はてなブックマーク

A reliability layer for self-hosted LLM tool-calling. Forge lifts an 8B local model to the top of its class on multi-step agentic workflows through guardrails (rescue parsing, retry nudges, step enforcement) and context management (VRAM-aware budgets, tiered compaction). The current top self-hosted config (Ministral-3 8B Instruct Q8 on llama-server) scores 86.5% across forge's 26-scenario eval sui