Automated README summary
Automatically summarized from the README on 28 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
agrouter is a Go CLI that picks the coding-agent CLI, model, and reasoning effort for each prompt from a catalog of Claude Code and Codex options, so cheap models handle trivial work and strong ones handle hard work.
How it uses Jev
Jev acts as the routing classifier. In staged routing it chooses among eligible CLIs, then the chosen CLI's models, then that model's effort levels, each stage narrowing the next. With --doc it first rates project complexity 0-10, which is passed as state to later stages. Results become a JSON decision or exec arguments.
Primitives:choicescore
Technique worth stealing
Staged routing: each classifier decision narrows the candidate set for the next stage, with confidence conditional on prior stages.
Try it
go install github.com/SvetlovA/agrouter/cmd/agrouter@latest, set AGROUTER_CLASSIFIER_API_KEY, then run agrouter -p "...".
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-1.14.0- Project signals
jev-1.14.0- Category
jev-1.14.0- Pattern tags
jev-1.14.0
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 excerpt0.30
- Shows a System One patternunclear0.41
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersnot found in the excerpt0.02
- Is a runnable toolFound in material0.93
- Top-10 learning shortlist signalnot found in the excerpt0.29
- Is a replica of the modelnot found in the excerpt0.04
- Solves a common problem (0–2)score on a 0–2 scale1.56 / 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 28 Oct 2026.