Flexible and scalable reinforcement learning training infrastructure for embodied and agentic AI post-training, decoupling logical workflow composition from efficient physical execution via the M2Flow paradigm.
An all-in-one data preparation system for LLMs, supporting reproducible operator pipelines for data generation, cleaning, evaluation, and filtering.
An open-source framework for building, evaluating, and training general multi-agent systems. Features natural language agent creation, distributed reinforcement learning training pipeline, and complex environment interactions. Ranks top on authoritative benchmarks including GAIA, OSWorld, and VisualWebArena.
An AI-powered data science team of agents that automates data loading, cleaning, feature engineering, EDA, visualization, and machine learning modeling (H2O + MLflow) through specialized agent collaboration, featuring a Streamlit visual pipeline studio to perform common data science tasks 10X faster.
An open-source AI agent platform offering no-code workflow building with dynamic graph-based solutions powered by the Actor Model, supporting multiple LLM integrations and real-time monitoring.
An open-source AI R&D automation tool developed by Microsoft that focuses on automating data and model-driven industrial R&D processes, enabling AI to drive data-driven AI to enhance R&D efficiency and productivity.
MiniMax-M2.1 is a state-of-the-art AI model designed for real-world development and agent scenarios. It excels in multilingual software development, complex workflow execution, and full-stack application development, providing open, controllable, and transparent AI agent capabilities。
A Large Language Model (LLM) Agent Framework developed by PaddlePaddle, based on ERNIE Bot's capabilities, providing tool orchestration, automatic scheduling, rich pre-built components, and low development barriers to help developers quickly build AI-native applications。
AutoDroid is a system that empowers Large Language Models to utilize smartphones for intelligent task automation, combining LLM capabilities with Android device interaction to automate complex mobile app tasks.
An end-to-end reinforcement learning training framework for orchestrating tools and agentic workflows that coordinates various models and tools to achieve more efficient solutions than large language models alone.
Page 1 / 2 · 20 total
Get the latest AI tools and trends delivered straight to your inbox. No spam, just intelligence.
