Forge lifts local models into reliable agentic performers

Forge’s guardrail stack pushed an 8‑billion‑parameter model from single‑digit success rates to 84 % on a 26‑scenario evaluation suite. The same stack raised Anthropic’s Sonnet 4.6 from 85 % to 98 % on the identical wo…

The system works as a drop‑in proxy that sits between any OpenAI‑compatible client and a local model server. It speaks both the OpenAI chat‑completion API and Anthropic’s messages API. Clients such as opencode, Contin…

Forge also ships a WorkflowRunner that defines tools, picks a backend, and manages the full lifecycle: system prompts, tool execution, context compaction, and guardrails. A SlotWorker adds priority‑queued GPU access f…