SuperAPI AI Directory
Partner with us中文AI newsFavorites

AI agents

2,963 results · Page 30 of 83

Agent Genesis

AI agents

Agent Genesis is an open-source AI component library for developers, providing copy-and-paste-ready AI agent code snippets to help developers integrate AI capabilities into their projects without writing everything from scratch. It offers a variety of AI templates, including RAG workflows and question-answering bots. The code is reusable, well-documented, and easy to maintain, is released under the MIT License, and has established an official partnership with IBM Watsonx.

Read more

agent-coworker

AI agents

CoWorker Protocol (agent-coworker) is a P2P agent collaboration protocol based on XMTP, with the core idea of "Skill-as-API": skills run on their owner's own machine, and others can only call them remotely and obtain results; the code, prompts, and methodology themselves are never transmitted. It supports end-to-end encryption, revocable trust, and asynchronous delegation, and has zero dependencies. The project was developed by Ziwei Zhao, Dantong Liu, and Xizhi Ding, with Wenxuan Wang (Renmin University of China) as advisor, is licensed under MIT, and provides GitHub, PyPI, and official website entry points.

Read more

Agent-R1

AI agents

Agent-R1 is a unified, modular agent reinforcement learning framework for training multi-step LLM agents. It trains through a step-native reinforcement learning loop: the model observes the environment, generates actions, receives tool or environment feedback, and continues executing until the task is completed or terminated. Unlike single-turn RL pipelines that treat interaction as a single ever-growing prompt-response pair, Agent-R1 models each episode as a step-level MDP transition, making tool use, environment state, context management, reward assignment, and policy optimization explicit components of the same training foundation. The framework is based on a Step-level MDP and provides three major design goals: step-level trajectory representation, flexible context management, and algorithm-system decoupling, supporting capabilities such as on-policy distillation (OPD), StepPO, multimodal vision-language model agents, and process rewards.

Read more