AI Model Training

Absolute Zero LeapLabTHU

The zero-data reasoning training paradigm proposed by Tsinghua University and other institutions, the model independently generates and solves questions to strengthen reasoning

Count Count

A collaborative notebook and visualization platform for modern data teams

Gradio Gradio

Use a few lines of Python to build an interactive web interface for machine learning models and share it as an open source library

ACE-Ego ACE-Ego

One brain, multiple types of embodied operation VLA model research project

DeepEval Confident AI

Open source evaluation framework for LLM application RAG and Agent, using Pytest style to incorporate evaluation into the R&D process

HELM HELM

The large model overall evaluation system launched by Stanford University emphasizes transparent evaluation of multiple scenarios and indicators.

DeepSeek API 深度求索

DeepSeek open API platform provides V3/R1/V4 series model inference capabilities at a very low price

HoneyHive HoneyHive

Observation, evaluation, monitoring and continuous improvement platform for production-level AI Agents

Agenta Agenta

The open source LLMOps platform covers prompt word experiments, evaluation, online and observation, and supports 50+ models and Agent orchestration.

Aim Stack Aim

Open source ML experiment tracking and visualization platform for teams focused on data sovereignty

DreamGen NVIDIA

NVIDIA Robot Learning Research Project Using Video World Models to Generate Synthetic Training Data

AnythingLLM AnythingLLM

All-in-one RAG desktop and server applications that can be deployed privately, integrating documents, models and agents into the same workspace