Search Results for "agent based" - Page 4
Sort By:
Showing 121 open source projects for "agent based"
View related business solutions-
Our Free Plans just got better! | Auth0You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
-
Context for your AI agentsBuild data pipelines that feed your AI models and agents without managing infrastructure. Crawl any website, transform content, and push directly to your preferred vector store. Use 10,000+ tools for RAG applications, AI assistants, and real-time knowledge bases. Monitor site changes, trigger workflows on new data, and keep your AIs fed with fresh, structured information. Cloud-native, API-first, and free to start until you need to scale.
-
1
GNNePCSAFT
Smart Thermodynamic Modeling with Graph Neural Networks
The project focuses on using Graph Neural Networks (GNN) to estimate the pure-component parameters of the Equation of State PC-SAFT. Currently, the model takes into account the hard-chain, dispersive, and associative terms of PC-SAFT. Future work on polar and ionic terms is being studied. FeOS is used for the PC-SAFT calculations. The estimated parameters can be used in DWSIM and Aspen HYSYS process simulators. -
2
Muse: Middleware Universal Scripting idE
Automate: WebSphere; WebLogic; JBoss; Glassfish; Tomcat; Linux, WinRM
.... *** OPEN SOURCE - GPL3/EPL. Use Python / Jython to automate WebSphere, WebLogic, JBoss, Glassfish and Tomcat Middleware Estates over JMX, both SSL and non-SSL + Linux SSH (agent-less) + WinRM Target all 5 servers, Linux and WinRM from the same workspace. Familiar Eclipse based Jython and Python Development IDE, pre-configured and ready to go. 4-Click Installer. Win x64, Linux WINE x64. Built-In JVM. Java 8/9/10, Amazon Corretto, JETPack13/14/16, IBM SDK Compatible. *** Now with powerful JBoss / GlassFish / Tomcat / Linux Active Auditing Framework. ... -
3
AI-Agent-Host
The AI Agent Host is a module-based development environment.
The AI Agent Host integrates several advanced technologies and offers a unique combination of features for the development of language model-driven applications. The AI Agent Host is a module-based environment designed to facilitate rapid experimentation and testing. It includes a docker-compose configuration with QuestDB, Grafana, Code-Server and Nginx. -
4
PromethAI
Open-source framework that gives you AI Agents
PromethAI-Backend is a backend framework for AI-driven automation and knowledge extraction. It is designed to integrate with large language models (LLMs) to provide AI-enhanced workflows, including content generation, summarization, and data analysis. -
Axe Credit Portal - ACP- is axefinance’s future-proof AI-driven solution to digitalize the loan process from KYC to servicing, available as a locally hosted or cloud-based software.Founded in 2004, axefinance is a global market-leading software provider focused on credit risk automation for lenders looking to provide an efficient, competitive, and seamless omnichannel financing journey for all client segments (FI, Retail, Commercial, and Corporate.)
-
5
ParlAI
A framework for training and evaluating AI models
ParlAI is a comprehensive research platform for building, training, and evaluating dialogue agents across a wide variety of tasks and datasets. It provides a unified interface—agents, teachers, and worlds—so the same model can be trained on multi-turn chit-chat, question answering, task-oriented dialogue, retrieval, or safety-focused datasets without changing core code. The library integrates tightly with PyTorch and supports both generative and retrieval-augmented models, along with... -
6
Multi-Agent Particle Envs
Code for a multi-agent particle environment used in a paper
Multiagent Particle Environments is a lightweight framework for simulating multi-agent reinforcement learning tasks in a continuous observation space with discrete action settings. It was originally developed by OpenAI and used in the influential paper Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments. The environment provides simple particle-based worlds with simulated physics, where agents can move, communicate, and interact with each other. ... -
7
TradeMaster
TradeMaster is an open-source platform for quantitative trading
TradeMaster is a first-of-its-kind, best-in-class open-source platform for quantitative trading (QT) empowered by reinforcement learning (RL), which covers the full pipeline for the design, implementation, evaluation and deployment of RL-based algorithms. TradeMaster is composed of 6 key modules: 1) multi-modality market data of different financial assets at multiple granularities; 2) whole data preprocessing pipeline; 3) a series of high-fidelity data-driven market simulators for mainstream... -
8
Gym
Toolkit for developing and comparing reinforcement learning algorithms
Gym by OpenAI is a toolkit for developing and comparing reinforcement learning algorithms. It supports teaching agents, everything from walking to playing games like Pong or Pinball. Open source interface to reinforce learning tasks. The gym library provides an easy-to-use suite of reinforcement learning tasks. Gym provides the environment, you provide the algorithm. You can write your agent using your existing numerical computation library, such as TensorFlow or Theano. It makes no... -
9
Throttled
Workaround for Intel throttling issues in Linux
This tool was originally developed to fix Linux CPU throttling issues affecting Lenovo T480 / T480s / X1C6. The CPU package power limit (PL1/2) is forced to a value of 44 W (29 W on battery) and the temperature trip point to 95 'C (85 'C on battery) by overriding default values in MSR and MCHBAR every 5 seconds (30 on battery) to block the Embedded Controller from resetting these values to default. On systems where the EC doesn't reset the values (ex: ASUS Zenbook UX430UNR), the power limit... -
All-in-one security tool helps you prevent ransomware and breaches.Blumira’s detection and response platform enables faster resolution of threats to help you stop ransomware attacks and prevent data breaches. We surface real threats, providing meaningful findings so you know what to prioritize. With our 3-step rapid response, you can automatically block known threats, use our playbooks for easy remediation, or contact our security team for additional guidance. Our responsive security team helps with onboarding, triage and ongoing consultations to continuously help your organization improve your security coverage.
-
10
Google Research Football
Check out the new game server
Google Research Football is a reinforcement learning environment simulating soccer matches. It focuses on learning complex behaviors such as team collaboration and strategy formation in competitive settings. -
11
Zenoss Community Edition
Zenoss - Intelligent IT Operations Management
Zenoss provides software-defined IT operations for the world’s largest organizations. We deliver the ultimate level of IT service health with simplicity by providing the most granular and intelligent IT service modeling possible, at any scale, and sharing these unique insights with other IT operations management (ITOM) tools to make them more efficient. Zenoss Community Edition is not a “demo” or trial version of Zenoss Enterprise or Zenoss Cloud! Before You install Zenoss Community... -
12
DouZero
[ICML 2021] DouZero: Mastering DouDizhu
DouZero is a reinforcement learning-based AI for playing DouDizhu, a popular Chinese card game. It focuses on perfecting AI strategies for competitive play using value-based deep RL techniques. -
13
ReinventCommunity
Jupyter Notebook tutorials for REINVENT 3.2
This repository is a collection of useful jupyter notebooks, code snippets and example JSON files illustrating the use of Reinvent 3.2. -
14
galacteek
Multi-platform browser for the distributed web
galacteek is a multi-platform Qt5-based browser and semantic agent for the distributed web. Be sure to install all the gstreamer packages on your system to be able to use the mediaplayer. After opening/mounting the DMG image, hold Control and click on the galacteek icon, and select Open and accept. You probably need to allow the system to install applications from anywhere in the security settings. -
15
Multi-Agent path planning in Python
Python implementation of a bunch of multi-robot path-planning
multi_agent_path_planning is a Python-based implementation of multi-agent pathfinding algorithms for coordinating multiple agents in shared environments without collisions. It is useful in robotics, warehouse automation, and gaming AI. -
16
Atgen A2 Automation
Atgen A2 is a radically simple Workload Automation & Scheduling tool.
Atgen A2 is a radically simple IT automation solution that automates application builds, continuous testing, data parsing & processing, report generation, batch processing, job scheduling, and many other IT needs. Avoid running repetitive batch jobs and managing access to deploy and update your applications — automate in a language that approaches plain English, using SSH or WinRM, with no agents to install on remote systems. https://www.atgensoft.com/ You can install a released version... -
17
googler
Google Search, Google Site Search, Google News from the terminal
googler is a power tool to Google (Web & News) and Google Site Search from the command-line. It shows the title, URL and abstract for each result, which can be directly opened in a browser from the terminal. Results are fetched in pages (with page navigation). Supports sequential searches in a single googler instance. googler was initially written to cater to headless servers without X. You can integrate it with a text-based browser. However, it has grown into a very handy and flexible... -
18
MADDPG
Code for the MADDPG algorithm from a paper
MADDPG (Multi-Agent Deep Deterministic Policy Gradient) is the official code release from OpenAI’s paper Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments. The repository implements a multi-agent reinforcement learning algorithm that extends DDPG to scenarios where multiple agents interact in shared environments. Each agent has its own policy, but training uses centralized critics conditioned on the observations and actions of all agents, enabling learning in... -
19
End-to-End Negotiator
Deal or No Deal? End-to-End Learning for Negotiation Dialogues
End-to-End Negotiator is a PyTorch-based research framework developed by Facebook AI Research to train neural agents capable of conducting strategic negotiations in natural language. The project implements the models presented in two key papers: “Deal or No Deal? End-to-End Learning for Negotiation Dialogues” and “Hierarchical Text Generation and Planning for Strategic Dialogue”. It enables agents to plan, reason, and communicate effectively to maximize outcomes in multi-turn negotiations... -
20
moosha-ai
An intelligent virtual assistant (IVA) or intelligent personal assista
An intelligent virtual assistant (IVA) or intelligent personal assistant (IPA) is a software agent that can perform tasks or services for an individual based on commands or questions. Sometimes the term "chatbot" is used to refer to virtual assistants generally or specifically accessed by online chat. In some cases, online chat programs are exclusively for entertainment purposes. Some virtual assistants are able to interpret human speech and respond via synthesized voices. ... -
21
SMAC
SMAC: The StarCraft Multi-Agent Challenge
SMAC (StarCraft II Multi-Agent Challenge) is a benchmark environment for cooperative multi-agent reinforcement learning (MARL), based on real-time strategy (RTS) game scenarios in StarCraft II. It allows researchers to test algorithms where multiple units (agents) must collaborate to win battles against built-in game AI opponents. SMAC provides a controlled testbed for studying decentralized execution and centralized training paradigms in MARL. -
22
deep-q-learning
Minimal Deep Q Learning (DQN & DDQN) implementations in Keras
The deep-q-learning repository authored by keon provides a Python-based implementation of the Deep Q-Learning algorithm — a cornerstone method in reinforcement learning. It implements the core logic needed to train an agent using Q-learning with neural networks (i.e. approximating Q-values via deep nets), setting up environment interaction loops, experience replay, network updates, and policy behavior. -
23
AESOP-ACP
A simulation framework for production process modeling in Python
ACP is a simulation framework aimed to production processes modeling. Compared to its ancestor - jES - it is lightweight, more general and written in Python. The basic goal of the simulator is to find bottlenecks in production process which could be hard to detect with traditional approaches (e.g., top-down). In addition, it can be used to speculate about “what-if” scenarios in order to suggest solution strategies. -
24
Universe Starter Agent
A starter agent that can solve a number of universe environments
The universe-starter-agent repository is an archived OpenAI codebase designed as a starter reinforcement-learning agent that can interact with and solve tasks in OpenAI’s Universe environment platform. Its purpose is to serve as a baseline or reference implementation so researchers or developers can see how to build agents that operate in real-time, visual environments (e.g., games, browser apps) via pixel observations and keyboard/mouse actions. Under the hood, this starter agent implements... -
25
Madara
Middleware for distributed applications
The purpose of the project is to develop a portable programming framework that facilitates distributed and multi-threaded programming for C++, Java, and Python. MADARA was originally developed as an agent-based middleware specifically for real-time, distributed artificial intelligence, but is now more general purpose for distributed timing, control, knowledge and reasoning, and quality-of-service. MADARA is composed of several tools and middleware, and the main entry point into the system is the Knowledge and Reasoning Language (KaRL) Engine, which provides a real-time scripting language for nanosecond execution times hooked into a flexible transport layer for distributed reasoning. ...
