Search Results for "deep learning toolbox"

zeta is a deep learning library focused on providing cutting-edge AI and neural network models with a strong emphasis on research-grade architectures. It includes state-of-the-art implementations for rapid experimentation and model building.

AGI Computer Control is an experimental autonomous software system designed to operate independently and generate income without human intervention. It aims to simulate artificial general intelligence (AGI) by leveraging evolutionary algorithms, deep active inference, and other advanced AI techniques. The project explores the boundaries of machine autonomy and self-directed behavior in computational environments.

CUDA Agent is a research-driven agentic reinforcement learning system designed to automatically generate and optimize high-performance CUDA kernels for GPU workloads. The project addresses the long-standing challenge that efficient CUDA programming typically requires deep hardware expertise by training an autonomous coding agent capable of iterative improvement through execution feedback. Its architecture combines large-scale data synthesis, a skill-augmented CUDA development environment, and long-horizon reinforcement learning to build intrinsic optimization capability rather than relying on simple post-hoc tuning. ...

Agent Reinforcement Trainer, or ART is an open-source reinforcement learning framework tailored to training large language model agents through experience, making them more reliable and performant on multi-turn, multi-step tasks. Instead of just manually crafting prompts or relying on supervised fine-tuning, ART uses techniques like Group Relative Policy Optimization (GRPO) to let agents learn from environmental feedback and reward signals.

...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.

The project is the codebase for an AI agent named Cicero developed by Facebook Research. It is designed to play the board game Diplomacy by combining open-domain natural language negotiation with strategic planning. The repository includes training code, model checkpoints, and infrastructure for both language modelling (via the ParlAI framework) and reinforcement learning for strategy agents. It supports two variants: Cicero (which handles full “press” negotiation) and Diplodocus (a variant...

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. The AI Agent Host provides a seamless interface for managing and querying data, visualizing results, and coding in real-time. The AI...