Agent Open Source Projects

🤖 Lobe Chat - an open-source, high-performance chatbot framework that supports speech synthesis, multimodal, and extensible Function Call plugin system. Supports one-click free deployment of your private ChatGPT/LLM web application.

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

🌟 The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Tasks, Repo

Create agents that monitor and act on your behalf. Your agents are standing by!

A toolkit for developing and comparing reinforcement learning algorithms.

🤖 Assemble, configure, and deploy autonomous AI Agents in your browser.

Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.

A list of AI autonomous agents

🤖 Chat with your SQL database 📊. Accurate Text-to-SQL Generation via LLMs using Agentic Retrieval 🔄.

Xray、Tuic、hysteria2、sing-box 八合一一键脚本

The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement learning and imitation learning.

🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org

Machine learning, in numpy

Wazuh - The Open Source Security Platform. Unified XDR and SIEM protection for endpoints and cloud workloads.

魔搭大模型训练推理部署工具箱，支持LLaMA、千问、ChatGLM、BaiChuan等多种模型及LoRA等多种训练方式(The LLM training/inference/deployment framework of ModelScope community, Support various models like LLaMA, Qwen, ChatGLM, Baichuan and others, and training methods like LoRA, ResTuning, NEFTune, etc.)

The open-source hub to build & deploy GPT/LLM Agents ⚡️

APM, (Application Performance Management) tool for large-scale distributed systems.

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

Open-source, secure environment with real-world tools for enterprise-grade agents.

Community guide to using YubiKey for GnuPG and SSH - protect secrets with hardware crypto.

BISHENG is an open LLM devops platform for next generation Enterprise AI applications. Powerful and comprehensive features include: GenAI workflow, RAG, Agent, Unified model management, Evaluation, SFT, Dataset Management, Enterprise-level System Management, Observability and more.

Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

:trollface: Self-hosted, lightweight server and website monitoring and O&M tool

UAParser.js - The Essential Web Development Tool for User-Agent Detection. Detect Browsers, OS, Devices, Bots, Apps, AI Crawlers, and more. Run in Browser (client-side) or Node.js (server-side).

Gathers machine learning and deep learning models for Stock forecasting including trading bots and simulations

Python implementation of algorithms from Russell And Norvig's "Artificial Intelligence - A Modern Approach"

StarCraft II Learning Environment

The paper list of the 86-page SCIS cover paper "The Rise and Potential of Large Language Model Based Agents: A Survey" by Zhiheng Xi et al.

Universe: a software platform for measuring and training an AI's general intelligence across the world's supply of games, websites and other applications.

A customisable 3D platform for agent-based AI research

The modern Java bytecode editor

OpenTelemetry Collector

A complete web-based remote monitoring and management web site. Once setup you can install agents and perform remote desktop session to devices on the local network or over the Internet.

AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.

Open Source Vulnerability Management Platform

Build ChatGPT over your data, all with natural language

A flexible event/agent & automation system with lots of bees 🐝

An easy to use and powerful chaos engineering experiment toolkit.（阿里巴巴开源的一款简单易用、功能强大的混沌实验注入工具）

The first "code-first" agent framework for seamlessly planning and executing data analytics tasks.

High Performance TCP/UDP/HTTP Communication Component

Service orchestration and management tool.

Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and CamelAI

Merlin is a cross-platform post-exploitation HTTP/2 Command & Control server and agent written in golang.

The open source platform for AI-native application development.

Open Source Cloud Native Application Protection Platform (CNAPP)

Linux运维监控工具，支持系统硬件信息，内存，CPU，温度，磁盘空间及IO，硬盘smart，GPU，防火墙，网络流量速率等监控，服务接口监测，大屏展示，拓扑图，端口监控，进程监控，docker监控，日志监控，文件防篡改，数据库监控，指令批量下发执行，web ssh，Linux面板(探针)，告警，SNMP监测，K8S，Redis，Nginx，Kafka，资产管理，计划任务，密码管理，工作笔记

A Next-Generation Training Engine Built for Ultra-Large MoE Models

🤖 AgentVerse 🪐 is designed to facilitate the deployment of multiple LLM-based agents in various applications, which primarily provides two frameworks: task-solving and simulation

Paper list of multi-agent reinforcement learning (MARL)

[COLM 2024] OpenAgents: An Open Platform for Language Agents in the Wild

👮 A PHP desktop/mobile user agent parser with support for Laravel, based on Mobiledetect

ModelScope-Agent(开源版GPTs): An agent framework connecting models in ModelScope with the world

Device detection (phone, tablet, desktop, mobile grade, os, versions)

Bistoury是去哪儿网的java应用生产问题诊断工具，提供了一站式的问题诊断方案

Up-to-date simple useragent faker with real world database

Implementations from the free course Deep Reinforcement Learning with Tensorflow and PyTorch

A flexible, high-performance 3D simulator for Embodied AI research.

Mesa is an open-source Python library for agent-based modeling, ideal for simulating complex systems and exploring emergent behaviors.

Main repository for Datadog Agent

Check out the new game server: