Stars
Official repo for paper: "GRACE: Generative Representation Learning via Contrastive Policy Optimization"
Reading notes about Multimodal Large Language Models, Large Language Models, and Diffusion Models
A version of verl to support diverse tool use
All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container.
Official Code for "Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search"
Evaluating Deep Multimodal Reasoning in Vision-Centric Agentic Tasks
Data Synthesis for Deep Research Based on Semi-Structured Data
[arXiv: 2505.17163] OCR-Reasoning Benchmark: Unveiling the True Capabilities of MLLMs in Complex Text-Rich Image Reasoning
Democratizing AI scientists with ToolUniverse
A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning
Build effective agents using Model Context Protocol and simple workflow patterns
🚀 The fast, Pythonic way to build MCP servers and clients
MCP Server for kubernetes management commands
🪐 ✨ Model Context Protocol (MCP) Server for Jupyter.
Official repo for the paper "Scaling Synthetic Data Creation with 1,000,000,000 Personas"
MCP-based Agent Deep Evaluation System
Connect APIs, remarkably fast. Free for developers.
Examples of using Pipedream's MCP server in your app or AI agent.
An agent benchmark with tasks in a simulated software company.
🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation
SWE-Factory: Your Automated Factory for Issue Resolution Training Data and Evaluation Benchmarks
FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus Agent Tools, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae…
Implementations of Reinforcement Learning and Planning algorithms
Build, evaluate and train General Multi-Agent Assistance with ease
🤗 smolagents: a barebones library for agents that think in code.
Scaling Deep Research via Reinforcement Learning in Real-world Environments.
[NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards