Automated README summary
Automatically summarized from the README on 20 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
An OpenAI-compatible LLM router built on LiteLLM. Clients send one model id, "jev-router", and the router selects which underlying model serves each request. For developers who want automatic model selection across providers like OpenRouter.
How it uses Jev
When TYPESAFE_API_KEY is set, JevDecider picks one model from the eligible candidates in router.yaml. It receives a minimized summary of the request: recent messages' roles and truncated text, plus image/tool signals. The chosen model serves the request; failures fall back to router.yaml's fallback.
Primitives:choice
Technique worth stealing
Filter candidates by capability (vision, output length, tools) before the decision, then let Jev choose among the eligible set.
Try it
pip install "litellm[proxy]" pyyaml; set OPENROUTER_API_KEY and TYPESAFE_API_KEY; run litellm --config config.yaml --port 4000.
Model judgments from README excerpts
Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.
Models & evaluation dates
- Inclusion gate
jev-1.13.0- Project signals
jev-1.13.0- Category
jev-1.13.0- Pattern tags
jev-1.13.0
Evidence
These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.
- Jev is core to the projectnot found in the excerpt0.24
- Shows a System One patternnot found in the excerpt0.22
- Describes handling uncertaintyFound in material0.80
- Reports measured numbersnot found in the excerpt0.04
- Is a runnable toolFound in material0.94
- Top-10 learning shortlist signalnot found in the excerpt0.38
- Is a replica of the modelnot found in the excerpt0.04
- Solves a common problem (0–2)score on a 0–2 scale1.82 / 2
- About JevFound in material0.97
no-judgment band (0.40–0.60)
no-judgment band (0.40–0.60)
The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 20 Sept 2026.