jevrag

Name: jevrag
Availability: InStock
Author: ajanm007

Jev-powered: Replaces hardcoded RAG thresholds with explicit calibrated decision points. Five primitives (retrieval stopping, chunk splitting, context selection, answer abstention, cache trust) behind

High Quality

New

Join 0+ developers using this skill

command

Development & Code Tools

intermediate

0 installs

4/5 quality

View Source

Last updated: September 23, 2026

AI Skill Market Insights

Real data. Real impact.

Popularity

Rising

Emerging

Active Users

Developers

Quick Start

Install Command

git clone https://github.com/ajanm007/jevrag.git

TEAR & SHARE

2-3hrs/WK

RISING

0.0K+ USING

jevrag

Replaces hardcoded RAG thresholds with explicit calibrated decision points. Five primitives (retrieval stopping, chunk splitting, context selection, answer abstention, cache trust) behind one swappable state → Decision → confidence → action interface, each evaluated on real datasets with a calibration harness that reports honestly.

Where Jev makes the decision

jevrag/decision.py — the

ask(state, questions) -> DecisionResult

method calls

api.typesafe.ai/v1/systemone

via the Jev backend. All five primitives in

jevrag/primitives/

route through this method.

Why it matters

Adds structured choices or scores to the workflow; performance and cost benefits have not been independently verified.

Claims & evidence

Author and repository text is preserved where clear; missing languages are enriched automatically. Checks establish source-level Jev integration, not runtime, safety, or performance validation.

About Jev

Jev is TypeSafe AI's System One decision model: it returns typed scores and choices (not free text), so agents can route, filter and gate at low latency and cost.

Source: ajanm007/jevrag — 1 stars, MIT. Listed by Awesome Jev.

jevrag

AI Skill Market Insights

Quick Start

Install Command

TEAR & SHARE

Tags

GitHub MCP Server

Be Part of the 0+ Developer Community

jevrag

Where Jev makes the decision

Why it matters

Claims & evidence

About Jev

License

Pal MCP Server

using-git-worktrees

finishing-a-development-branch

test-driven-development

Channels

Learn

Compare

Company

Agents