jevbooks

← All projects

jev-figure-router

hoangngochuong24947-gif/jev-figure-router

Universal figure and diagram router for AI agents, powered by TypeSafe Jev.

Classification & Routing1.00Runner-up: Verification & GuardrailsFunnel
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

A router that maps an AI agent's visualization request to one of six rendering branches (scientific plots, architecture diagrams, slides, AI-generated visuals, materials computation, chart MCP), returning a target tool and output format.

How it uses Jev

The README describes Jev as a System-1 decision engine that classifies the drawing query in under 300ms and returns a branch, target tool, rendering format, confidence and fast-path flag. It does not state which Jev primitives (Choice/Score/Noul) are used or how the state is constructed.

Technique worth stealing

Fast-path routing: if confidence >= 0.85, invoke the specialized tool directly instead of loading the full router table.

Try it

git clone the repo, run ./install.sh, set OPENROUTER_API_KEY, then python3 scripts/fast_route.py -q "..." --template

View on GitHub

Start using Jev: API key and your first request →

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 projectFound in material0.83
  • Shows a System One patternunclear0.57
  • Describes handling uncertaintynot found in the excerpt0.09
  • Reports measured numbersnot found in the excerpt0.09
  • Is a runnable toolFound in material0.82
  • Top-10 learning shortlist signalnot found in the excerpt0.29
  • Is a replica of the modelnot found in the excerpt0.11
  • Solves a common problem (0–2)score on a 0–2 scale1.49 / 2
  • About JevFound in material0.93
Signals
Jev is core to the project0.83Shows a System One pattern0.57Describes handling uncertainty0.09Reports measured numbers0.09Is a runnable tool0.82Top-10 learning shortlist signal0.29Is a replica of the model0.1100.51Solves a common problem (0–2)1.49 / 2012

no-judgment band (0.40–0.60)

Design patterns
Funnel0.8500.51

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.