MedResearcher-R1 is a Deep Research Agent designed for medical scenarios.

The official repo of "WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents"

Official code for paper "SPA-RL: Reinforcing LLM Agent via Stepwise Progress Attribution"

AgentScope: Agent-Oriented Programming for Building LLM Applications

Kimi K2 is the large language model series developed by Moonshot AI team

Universal memory layer for AI Agents; Announcing OpenMemory MCP - local and secure memory management.

slime is a LLM post-training framework for RL Scaling.

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

An AI agent development platform with all-in-one visual tools, simplifying agent creation, debugging, and deployment like never before. Coze your way to AI Agent creation.

Qwen Code is a coding agent that lives in the digital world.

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…

Use Claude Code as the foundation for coding infrastructure, allowing you to decide how to interact with the model while enjoying updates from Anthropic.

A VS Code extension to view Apache Parquet files as JSON

Official repo for "PAPO: Perception-Aware Policy Optimization for Multimodal Reasoning"

Awesome-Long2short-on-LRMs is a collection of state-of-the-art, novel, exciting long2short methods on large reasoning models. It contains papers, codes, datasets, evaluations, and analyses.

Open source code for Paper: Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions

An open-source AI agent that brings the power of Gemini directly into your terminal.

Tongyi DeepResearch, the Leading Open-source DeepResearch Agent

Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (LLM).

verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"

Lightweight coding agent that runs in your terminal

A MemAgent framework that can be extrapolated to 3.5M, along with a training framework for RL training of any agent workflow.

[CVPR 2025] A Comprehensive Benchmark for Document Parsing and Evaluation

Bitcoin Core integration/staging tree

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

A high-quality tool for convert PDF to Markdown and JSON.一站式开源高质量数据提取工具，将PDF转换成Markdown和JSON格式。

A fast and lightweight framework for creating decentralized agents with ease.

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)