开源的端到端产品级通用智能体，支持多智能体设计和快速部署。
DeepSeek-V3 is an advanced Mixture-of-Experts language model with innovative inference capabilities and efficient training methods.
DeepSeek-R1 is an open-source AI model focused on enhancing reasoning capabilities through reinforcement learning.
A curated list of papers for generalist agents in both virtual and physical worlds.
MiniMind is an open-source project to train a 26M-parameter GPT model from scratch in just 2 hours.
CAMEL is an open-source multi-agent framework focused on finding the scaling laws of agents.
OpenManus is an open-source framework for building general AI agents without an Invite Code.
Finetune Llama 4, TTS, DeepSeek-R1, Gemma 3 & Reasoning LLMs 2x faster with 70% less memory!
R1-searcher incentivizes search capability in LLMs using reinforcement learning for enhanced reasoning performance.
Autonomously train research-agent LLMs on custom data using reinforcement learning and self-verification.
Pioneering Multimodal Reasoning with CoT, an open-source model for advanced visual and text reasoning.
Implementation of all RAG techniques in a simpler way, focusing on educational and modifiable code.
AISecKit
