Starred repositories
Write HTML. Render video. Built for agents.
TCOD: Exploring Temporal Curriculum in On-Policy Distillation for Multi-turn Autonomous Agents
The open-source managed agents platform. Turn coding agents into real teammates — assign tasks, track progress, compound skills.
The official paper for EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL.
A Model Context Protocol server for searching and analyzing arXiv papers
AI-agent Skill for generating polished HTML slide decks: editorial magazine and Swiss layouts, image prompts, social covers, and a WebGL/low-power presentation runtime.
A curated collection of papers and resources on On-Policy Distillation for Large Language Models.
A Survey on Large Foundation Models as Game Players - Datasets, Models, Harness and Benchmarks
A macOS menu bar application that monitors AI coding assistant usage quotas. Keep track of your Claude, Codex, Antigravity ,and Gemini usage at a glance.
A Survey on Large Language Model-Based Game Agents (ACM CSUR)
An Extended Benchmarking of Multi-Agent Reinforcement Learning Algorithms in Complex Fully Cooperative Tasks
A Unified Virtual Filesystem For AI Agents
📡 Your own AI-powered news radar. Generates daily briefings in English & Chinese. | 用 AI 构建你专属的新闻雷达
A Systematic Analysis and Discussion of Claude Code for Designing Today's and Future AI Agent Systems
[ACL 2026 Oral] The official code of "ImplicitMemBench: Measuring Unconscious Behavioral Adaptation in Large Language Models"
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.
PERSONA: Dynamic and Compositional Inference-Time Personality Control via Activation Vector Algebra (ICLR 2026)
A StarCraft II bot api client library for Python 3
OpenClaw-RL: Train any agent simply by talking
The official repo for "CodeScaler: Scaling Code LLM Training and Test-Time Inference via Execution-Free Reward Models"
Coding agent skill for making reveal.js presentations
Dr. MAS is an end-to-end RL training framework for multi-agent LLM systems, supporting the co-training of multiple (heterogeneous) LLMs.