Open-World Self-Evolution for LLM Agents — agents that build both their skills and their own verification signals from scratch, with no target-task supervision. (Code coming soon.)

Multi-agent research automation framework for LLM agents, with adversarial lab meetings, paper-review rounds, auditable Markdown workflows, an autonomous runtime watchdog, and a pixel-art web dashboard.

LLM agents as your hyperparameter optimizer.

The python library for research and development in NLP, multimodal LLMs, Agents, ML, Knowledge Graphs, and more.

A framework for discovering, compiling, and validating reusable skills for scientific agents.

OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards

🦖 Serverless AI Agent Framework with Geo-distributed Edge AI Infra.

A Python library for building AI agents that leverage the full power of Google Antigravity.

Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning