GitHub agents

Open-source agent skills for turning raw book ideas into full manuscripts with blind literary evaluation gates.

Android Native AI agent for phone automation — control apps via Accessibility / Root / Shizuku, run Shell / SSH commands, and extend with MCP, Skills

Open-source AI gateway for LLMs & AI agents, built in Rust. One OpenAI-compatible API for OpenAI, Anthropic, Gemini, Bedrock & more — routing, guardrails, caching, rate limits, observability.

A modular context-based agent system

Open skill for capturing AI agent work as structured traces.

Compiles AI agent traces and truns them into reusable context.

"AI 桌面管家 · 多 Agent 协作编排 · 一句话调动团队完成复杂任务

给前端 Agent 使用的中文规范，统一产品界面、数据状态、组件组织和代码归属。

Self-designing, durable, self-improving agent orchestration: describe a goal — an agent designs the graph, a fleet of sealed full-agent nodes runs it, and a learning loop makes it better every run.

该项目技术已过时，综合考虑放弃维护。可移动到ai_interview项目参考新技术实现

DeepSeek API Platform integration for OpenClaw

key0 is the commercial gateway for your AI agents and APIs. Let AI agents discover, pay for, and access your APIs autonomously - no human in the loop.

OpenClaw AI trading agents - Skill Forge, Chat, BankrBot, Polyclaw, Alpaca, Kalshi, Whale TrackingOpenClaw AI trading agents OpenClaw AI trading agents

Local-GenAI-Search is a generative search engine based on Llama 3, langchain and qdrant that answers questions based on your local files

Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedback

Next.js app for serverless deployments of OpenAI Whisper on Banana.dev

nitmgpt (Notification-in-the-middle GPT). Filter ads or spam notifications via ChatGPT.

A package to allow OpenAI's custom GPTs to access your Mac via Apple's Shortcuts.

An open AI environment using selenium + docker for training automated web agents

Build AI Agents for popular LLMs quick and easy in Laravel

A multi-agent engine for the UBC Agents

A microframework for creating simple AI agents.

Build powerful and secure AI Agents powered by Starknet.

A wargaming platform compatible with reinforcement learning agents

An orchestration system for managing AI coding agents. The system uses Aider (an AI coding assistant) to handle coding tasks and provides real-time monitoring of agent outputs through a user-friendly interface.

Universal AI Agent Orchestrator - Run any AI coding agent (Claude Code, Amp, OpenCode, Codex, Droid, Gemini) repeatedly until all tasks are complete

The Context Engineering framework for building smarter, more reliable AI Agents.

Q-Star Agent Code: A reinforcement learning-based framework for intelligent agents using Microsoft AutoGen. It leverages Q-Star, a Q-learning variant, for dynamic decision-making. Ideal for developing adaptive AI agents in diverse applications, from service bots to advanced simulations. Includes setup and customization guidelines.

Code for the RL method MATD3 described in the paper "Reducing Overestimation Bias in Multi-Agent Domains Using Double Centralized Critics"

Ready to Deploy Fullstack OpenSource Agentic Apps

Compose to create working TeamCity server with PostgreSQL and Agents

Full-stack Python Code Agent platform

User agent changer for Safari

An open source environment for digital agents.

Agentic chat runtime where markdown is the protocol

Generic Mac OS X menu bar app (agent) template

GPG Reaper - Obtain/Steal/Restore GPG Private Keys from gpg-agent cache/memory

This code implements Prioritized Level Replay, a method for sampling training levels for reinforcement learning agents that exploits the fact that not all levels are equally useful for agents to learn from during training.

This repository contains an application using ROS2 Humble, Gazebo, OpenAI Gym and Stable Baselines3 to train reinforcement learning agents for a path planning problem.

Code for ACL25-findings. An LLM-based agent simulation framework that simulates human behavior and generates dynamic, text-based social graphs.

A curated, DevOps-focused list of Model Context Protocol (MCP) servers—covering source control, IaC, Kubernetes, CI/CD, cloud, observability, security, and collaboration—with a bias toward maintained, production-ready integrations.

WangChanGLM 🐘 - The Multilingual Instruction-Following Model

Use DALL·E 2 with Nodejs

Open-Audio TTS: A robust web app leveraging OpenAI's powerful Text-to-Speech (TTS) models to generate natural-sounding audio from text. Built with modern web technologies for an intuitive user experience, including customizable voice and speech speed settings, and the ability to download audio files directly.

VideoDB Python SDK

MIT-licensed Framework for LLMs, RAGs, Chatbots testing. Configurable via YAML and integrable into CI pipelines for automated testing.

Train a DQN Agent to play CarRacing 2d using TensorFlow and Keras.

AlphaSwarm is a starter kit for building LLM-powered AI agents that interpret natural language trading strategies, analyze real-time market signals, and autonomously execute trades across multiple chains.

Lilium AI: The ultimate personal AI agent framework for autonomous computer control. Featuring browser automation, shell execution, and multi-channel integration (WeChat/Telegram/Discord).

AI agent web app platform

Apply LLMs for automated ranking Resume

Backend for SlideSpeak. Create PowerPoints with AI. Get summaries, ask questions, create presentations and more.

RAG-powered documentation assistant that converts, processes, and provides semantic search capabilities for Odoo's technical documentation. Supports multiple Odoo versions with an interactive chat interface powered by LLM models.

Akamai MFA CLI and SSH Agent (v2)

A Facebook Messenger Bot

Browser based agent orchestrator / You host the server wherever you want / Harnesses all CLI AI harnesses / Mobile and VR Voice coding

simple multi-agent pathfinding (MAPF) visualizer for research usage

A library for building software agents using behavior trees and language models.

A local LLM chatbot with RAG for PDF input files

一个支持定义多个角色的 AI 群聊 Web APP

SQLMap with Autonomous AI, phased workflows, RAG memory, and MCP Agent Tools

longcallR is a tool for SNP calling, haplotype phasing, and allele-specific analysis with long-read RNA-seq data.

A Terminal User Interface for AI collaboration on code, using a Retrieval-Augmented Generation (RAG) pipeline designed specifically for Rust code generation and refactoring.

High-performance vector search for Browser, Node, and Edge

🖥️ Run a Team of AI Agents. In Your Terminal.

[🏆 CHI26 Best Paper] CoBRA: Reproducible control of LLM agent behavior via classic social science experiments

Curated collection of tools for agentic LLMs in Emacs

Vibe Island releases & update feed — download the latest DMG of the macOS notch panel for 25 AI coding agents (Claude Code, Codex, Cursor & more).

A lightweight autonomous AI coding agent with terminal-based UI, inspired by Codex and Cline.

Enable AI agents to create and execute their own tools in Rust autonomously. Available as web API and MCP services

Code repo for "LifelongAgentBench: Evaluating LLM Agents as Lifelong Learners"

A collection of different implementations of the same agent to show differences in frameworks.

The UI5 MCP server improves the developer experience when working with agentic AI and the UI5 framework.

Compiles AI agent traces and truns them into reusable context.

List of AI Agent related discord channels with links

MCP server to communicate with DAP servers allowing AI Agents the ability to debug live programs.

Self improving agents through iterations

iOS application for Lumo

MCP server for OpenAI's Deep Research APIs, Gemini Deep Research Agent, Allen AI's DR-Tulu, and Hugging Face's Open Deep Research

The data represents financial transactions -- bank transfers, purchases, credit card transactions, checks, etc. Most of the transactions are legitimate. A few represent money laundering. The data is in CSV format. The data is generated using a multi-agent virtual world model. All of the agents in the virtual world have actions governed by statistical distributions. Thus the model and data are NOT based on obfuscating or anonymizing real individuals. Everything is synthetic. More specifically the underlying model uses a virtual world of banks, individuals, and companies -- with individuals and companies buying items, and doing bank transfers to make payments, get supplies, pay salaries, etc. The underlying model has good and bad actors, with bad actors doing things like smuggling, extortion, illegal gambling, etc. The bad actors sometimes attempt to launder ill-gotten funds resulting in money-laundering transactions. NOTE : Although this repository is under the Apache-2.0 license, the actual data is released under the CDLA-Sharing-1.0 license.

The source code of [Sec'25] Make Agent Defeat Agent: Automatic Detection of Taint-Style Vulnerabilities in LLM-based Agents

Ship with less chaos. Flux is a fast, simple Kanban board with MCP integration so your LLMs can help run the show.

AI agent skills, agent teams, MCP servers, and tools that make AI coding assistants better at Swift and iOS development.

A curated list of AI agent platforms, frameworks, protocols, tools, and resources

Production-ready multi-agent academic illustration system with Chinese GUI, background generation, plot workbench, and portable result bundles. Extended from PaperBanana.

An open taxonomy and scoring framework for evaluating AI agent sandboxes: 7 defense layers, 7 threat categories, 3 evaluation dimensions, 27 "sandboxes" scored.

PCLA: A framework for testing autonomous agents in the CARLA simulator

🚀 Way Back Home

心灵伴侣，AI+心理健康Agent项目案例

企业级多Agent知识管理系统：4个AI Agent协作完成文档解析→知识抽取→智能问答→增量更新，Python/Java/Go三语言实现

AI影视创作策划评估工作流|剧本创作 Agent 平台是一个基于 AI 的专业影视创作辅助系统，整合了 20+ 个专业 Agents，覆盖从策划、创作到评估的全流程。短剧创作|策划|评估Agent,故事大纲生成｜详细情节点｜剧本｜故事质量ip评估｜已播剧情分析｜故事五元素分析｜情节点工作流｜人物小传｜人物关系｜思维导图｜

A feature-rich, dependency-free Node.js statusline for Claude Code with model, task, git state, context window, rate limits, and Anthropic peak-hours indicator

Control robots and physical hardware with natural language through Strands Agents.

This repo contains the critical chat_template.jinja fix for Qwen3/3.5/3.6 to work smoothly in agentic task.

Kyros — The Memory OS for AI Agents Give your AI agents secure, self-correcting, persistent memory in 3 lines of code. Three memory types (episodic, semantic, procedural) with built-in forgetting curves, cryptographic integrity, and automatic contradiction resolution. Model-agnostic REST API with Python and TypeScript SDKs.

一个生产级的深度研究 Agent 系统，从零构建多智能体编排、Red-Blue 对抗降噪、 语义级上下文压缩、跨 Agent 共享记忆四大核心能力，配套 165 次独立实验 + Bootstrap 统计显著性检验的完整评测体系。

Multi-agent macro trading bot: multi-factor stock scoring, momentum portfolio construction, backtesting vs SPY/Nasdaq, and live Alpaca execution.

Floating macOS HUD for live Claude & Codex usage quotas — menu-bar toggle, threshold/recovery reminders, custom hotkey, dark/light. Reads Chrome cookies locally.

A Claude Code skill for web report decks — richer ECharts charts, one file per slide (edit one page, save tokens), and complex structure diagrams. 16:9 & vertical, PDF/image export.网页版 PPT 汇报的 Claude Code skill：ECharts 把数据画得更好看、每页一个文件改一页省 token、能做复杂结构图（架构/框架/价值链）。16:9 + 竖屏，导出 PDF 和图片