Automated README summary
Automatically summarized from the README on 3 Nov 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 (Claude Code, Codex, or others from config), model, and reasoning effort for each prompt, so callers don't need to know each CLI's flags. It runs in decision mode (prints JSON) or exec mode (runs the CLI).
How it uses Jev
Jev (TypeSafe) is the default routing classifier. agrouter asks it to choose among eligible CLIs, then models, then effort levels in up to three stages, each narrowing the next; with --doc it first rates project complexity 0-10. The chosen values become the CLI's model/effort arguments in exec mode.
Primitives:choice
Technique worth stealing
Staged routing: each stage's candidate set is narrowed by the previous choice, and a caller-supplied value fixes its stage so it isn't re-decided.
Try it
go install github.com/svtlv/agrouter/cmd/agrouter@latest, set the classifier API key, then run agrouter with a prompt.
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 excerpt0.11
- Shows a System One patternunclear0.44
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersnot found in the excerpt0.03
- Is a runnable toolFound in material0.93
- Top-10 learning shortlist signalnot found in the excerpt0.27
- Is a replica of the modelnot found in the excerpt0.03
- Solves a common problem (0–2)score on a 0–2 scale1.47 / 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 3 Nov 2026.