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
- Stars
- 1
- Forks
- 0
Why it is listed
This Jev-pattern harness demonstrates routing and risky-tool gating, but its local classifier is a TF-IDF/cosine-similarity substitute rather than TypeSafe’s trained Jev model.