OpenForgeRL: Train Harness-native Agents in Any Environment

За 30 секунд

Что произошло

OpenForgeRL is an open-source framework enabling end-to-end reinforcement learning training of AI agents within complex inference harnesses like Claude Code and Codex.

Почему это важно

Matters for engineers building or training agentic systems who need to train agents directly in production harnesses without rewriting infrastructure.

На что обратить внимание

Framework is new research; error recovery remains weak, and practical deployment complexity with Kubernetes orchestration and proxy infrastructure is not fully detailed.