Starred repositories
Code and implementations for the paper "AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning" by Zhiheng Xi et al.
The code for paper "MemGym: a Long-Horizon Memory Environment for LLM Agents".
MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory
This is a library to use with Robinhood Financial App. It currently supports trading crypto-currencies, options, and stocks. In addition, it can be used to get real time ticker information, assess …
[NeurIPS 2025 Spotlight] OpenCUA: Open Foundations for Computer-Use Agents
A transparent, minimal, and hackable agent framework. ~300 lines of readable code. Full control, no magic.
An Open-Source Large-Scale Reinforcement Learning Project for Search Agents
The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!
The code for paper "EPO: Entropy-regularized Policy Optimization for LLM Agents Reinforcement Learning"
An extremely fast Python package and project manager, written in Rust.
[EACL'26] DeepSieve: Information Sieving via LLM-as-a-Knowledge-Router
[ICML 2025 Oral] Official repo of EmbodiedBench, a comprehensive benchmark designed to evaluate MLLMs as embodied agents.
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)
[ICML'25] Our study systematically investigates massive values in LLMs' attention mechanisms. First, we observe massive values are concentrated in low-frequency dimensions across different attentio…
[ICLR 2025] Benchmarking Agentic Workflow Generation
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthr…
User Profile-Based Long-Term Memory for AI Chatbot Applications.
Code for EACL 26 Findings paper "I-MCTS: Enhancing Agentic AutoML via Introspective Monte Carlo Tree Search"