IDE.

Multi-perspective AI development workflows using councils of specialized agents. Plan, build, review, and ship — with 13 agent personas across 6 councils.

File-based agent-to-agent messaging for Claude Code — multiple AI instances communicate via JSON files, MCP channels, and auto-wake on a single machine

AI-Driven Full-Text Screening and Data Extraction for Systematic Reviews and Evidence Synthesis

Ultimate Claude Skill for Product Discovery. 18 tasks across 6 blocks: Market Analysis, Customers (JTBD/CJM), Strategy (Lean Canvas/OST/SWOT), Validation (rapid testing/PMF), Main Scenario, Artifacts (one-pager, financial plan, pitch deck, interview guide). 3 modes: Light / Full / Geographic Expansion. Run on latest Claude Opus.

Market intelligence toolkit for Claude Code. Iterative research workflows, trend modeling with three-valued logic, multi-format reports, and automated GitHub issue creation from findings.

Unified AI agent harness framework for Codex, Claude, Cursor and Copilot by wild

Interactive deep-dive into Gemini CLI internals — 150+ illustrated pages, 50+ step-by-step animations, Mermaid diagrams, and source-level walkthroughs. Built with React 19 + TypeScript + Tailwind CSS 4.

A simple, experimental multi-agent AI system, built with Python, that automates triaging and fixing GitHub issues.

Recursive project management for Claude Code. One primitive, any scale.

小白通过 CCA 最全手册 - Claude Certified Architect (CCA-F) 中文备考指南，覆盖 6 大 Domain 25 章节，含自检题/术语对照/学习节奏

WhatsApp channel plugin for Claude Code — connect your WhatsApp to an AI agent. QR scan, voice transcription, access control, media support.

AI-powered content generation and auto-posting engine built for Claude Code and Codex. Generate viral videos, carousels, and reels for TikTok, Instagram, and X using Grok. No API keys needed — uses browser cookies for both generation and posting. Template-first, agent-driven, free and open source.

agent-replay is a 100% local, SQLite-powered CLI tool for time-travel debugging AI agents that lets you replay execution traces, diff behavioral changes, fork runs to test fixes, and run AI-powered evaluations or safety guardrails to eliminate hallucinations and production failures.

Myco is the nervous system for AI-assisted software teams. Works automatically alongside the coding agents, subagents, and agent teams you already use

AI team for Codex — researcher, PM, architect, developer, QA, and reviewer orchestrated through a configurable pipeline.

A full-stack AI engineering playbook — infrastructure, model lifecycle, agents, MCP, memory, evaluation, and production systems.

A command center for AI coding agents — run Claude, Gemini & Codex in parallel, each in its own git worktree

ElucidatingYourLLM — rules framework to onboard your LLM: fewer AI hallucinations and unpredictable behavior, with AI-assisted deployment. Cursor · Claude Code · OpenClaw

Claude skill that wraps CloakBrowser stealth Chromium — fetch, screenshot, PDF, and run JS through anti-bot detection (Cloudflare, reCAPTCHA, FingerprintJS) from any Claude agent.

Persistent local memory for Claude, Cursor & Codex. 21 MCP tools, hybrid retrieval (BM25 + vector RRF), bi-temporal queries, contradiction detection. SQLite + Knowledge Graph. No cloud, no API keys. npx @studiomeyer/local-memory-mcp

🚀 企业级私有化 RAG 知识库系统 | 💯 纯离线部署、无需联网 | 🔐 支持 LDAP/AD 统一认证与 RBAC 部门级权限隔离 | ⚡️ 基于 LlamaIndex + Ollama + BGE-M3/Rerank | 📝 支持多格式文档解析、上下文对话记忆及精准的 PDF 原文溯源高亮 | 📊 内置数据可视化仪表盘（🚀 Enterprise RAG Knowledge Base. 💯 Fully offline/air-gapped deployment. 🔐 Features LDAP/AD integration, RBAC & Department Isolation. ⚡️ Powered by LlamaIndex, Ollama, and Local R

Markdown-first, long-term memory infrastructure for AI agents. Hybrid BM25 + semantic search across markdown/code files via MCP.

AI agent skill for technical docs — Diataxis + 27 rules, 6 style guides (Google, Good Docs). Works with Claude Code, Cursor, Codex, Windsurf.

A universal Agent Skill for deep, multi-source learning across 18+ AI coding agents

MITM proxy for Claude Code with real-time TUI, web UI & MCP server — intercept, inspect, and send messages to the Anthropic API. Headless mode for automation.

Multi-agent coordination system for software engineering with 9 specialized AI agents - Documentation, API Design, Backend Architecture, Java/Go Development, DDD, and Observability

Production-grade Retrieval-Augmented Generation (RAG) API built with FastAPI, LangChain, OpenAI, and Qdrant.

Comprehensive Android device control via ADB — typed Python package + CLI + Claude Code skill. Master Tester Doctrine governed (338 tests, 1.59:1 ratio).

CLI coding agent powered by the MiMo large language model

Local-first Gmail + LinkedIn writing copilot (MV3 extension) powered by Claude. Dev beta with one-command installer.

⚡ Synerix — 高性能 AI 编程终端 | 多智能体协作 + TUI 界面 + 安全沙箱

Tell Claude Code what you want once. It works until the job is verifiably done — and gets smarter every time. Self-correcting goal loops with independent verification and growing memory.

Copy and paste prompts for cursor agent. Free for anyone to use or add to. This repository provides a curated collection of advanced .mdc rules for Cursor IDE to optimize AI agent behavior, memory management, and development workflows.

Open-source agent orchestration framework providing deterministic multi-agent workflows, AST verification gates, and maintainer automation pipelines.

The canonical standard for building production-grade agentic products — autonomy ladder, composition patterns, the 8-layer harness, eval discipline — plus a Claude Code skill set that operationalizes it.

Watercooler: your team's shared reasoning layer for agentic coding. Preserve the "why" around your code.

Generate a production-ready, best-practice Claude Code harness tailored to your use case in minutes -- at any skill level. Or validate, update, and improve a harness you already have.

Official Roadmap for Catalyst – Track upcoming features, improvements, and releases. Submit feature requests and help shape the future of Catalyst

The recursive self-improvement loop for your skills (including itself) — runs a retro after every session and turns corrections into permanent skill improvements, so skills compound instead of plateauing.

The WorkBoard for Claude Code and humans. Watch your work come to life — never lose an idea, never lose a workflow.

No-code AI voice agent for n8n: calls your leads, qualifies them, pulls their email out of the conversation, and logs every transcript to Google Sheets with Slack alerts. Vapi, Twilio, OpenAI.

Structural security, governance and execution for AI agents: validate actions before they touch files, credentials, network, APIs, or money.

Claude Code Skills, Agents & Plugins — UitKit

single-executable / library which combines llama.cpp, whisper.cpp, and stable-diffusion.cpp

Local-first, eval-first memory for long-horizon AI agents — no LLM at ingest. Python SDK + MCP server with source-traceable recall, belief revision, selective forgetting, and reproducible benchmarks.

Agent Switch: Claude Code, Claude Desktop, Codex CLI, Codex Desktop, Hermes, OpenCode, OpenClaw and AI agent config switcher, model router, and local OpenAI/Anthropic gateway

Zero-human full-stack deployment as a bundle of /sc-* Claude Code slash commands — GitHub + Convex (self-hosted & Cloud) + Dokploy + Vercel + Hostinger DNS, source to verified live URL. Node ≥18, no runtime dependencies. 8 skills implemented, 5 stubs.

MCP server that lets AI agents (Claude, Cursor) debug your .NET / ASP.NET Core app

Open-source runtime security and governance for AI agents, MCP tools, robotics, industrial automation, and physical AI.

Prompt optimizer for Claude Fable 5, built as a claude.ai Project — 43 source-backed rules, complexity routing, and API parameter recommendations, grounded exclusively in official Anthropic documentation.

Eliminates generic AI slop and enforces premium UI/UX design via 10 sequential gates, ratio-based layout/composition audits, and open-design craft integration.

Fast, offline code search and code intelligence for LLM agents.

Open-source MCP server connecting Claude AI to Oracle EPM Cloud via REST APIs. Run business rules, export data, and automate month-end close through natural language. Full tutorials and articles at fmepm.com. Built by Fred Mamadjanov, Oracle ACE Pro.