jevbooks

← All projects

metis

Ayush0054/metis

Automatic GitHub issue triage and PR screening using TypeSafe AI Jev.

Automated README summary

Automatically summarized from the README on 4 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

Metis is a Python framework for building workflows powered by TypeSafe AI's Jev model. It provides a reusable GitHub Action for automatic issue triage and PR screening, and includes example workflows for support routing.

How it uses Jev

Jev is used via the Jev integration. In workflows, steps call jev.check(state, criteria) to get yes/no probabilities for a checklist, or jev.evaluate(state, questions) to run Choice, Noul, and Score questions. Results are used to make routing, labeling, or screening decisions based on thresholds.

Primitives:choicescorenoul

Technique worth stealing

Define workflows as classes with named steps; use Jev for typed judgments and thresholds for decisions.

Try it

pip install metis-workflow, then run: metis-workflow run --workflow-file examples/support_routing.py --event ticket.json

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 material0.72
  • Shows a System One patternnot found in the excerpt0.27
  • Describes handling uncertaintynot found in the excerpt0.05
  • Reports measured numbersnot found in the excerpt0.04
  • Is a runnable toolFound in material0.94
  • Top-10 learning shortlist signalnot found in the excerpt0.31
  • Is a replica of the modelnot found in the excerpt0.04
  • Solves a common problem (0–2)score on a 0–2 scale1.83 / 2
  • About JevFound in material0.97
Signals
Jev is core to the project0.72Shows a System One pattern0.27Describes handling uncertainty0.05Reports measured numbers0.04Is a runnable tool0.94Top-10 learning shortlist signal0.31Is a replica of the model0.0400.51Solves a common problem (0–2)1.83 / 2012

no-judgment band (0.40–0.60)

Design patterns
Traffic light0.97Questionnaire0.94Grey zone0.85Scorecard0.79Funnel0.68Inspection0.4100.51

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 4 Oct 2026.