QeRL enables RL for 32B LLMs on a single H100 GPU.

"LightReasoner: Can Small Language Models Teach Large Language Models Reasoning?"

"DeepResearch-Eval: An End-to-End Evaluation Framework for DeepResearch Systems"

All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container.

Awesome-GraphRAG: A curated list of resources (surveys, papers, benchmarks, and opensource projects) on graph-based retrieval-augmented generation.

Build resilient language agents as graphs.

ScaleCUA is the open-sourced computer use agents that can operate on corss-platform environments (Windows, macOS, Ubuntu, Android).

Paper2Agent is a multi-agent AI system that automatically transforms research papers into interactive AI agents with minimal human input.

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more!

MCP Server for Computer Use in Windows

"VideoRAG: Chat with Your Videos"

🚀 EvoAgentX: Building a Self-Evolving Ecosystem of AI Agents

[Survey] A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems

MiroMind Research Agent: Fully Open-Source Deep Research Agent with Reproducible State-of-the-Art Performance on FutureX, GAIA, HLE, BrowserComp and xBench.

OpenCUA: Open Foundations for Computer-Use Agents

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

Renderer for the harmony response format to be used with gpt-oss

Pre-trained, Scalable, High-performance Reward Models via Policy Discriminative Learning.

Open-source, secure environment with real-world tools for enterprise-grade agents.

Fetch an entire site and use it as an MCP Server

"VideoAgent: All-in-One Agentic Framework for Video Understanding, Editing, and Remaking"

"DeepCode: Open Agentic Coding (Paper2Code & Text2Web & Text2Backend)"

DeerFlow is a community-driven Deep Research framework, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community.

Solve Visual Understanding with Reinforced VLMs

TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.

Profile-Based Long-Term Memory for AI Applications. Memobase handles user profiles, memory events, and evolving context — perfect for chatbots, companions, tutors, customer service bots, and all ch…