Official Code of Memento: Fine-tuning LLM Agents without Fine-tuning LLMs

AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, GitHub Copilot CLI, OpenClaw, Factory Droid, Trae, Google Antigravity). Turn any folder of code, docs, papers, images, o…

Academic Research Skills for Claude Code: research → write → review → revise → finalize

Public repository for Agent Skills

AI agents running research on single-GPU nanochat training automatically

This project includes code for using the WebGym framework to train web agentic models.

Co-evolving policy actors and experience extractors for efficient experience-driven agent RL

General technology for enabling AI capabilities w/ LLMs and MLLMs

OpenClaw-RL: Train any agent simply by talking

The absolute trainer to light up AI agents.

Reinforcement Learning from Text Feedback

Reinforcement Learning via Self-Distillation (SDPO)

Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning

Machine Learning Interviews from FAANG, Snapchat, LinkedIn. I have offers from Snapchat, Coupang, Stitchfix etc. Blog: mlengineer.io.

CL-bench: A Benchmark for Context Learning

Awesome In-Context RL: A curated list of In-Context Reinforcement Learning - - —

A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning

A Gym for Agentic LLMs

Defeating the Training-Inference Mismatch via FP16

The best ChatGPT that $100 can buy.

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Accompanying code for "Discovering State-of-the-art Reinforcement Algorithms" Nature publication

[ICLR 2026] Agentic Reinforced Policy Optimization (ARPO)

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

Building Open LLM Web Agents with Self-Evolving Online Curriculum RL

Democratizing Reinforcement Learning for LLMs