GitHub agents

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

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

AI-native desktop localization system for Paradox mods—LLM orchestration, context engineering, structured validation, repair loops, human review, and local-first project control.

JanSahayak AI – A multilingual AI assistant that helps citizens understand and access government welfare schemes through conversational voice and chat.

An MCP server for safer coding agents: skill routing, C4 workflow gates, memory checks, and verification before completion.

Short-horizon order-flow pulse engine for Robinhood crypto markets.

Claude Code iMessage MCP channel. Text with blue bubble, Apple-native iMessage to work on your Claude Code sessions. Open source for developers, purpose-built on top of the Claude docs "Channels reference" guide.

Web dashboard for OpenSpec — one kanban board across every repo, showing which artifact is next and what is blocked. OpenSpec 1.6 compatible.

A tiny, declarative, agent-friendly library for your Git repositories.

Build a reusable Markdown context about you and your company (Claude Code skills + templates), then use it in ChatGPT, Claude, Gemini, Cursor or CLAUDE.md. Write context once, reuse everywhere. MIT.

CLI and AI agent skills for the Tokenomist crypto data API: token unlocks, vesting, emissions, allocations, fundraising, burns and buybacks.

Cybersecurity knowledge graph for code review with evidence-backed answers

A local-first second brain for scientists, researchers, coders, and nerds.

:bed: ”装闭“-AI驱动的开源装修闭坑系统。让装修套路“装”不下去。装修闭坑，“装闭”就够了

Local pre-flight linter and architecture gate for AI agents. Uses tree-sitter, Stack Graphs, and Datalog to mechanically block structural drift, layering bypasses, and scope creep on virtual ASTs before code changes land.

Desktop coding assistant — Electron, React and TypeScript.

Persistent memory and agent lifecycle for Claude Code — because sessions shouldn't start from zero.

학술 PDF 논문을 AI로 번역하고 논문 내용을 기반으로 대화할 수 있는 통합 웹/데스크톱 앱 서비스

An opinionated AI software engineering workflow built for BMAD

We heard you like harnesses, so we built a harness for your harness, so you can harness while you harness. Feel me?

Real-time observability dashboard for AI agent runs: live task progress, journal events, and orchestration state. Published on npm.

European Parliament MCP Server - Political intelligence for AI agents

Bootstrap a fully personalized Obsidian vault with AI. Interactive onboarding, document ingestion, and automatic knowledge base generation for Claude Code and compatible AI agents.

37 folder-drop skills for Microsoft 365 Copilot Cowork. 21 workflow skills plus a 16-persona executive review board. Drop a folder into OneDrive, no admin, no app package. The same SKILL.md files run verbatim in Claude Code.

RimZ is a realtime dashboard and control room for harnessing agentic coding, build on tmux and Zellij.

MCP server for SAP GUI for Windows automation via the SAP GUI Scripting API.

A KDE Plasma plasmoid to add desktop chat with LLMs

Local-first AI that can actually use your computer.

Hand a live Claude Code, Codex, or opencode session to anyone with three spoken words - encrypted, no account. Or carry your whole Claude Code history to a new laptop, every path rewritten.

Interactive terminal coding agent in Rust — runs the DeepSeek V4 Flash model locally on macOS (Metal), with a Ratatui TUI, a full tool suite, MCP, and persistent sessions.

High-assurance, artifact-agnostic prompt for authorized security labs, exploit-chain research, PoC validation, and evidence-led reporting.

Let Your AI Play Detroit：Become Human

Interview questions and prep for AI Engineer, LLM Engineer, and Applied AI roles. Built for software engineers breaking into AI and ML practitioners levelling up: company-specific question sets, role-based study maps, worked answers, and from-scratch coding challenges.

Read-only Kubernetes troubleshooting agent in Go (client-go) — explains CrashLoopBackOff, ImagePullBackOff, OOMKilled, Pending/Unschedulable with P1-infra to P2-workload reports; guarded reversible --fix; optional AI --explain via Claude API.

Open-source visual ai builder that lets you design AI visual ai agents workflows by dragging and dropping nodes on a canvas, and then compiles them into runnable Python projects for langgraph and Google ADK (Agent Development Kit).

A ready-to-use Obsidian vault for running an AI agent (Claude, Codex, etc.) as a personal OS: skills, grounding notes, and a self-improving feedback loop. Clone and open as a vault.

Synthetic dual-reflection GPA benchmarks with optional OpenAI method-card agent

How to build apps for ChatGPT?

Unofficial OpenAI-compatible bridge for Factory Droid

Whitebox & Blackbox AI 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

Write social cards as React components — tooka renders 1080×1350 carousels, exports IG-ready PNGs, and one-click publishes to Facebook, Instagram, and Threads.

The framework for building stateful agents. Your agent is a folder of state, served over MCP, used from any runtime.

这个项目为两件事而生，重心是学AI代理：把RAG、引用校验、最大工具循环这些机制零框架亲手写一遍，再配一个「学习中心」把每个机制讲成课；其次是学命理——把八字排盘室外可的点击活教材，每个干支、十神问、大运追到底。就算不接api key，也可以体验到大部分。

AI Agent engineering and quantitative finance knowledge base: source-level architecture analysis, Agent-to-Agent protocol research, runnable code experiments, industry insights. Obsidian vault, ready to clone.

Local-first agent workflow for building private cross-project memory with explicit consent, validation, and crash-safe history.

夕小瑶 × DeepSeek Harness Web 皮肤合集、安装器与社区创作工具链

Learn how to build 24/7 automated AI agents & chatbots for your website, SaaS, or Shopify store with zero coding required.

Claude Code: The Definitive Guide to Agentic Development — a technical book written in one weekend by AI, free EPUB/PDF for e-ink readers. Includes the assignment file so you can write your own.

OpenClaw + 大模型驱动的完整电商客服自动化系统：覆盖淘宝、拼多多、抖音、快手、小红书、视频号，包含浏览器/手机 Worker、订单物流与售后工具、记忆、回执、恢复和 Eval。

DeepSeek Harness 的 SDR 数字员工插件：九阶段外贸获客 SOP、结构性人工审批、客户去重、持久化知识检索与审计日志，默认 dry-run 安全演示。

One format, two readers. People and AI agents now co-write the same document. Legible for people; addressable, verifiable, and versioned for machines. GEML is plain text — organized by one typed block for everything, remembered by a .gemlhistory sidecar.

Runtime security for AI agents. In-process, zero dependencies, Apache 2.0.

Cross-platform SSH and SFTP client with organized server assets, terminal workflows, port forwarding, secure sync, and AI assistance.

MeowGPT is a set of tools for ChatGPT that allows you to use ChatGPT with minimal coding.

Airdrop optimizer - tracks live campaigns, estimates ROI, allocates capital.

AI-powered autonomous trading agents for Polymarket prediction markets. This framework enables developers to build sophisticated trading bots using state-of-the-art LLMs, RAG (Retrieval-Augmented Generation), and superforecasting methodologies. Built with Python 3.12+, LangChain, FastAPI, and modern development tooling.

Solana breakout-pressure engine that filters fake volume and ranks tradable continuation setups.

An opinionated development framework for building production-ready AI agents with LangGraph. It grounds AI coding assistants (Cursor, Windsurf, Cline) and guides them to use local, official documentation, ensuring reliable, secure, and observable agentic workflows.

A web automation library that lets AI agents browse the web using declarative JSON, with a unified dual-engine API and powerful anti-bot evasion.

DeFi protocol research agent for Solana. Scores protocols on security, traction, tokenomics, team, and moat using Claude.

Drift-aware Robinhood portfolio rebalancer that prices execution friction before proposing trades.

Describe a Solana program in plain English - Sigil's AI agent writes the Anchor code.

Context-aware alert board for Solana token price moves.

CT sentiment - scans Crypto Twitter, scores narratives, surfaces trading signals.

Multi-agent MCP orchestrator for Solana DeFi - routes tasks to specialized Claude agents, synthesizes results, acts autonomously.

Yield optimizer — rebalances across Kamino, MarginFi, Solend for max APY

Cross-chain bridge monitor for Solana. Tracks asset flows between Solana and EVM chains and detects anomalies using Claude.

Protocol intelligence writer that turns market data into memo-style weekly reports with clear provenance.

Autonomous AI Security Operations — 35 agents replacing $300K/year SOC teams for $50/year

Build your own AI-powered automation tools in the terminal with this extensible agent framework

Rust Market Simulation Library with a Python API

GoodFoods Reservation Assistant Powered by Agentic AI • Built with Pydantic Tools and Streamlit :)

RiveScript is a scripting language for authoring chatbots.

Node Js OpenAI Authentication Library for ChatGPT

An application that enable the users to upload PDF files and ask questions regarding their content using Retrieval Augmented Generation (RAG)

AI memory layer that lives in your stack

The UnisonAI Multi-Agent Framework built on custom workflow which allows ai agents to talk together and provides a flexible and extensible environment for creating and coordinating multiple autonomous AI agents. UnisonAI is designed with flexibility and scalability in mind.

This is the Yaitec Hub (Yaitec Community) Repository for sharing AI Templates with Community

IYKYK

An agentic workflow runtime

MCP that combats tools overload

AI-powered shell assistant that helps you execute commands and file operations through natural language.

Beginner-friendly tutorials, agent personas, skills, and templates for heyron users.

Lightweight, model-agnostic chat history compression (trim + summarize) for AI assistants.

Reusable workshop kit for teaching OpenClaw with setup guides, facilitator runbooks, and hands-on labs.

Vendor-agnostic orchestration OS for autonomous AI agents. Coordinate Claude, GPT, Gemini, and Grok using Markdown files as shared memory. Human-in-the-loop, Git-native, runs on GitHub Actions free tier.

Healthcare dashboard with AI-powered chart generation

Portable security rules for the action boundary of AI agents

200 AI agent skills, hardened with targeted behavioral guardrails. Free drop-in replacements.

Local-first personal memory & knowledge store for LLM agents. ローカルLLM向けの個人用メモリ／知識ストア（short / chronicle / memopedia / archive の4層構成）。

Kubernetes helm chart for OpenClaw (former Moltbot/Clawdbot)

OpenClaw-compatible MASL safety gate with public RAG packs for memory-aware AI agents

A Swift CLI tool for building simple Markdown docs for a package's public interface from its symbol graphs. LLMs love that stuff, too!

A curated collection of LLM-powered Flutter apps built using RAG, AI Agents, Multi-Agent Systems, MCP, and Voice Agents.

Open-source LLM agents framework for token systems simulations — pioneered domain-specific cognitive architectures with plan-and-act agents for data science process automation, built on cadCAD/radCAD

Welcome to the RAG University repository! This repository contains code implementations for Retrieval-Augmented Generation (RAG) models, specifically designed for Language Model (LM) tasks. RAG models combine the strengths of both retrieval and generation approaches, enhancing the capabilities of LLMs.