Stars
Benchmarking Language Agents Under Controllable and Extreme Context Growth
Doing simple retrieval from LLM models at various context lengths to measure accuracy
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 collection of projects designed to help developers quickly get started with building deployable applications using the Claude API
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…
Code search MCP for Claude Code. Make entire codebase the context for any coding agent.
A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.
A Model Context Protocol server for Excel file manipulation
[ICLR 2026] Agentic Reinforced Policy Optimization (ARPO)
This MCP server integrates with your Google Drive and Google Sheets, to enable creating and modifying spreadsheets.
[ICLR 2026] The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution
Pushing Test-Time Scaling Limits of Deep Search with Asymmetric Verification
An extremely fast Python package and project manager, written in Rust.
A Model Context Protocol (MCP) server for Gmail integration in Claude Desktop with auto authentication support. This server enables AI assistants to manage Gmail through natural language interactions.
Muon is an optimizer for hidden layers in neural networks
[ICLR 2026] End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning
From Accuracy to Robustness: A Study of Rule- and Model-based Verifiers in Mathematical Reasoning.
Train your Agent model via our easy and efficient framework
[ICLR2026] Laser: Learn to Reason Efficiently with Adaptive Length-based Reward Shaping
🔧Tool-Star: Empowering LLM-brained Multi-Tool Reasoner via Reinforcement Learning
Scaling Deep Research via Reinforcement Learning in Real-world Environments.