A full-stack LLM development toolkit from NVIDIA covering synthetic data generation, multi-backend inference, model training, and 11-category benchmark evaluation, scaling from single GPU to tens-of-thousands-GPU Slurm clusters.
The Open Source AI Engineering Platform for Agents, LLMs & Models, providing experiment tracking, model registry, LLM observability, evaluation, prompt optimization, and a unified AI gateway.
Blades is a multimodal AI Agent framework for the Go language, supporting custom models, tools, memory, middleware, and more. It's designed for multi-turn conversations, chain-of-thought reasoning, and structured output applications.
A Python library for orchestrating zero-shot computer vision models, enabling custom end-to-end pipeline creation without needing to collect and annotate large training datasets.
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。
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.
A lightweight framework for automating large language models and developing autonomous language agents, enabling developers to build LLM applications with a Pythonic approach while supporting multiple models and tool integrations.
ReCall is a novel reinforcement learning framework that trains LLMs to reason with tool calls, enabling them to solve complex problems without requiring supervised data on tool use trajectories or reasoning steps.
Page 1 / 2 · 15 total
Get the latest AI tools and trends delivered straight to your inbox. No spam, just intelligence.
