Open Frontier Intelligence

AgentENV (AENV) is a distributed platform for running agent environments at scale.

A high-throughput and memory-efficient inference and serving engine for LLMs

EdgeBench: Unveiling scaling laws of learning from real-world environments

[ACL 2026 Oral] VFA: Empowering Multilingual MLLMs via Vision-Free Adaptation

[ACL 2026 Oral] VFA: Empowering Multilingual MLLMs via Vision-Free Adaptation

🏛️ 三省六部制 · OpenClaw Multi-Agent Orchestration System — 9 specialized AI agents with real-time dashboard, model config, and full audit trails

Checkpoint-engine is a simple middleware to update model weights in LLM inference engines

Scaling Long-Horizon SWE Environments

FORTSearcher: Synthesizing Hard-to-Shortcut Search Tasks for Deep Search Agents

Computer Environments Elicit General Agentic Intelligence in LLMs

Uni-Agent is a framework for training long-horizon agents.

Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.

nnScaler: Compiling DNN models for Parallel Training

Data-centric LLM training with dynamic sample selection, domain mixture optimization, and example reweighting inside the LLaMA-Factory training loop.

An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale

A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎，预测万物

An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

A curated list of papers, tools, and benchmarks on LLM-based computer-use agents, covering both terminal/CLI and GUI approaches.

Specification and documentation for Agent Skills

OpenClaw-RL: Train any agent simply by talking

The open source coding agent.

A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, has memory, scheduled jobs, and runs dir…