Search Results for "strategy"

AI-Trader is an open-source AI-powered quantitative trading framework designed to combine financial analysis, machine learning, and autonomous trading workflows into a unified research platform. The project integrates large language models, financial indicators, market analysis pipelines, and automated decision-making systems to support strategy generation and market prediction tasks. It is built to help researchers and developers experiment with AI-assisted trading strategies using historical and real-time financial data. The framework supports modular components for portfolio analysis, signal generation, market reasoning, and trading automation, allowing users to customize workflows for different trading styles and asset classes. ...

Hindsight is an advanced, open-source memory system for AI agents designed to enable long-term learning, reasoning, and consistency across interactions by treating memory as a first-class component of intelligence rather than a simple retrieval layer. It addresses one of the core limitations of modern AI agents, which is their inability to retain and meaningfully use past experiences over time, by introducing a structured, biomimetic memory architecture inspired by how human memory works....

...Built as an extension of the veRL reinforcement learning infrastructure, the project focuses on enabling scalable training for agents that perform multi-step reasoning and decision-making tasks. The framework supports multi-turn interactions between agents and their environments, allowing the system to receive feedback after each step and adjust its strategy accordingly. This step-wise interaction model makes it possible to train agents to operate in long-horizon scenarios where decisions depend on cumulative context and previous outcomes. Developers can configure memory modules that determine how historical information is stored and incorporated into each step of the reasoning process.

...The framework runs these subtasks in isolated Git worktrees so agents can work on separate components of a project without interfering with one another. By coordinating these agents through a recursive task decomposition strategy, the system allows large problems to be solved collaboratively by multiple AI processes. The architecture is designed to experiment with large-scale agent coordination and distributed problem solving.

...It provides developers and quants with structured modules to fetch market data, process time series, generate technical indicators, and construct features appropriate for machine learning models, while also supporting backtesting and evaluation metrics to measure strategy performance. Built with modularity in mind, FinRobot allows users to plug in custom models — from classical algorithms to deep learning architectures — and orchestrate components in pipelines that can run reproducibly across experiments. The framework also tends to include automation layers for deployment, enabling trained models to operate in live or simulated environments with scheduled re-training and risk controls in place.

...Instead of relying only on static training data, the agent performs searches, visits pages, and extracts evidence before forming answers to complex queries. It is built to operate end-to-end: planning a research strategy, gathering sources, reasoning over conflicting claims, and writing a grounded response. The repository includes evaluation results on multi-step QA and research benchmarks, illustrating how web-time context boosts accuracy. Because the system is modular, you can swap the search component, reader, or policy to fit private deployments or different data domains. ...

Comprehensive agent-based e-commerce system realizing price negotations and combining: (a) adaptability and intelligence (change strategy according to history of purchases), (b) mobility (based on transfer of negotation modules and agents).

Symbiomotive is an extensible engine for modeling multi-agent environments that exhibit self-organizing, symbiotic behaviors.

sciSoccer is a framework to develop strategies for soccer playing robots like RobotCup. It is composed by libraries for robot communication, video capturing, image recognition, strategy implementation and a graphical user interface.

This project aims to promote computer science. In the way of 'serious games', it will particularly help students to improve their computer skills. This project provides a framework to create space battles between AI.

Tryx is a simple board game, and is an evolution of the classic Tic-Tac-Toe game. The difference is that each player can have at most 3 symbols on the board: when a player puts its fourth symbol on the board, the oldest symbol disappears.

The central aim of OrkAPI is to be an interface to any kind of Ork-related data within Java. It also features a GUI that can assist in creating a move and inspecting the collected data. There are many points to extend OrkAPI with "Plugin" classes.

Formicidae is the official simulator and visualizer for the Ant-Wars competitive programming site, written in Java and SISC. The site is hosted at www.ant-wars.net.

RoboScout is a software that simulates realistic vehicle behaviour that drives by itself and avoids obstacles in a virtual world. Every instant, the vehicle decides by itself how to modify its speed and direction according to its environment.

Educational game framework supporting board games, strategy games, and other grid-based game boards. Currently uses Python/wxPython as the application language/library. C++ libs included to help create AI for the various games.

Anarchonomy is a Java application simulating AI agent based production, consumption, trade and force with a minimum of economic assumptions, letting users create and change their own rule and scenario sets.

OpenArena is an developing enviroment for autonomous software agents and software worlds.

This project aim to provide a crowd movement simulation based on primitive human behaviours and emerging behaviours for research and educational purposes. The application (front-end) is generic and can be reused.

using simple cuboids and gjk algorithm, this general purpose algorithm gives a ready made code to work with swissranger 3D camera.

ORTS is an RTS game engine. It is server/client-based and therefore suitable for on-line competitions. Games and the OpenGL GUI are scriptable. A sample game with many MD3 models is included. SVN access is provided through the home page.