GitHub agents

Natural Language Data Augmentation Tool for Conversational Systems

Go implementation of OpenAI's Gym.

Tutorial and template for a semantic search app powered by the Atlas Embedding Database, Langchain, OpenAI and FastAPI

Storybook Genie is a command line interface tool that can generate Storybook stories from React components

Push to talk voice recognition using Whisper

Natural Language Application Development (NLAD) - A methodology for building applications by leveraging LLMs to create higher levels of abstraction in software development.

InterfaceAgent: a versatile framework designed to create system and interface agents capable of managing mobile and desktop applications and features.

Researcher Agent to write blog posts/ articles using Amazon Bedrock and websearch.

BingGPT Discord Bot that can handle /ask & /imagine prompts using reverse engineered API of Microsoft's Bing Chat under the hood

🦀 A Pure Rust Framework For Building AGI.

AI 应用示例合集

An LLM-powered Slack bot for your internal knowledge, powered by tiger-agents-for-work libraries.

AdaSociety is a customizable multi-agent environment featuring expanding state and action spaces, alongside explicit and alterable social structures. AdaSociety is friendly to tensor-based and LLM-based methods.

AutoGen最新架构v0.4正式发布第一个稳定版本，v0.4是对AutoGen的一次从头开始的重写，目的是为构建Agent创建一个更健壮、可扩展、更易用的跨语言库，其应用接口采用分层架构设计，存在多套软件接口用以满足不同的场景需求 。

A framework for evaluating AI audit agents using recent real-world data

OCS (OpenCode Config Suites) installer for Multi Agents workflow, AI coding setup, and cross-platform OpenCode onboarding.

CLI Tool for 8k context ai models

char const* const commands[] = { "aapt", " aapt", " zipalign", "abduco", " abduco", "abook", " abook", "alpine", " alpine", " pico", " pilot", " rpdump", " rpload", "angband", " angband", "apache2", " ab", " apachectl", " apxs", " checkgid", " dbmmanage", " envvars-std", " fcgistarter", " htcacheclean", " htdbm", " htdigest", " htpasswd", " httpd", " httxt2dbm", " logresolve", " rotatelogs", " suexec", "apr-dev", " apr-1-config", "apr-util-dev", " apu-1-config", "apt", " apt", " apt-cache", " apt-config", " apt-get", " apt-key", " apt-mark", "aria2", " aria2c", "atomicparsley", " AtomicParsley", "attr", " attr", " getfattr", " setfattr", "autossh", " autossh", "bash", " bash", "bc", " bc", " dc", "binutils", " addr2line", " ar", " arm-linux-androideabi-ar", " arm-linux-androideabi-ld", " arm-linux-androideabi-nm", " arm-linux-androideabi-objdump", " arm-linux-androideabi-ranlib", " arm-linux-androideabi-readelf", " arm-linux-androideabi-strip", " as", " c++filt", " elfedit", " gprof", " ld", " ldd", " nm", " objcopy", " objdump", " ranlib", " readelf", " size", " strings", " strip", "bison", " bison", " yacc", "blogc", " blogc", " blogc-make", " blogc-runserver", "bmon", " bmon", "brogue", " brogue", "bs1770gain", " bs1770gain", "bsdtar", " bsdcat", " bsdcpio", " bsdtar", "busybox", " busybox", " env", "bvi", " bmore", " bvedit", " bvi", " bview", "bzip2", " bunzip2", " bzcat", " bzcmp", " bzdiff", " bzgrep", " bzip2", " bzip2recover", " bzless", " bzmore", "cadaver", " cadaver", "calcurse", " calcurse", " calcurse-caldav", " calcurse-upgrade", "cava", " cava", "cboard", " cboard", "ccache", " ccache", "ccrypt", " ccat", " ccdecrypt", " ccencrypt", " ccguess", " ccrypt", "cgdb", " cgdb", "clang", " arm-linux-androideabi-clang", " arm-linux-androideabi-clang++", " arm-linux-androideabi-cpp", " arm-linux-androideabi-g++", " arm-linux-androideabi-gcc", " c++", " cc", " clang", " clang++", " clang-5.0", " clang-cl", " clang-cpp", " clang-format", " clang-rename", " cpp"

A reference blueprint for building persistent, multi-agent Claude Code setups with Telegram and Discord.

Private RAG system with semantic context ingestion to improve source of truth of reliable sources

Spring AI Examples

Claude agent sdk as a provider for pi

Circuitron: Agentic PCB Design Accelerator — Generate, plan, and layout circuits from natural language prompts.

AI-powered customer support agent with WhatsApp, Email & Phone channels

Local-first observability your agent reads back. TMA1 records every LLM call, then routes what it sees into the agent's next turn via hooks and MCP.

本系列内容将带领大家从零基础理解 LangChain V1.x 及其相关生态（包括 LangGraph、DeepAgents 等）在当前主流智能体（Agent）开发中的定位与核心能力。将依次完成基础环境准备、依赖安装、入门级 LLM 调用、Prompt 工程实战、Agent 类自动化流程构建、知识库（RAG）、向量检索、结构化/非结构化数据处理、多模态与插件集成等能力点。通过真实业务场景（如问答助手、内容摘要、API 组装等）的逐步拆解与落地案例，配合全流程源码讲解和操作演示，你将掌握 LangChain 最新 V1.x 体系下的核心开发范式，以及最佳工程实践和故障排查思路，最终能够独立搭建、升级和维护自己的智能体应用与工作流系统。

AerialClaw: Towards General Intelligence for Autonomous Aerial Agents

[ICLR 2026] Beyond a Million Tokens: Benchmarking and Enhancing Long-Term Memory in LLMs

Local-first AI workspace for macOS. Ten workspaces — Coder, Agent Swarm, Finance, 3D Forge, Sandbox, Virtual OS and more. 12 providers, or fully offline with Ollama. No backend, no telemetry, no account. Your keys and files stay on your machine. 8.9 MB, MIT.

Local-first Rust TUI/CLI for auditing AI coding-agent sessions: cost, tokens, latency, failures, and health｜本地优先 Rust TUI/CLI，审计 AI 编程 Agent 会话的成本、Token、延迟、失败与健康度

LLM-powered Crypto Trading Framework with Vision AI chart analysis, real-time Neural Engine, and a live monitoring dashboard at semanticsignal.qrak.org. Features memory-augmented reasoning and professional risk metrics.

Private Skill distribution platform for AI coding agents: publish, install, update, and rollback team skills across Cursor, Claude Code, Codex, and OpenClaw with a minimal server + skb CLI.

React Native Duolingo clone with a real-time AI voice teacher. Built with Expo, Stream Voice Agents, Clerk auth, and NativeWind for a complete, interactive mobile learning experience.

A curated list of HTML slide generation skills and template libraries for Claude Code, Codex, Cursor, OpenClaw, and Hermes. 精选 HTML 演示文稿 Skill 与模板库。

A curated guide to the Herdr ecosystem: tools, workflows, configs, clients, skills, and integrations.

OWASP Foundation web repository

Spec2Case 是生产级 AI 测试用例生成智能体，支持图片/文本需求理解、人工确认、LangGraph 流程编排和 Excel 用例导出。

Local MCP server that exposes eBay Sell APIs to AI assistants with OAuth, tool gating, and stdio/HTTP transports.

Iron-Man-style voice assistant + holographic HUD for Hermes Agent. Local Whisper STT, ElevenLabs voice, agent-summoned media panels, runs on your own hardware.

Local-first MCP gateway. One port for every tool and every AI client: lazy discovery (~90% token savings), tool integrity + quarantine, secrets in the OS keychain.

开源 AI 应用评测平台，支持 RAG、AI Agent、多轮对话、LLM-as-Judge、接口评测、评测报告和人工盲测。Open-source AI evaluation platform for RAG, AI Agents, multi-turn conversations, LLM-as-Judge, endpoint evaluation

WRAITH — Weakness Reasoning & AI Threat Hunter | Multi-agent RL-driven penetration testing framework | DEF CON 2026

Local-first agent workspace for knowledge, tasks, documents and verifiable workflows · Локальная агентная система для знаний, задач и проверяемых процессов · t.me/romarayt

2019语言与智能技术竞赛-基于知识图谱的主动聊天

PowerShell module that enables you to use AI Code Completion in the command line.

This is an open source implementation of the Github Copilot AI Model based on reverse engineering of the VSCode and IDEA plugins.

Agentic-first Cursor Rules powered by MiniMax M2 — clarify-first prompting, interleaved thinking, and full tool orchestration for production-ready AI coding

Accurate and flexible loops calling tool for 3D genomic data.

BEAM-native personal AI agent built on Elixir/OTP. Runs on your hardware. Your data stays yours.

An LLM-based tool to chat with your documents and databases, including a management system | 面向企业内部环境的大模型(LLM)知识库问答系统，包含后台管理系统

Kieker is an observability framework, that consists of an monitoring and tracing agent, and compatible analysis tools

DialOp: Decision-oriented dialogue environments for collaborative language agents

A Python CLI to test, benchmark, and find the best RAG chunking strategy for your Markdown documents.

wacat - Challenge Your Web App with Cat Chaos and AI-Driven Testing!

PATIENT-Ψ: Using Large Language Models to Simulate Patients for Training Mental Health Professionals (EMNLP 2024)

:robot: The next generation of Multi-Modal Multi-Agent platform. :space_invader: :unicorn: :crystal_ball:

[ICML 2026] AutoControl Arena: Frontier AI Risk Auto-Discovery Platform

Streamlit demo of Scrapegraph-ai for GPT4-hackaton

Simple python tool which finds the location of a wifi access point from its BSSID (Basic Service Set Identifier) which is the MAC address of the wifi access point and optionally displays the location on Google Maps. This is implemented by calling the Apple Location Services API.

Hybrid RAG AI Agent built with MongoDB, Pydantic AI, and Docling - combines semantic and text search with reciprocal rank fusion.

Hyprdots, Hyprland Omarchy, Quickshell, Agentic Local-Ai, Custom Integrated, Minimal

MAPF-LNS2: Fast Repairing for Multi-Agent Path Finding via Large Neighborhood Search

对标大厂内部研发环境建设，面向小型创业团队的云端 IDE 标准环境。 预置 VSCode 在线版与 Claude Code、Gemini、Codex 等 AI 编程工具。 专为弱网、出行、休眠与长时间 Agent 运行场景设计。 保持熟悉体验，实现持续在线的开发协作。

[RAG训练营] u.geekbang.org/subject/airag/1009927 这是我用Cursor自行制作的RAG Framework，好处是可以掌控RAG每一个环节的教学细节。

Foundation is a flexible, modular, and composable framework to model socio-economic behaviors and dynamics with both agents and governments. This framework can be used in conjunction with reinforcement learning to learn optimal economic policies, as done by the AI Economist (https://www.einstein.ai/the-ai-economist).

Reliability harness for long-running OpenClaw agents: persistent state, strict task contracts, scheduled execution, and external validation.

Implementation of Deep Thinking Trading System

Open-source enterprise AI workforce platform — containerized roles, declarative skills, MCP tools, policy-driven security, K8s-native scheduling

Tandem is the authority layer between AI agents and company tools: runtime policy for tools, memory, approvals, and audit trails.

"ULTRASHIP" Claude Code plugin — 39 skills, 33 tools, 11 agents for ship-ready workflows: planning, review, pentesting, safety guardrails, canary monitoring, SEO/AI-readiness check, penetration testing, code review, competitive analysis, incident response. 1 dependency. 180 tests. MIT.

The Trading Research Framework inspired by Deerflow Multi-Agent!

Curated workflow recipes that combine hooks, MCP servers, skills, agents, and CLAUDE.md to automate real Claude Code tasks

Muse Studio is an Agentic AI workspace for planning, visualizing, and iterating on stories and video creation.

Frontend AI coding agent platform with CLI, VS Code extension, desktop app, MCP server, RAG planning, Skills, SDD guardrails, browser automation, and LoRA planner models | 面向前端工程的 AI Agent 平台，支持 CLI、VS Code 插件、桌面端、MCP 服务、RAG、Skills、SDD、浏览器自动化与 LoRA 规划模型

Agentic Coding CLI & chat bot

A sample agentic ai platform to run agentic workflows on AWS using either EKS or Bedrock AgentCore with open source frameworks like LangChain/LangGraph, Strands, etc..

🎵 将音乐搬进AI终端 · 打造Coding专属智能DJ · 听歌新范式 · 交互式音乐 ｜A retro pixel DJ for Claude Code / Codex CLI / Terminal with Apple Music / QQ Music / Local Music — plays music, shows synced lyrics, and 😱 panics when your tests fail.

Open source framework to vibecode and prototype voice agents with Gradium APIs

OpenTiny NEXT-SDKs is a front-end AI and browser automation toolkit. It implements WebMCP + WebSkills to build AI-native apps, and leverages webmcp-cli to enable LLM agents to remote-control any webpage without source code modifications. OpenTiny NEXT-SDKs 是一套前端 AI 与浏览器自动化工具包。它通过 WebMCP + WebSkills 协议构建 AI 原生应用，并利用 webmcp-cli 实现了无需修改源码即可让大模型代理自动控制任

One local dashboard for every Claude Code, Codex, Cursor, Antigravity, and Kilo Code session on your Mac. Spawn in parallel, ship in parallel. Open source, MIT.

Mailbox-native protocol and SDKs for asynchronous agent collaboration over email

Voice-driven multi-agent assistant — Realtime API + CLI runners + multi-channel orchestration.

A privacy-focused AI chat platform built with Vite + Capacitor + Cloudflare. Runs locally or in the cloud, supports Gemini models, live web search, and intelligent key rotation. No sign-up required — fast, secure, and customizable.

Addressee detection for voice agents: device-directed speech detection that runs before STT, so background speech, side conversations, and the agent's own TTS echo never trigger it. No wake word, model-agnostic, drop-in for LiveKit, Pipecat, ElevenLabs, Twilio, and OpenAI. The layer your VAD and turn detection are missing.

⌚ 在 Apple Watch 上批准 Claude Code / Codex 的危险操作,任务完成自动提醒 | Approve your AI coding agent's risky actions from your Apple Watch, get buzzed when tasks finish

Markdown Editor Pro — A powerful, feature-rich markdown editor with live preview, LaTeX math support, GitHub-inspired styling, and seamless integration into React apps. Built with React, TypeScript, and Tailwind CSS.

Autonomous AI-powered security scanning platform — CLI scanner, web dashboard, and one-command Docker deployment

Connect your agent to the apps you already use - with or without Zapier.

Open-source, Cloudflare-native agent runtime for Codex, Claude Agent SDK, and OpenCode—with API endpoints, isolated sandboxes, and inspectable runs.

🏰 Real-time dashboard for monitoring and managing Clawdbot AI agents

🦞 Pre-hardened, multi-agent OpenClaw setup. One script from zero to a fully secured AI assistant on Discord, Telegram, or both.

Official and Reverse Engineered ChatGPT PHP SDK (Not GPT-3)

TaskFlowAI is a lightweight and flexible framework designed for creating AI-driven task pipelines and multi-agent workflows. It provides developers with a streamlined approach to building agentic systems

chatgpt google gemini pro ai flash 3.5 app windows download pc google ai desktop client windows 11 10 official application free exe install shortcut workspace chat assistant

Use LLMs for building real-world apps

A diverse, simple, and secure all-in-one LLMOps platform

A minimal, end‑to‑end deep‑research agent implemented with AI SDK and Next.js

Using Large Language Models for Repo-wide Type Prediction