agent-harness-with-jev-llm
dhirajpatra/agent-harness-with-jev-llm
A small multi-agent harness built around the pattern from LangChain's post: use a fast, non-generative "System One" classifier (TypeSafe AI's Jev) for structured in-loop decisions -- routing and risky-tool-call gating -- and reserve a real chat LLM for the genuinely open-ended reasoning.
Python
- 星标
- 1
- 派生
- 0
收录依据
这个 Jev 模式的代理框架演示任务路由和高风险工具门槛,但本地分类器是 TF-IDF/余弦相似度替代实现,并非 TypeSafe 训练的 Jev。