index / dhirajpatra/agent-harness-with-jev-llm
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.
Research and EvalsRoutingListedPython
Repository
Stars0
LanguagePython
License—
Created2026-09-22
Last pushed2026-09-22
Officialno
Judgment
Genuine Jev project0.94
gate 0.5
Uses Jev at runtime0.89
Is a meta list0.02
Is a reimplementation0.79
Quality scales
Substance1.64 / 3
gate 0.5
Docs2.98 / 3
Novelty0.90 / 3
Composite score0.58
Category distribution
Agent and Dev Tooling0.70
Learning0.21
Applications0.04
Integrations0.04
Research and Evals0.01
Other0.00
SDKs and Clients0.00
Games and Simulation0.00
Assigned categoryResearch and Evals
Category probability0.70
Category confidence0.67
PatternRouting
Pattern confidence0.99
Curation
StatusListed
Reasongate passed
README pickno
Overridenone
Sources
- search:"typesafe.ai"
- search:"system one" jev
- search:jev in:name,description,readme created:2026-09-22
Provenance
Modeljev-1.13.0
Question setv2
Judged at2026-09-22 11:45 UTC