User repository on GitHub
- Forks
- 12
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Tools & CLIs
Passage (Working Memory Jev)
A localhost teaching aid that uses the real Jev API to review English instructional passages and estimate how many ideas a learner must hold at once, comparing the demand against a 1-5 slot budget with average, peak, and confidence labels.
- Stars
- 77
- Language
- Python
- Reading time
- 2 min
- Published by
- Community
- Author
- austinaway
- Last verified
- Oct 2026
Used inJev for Education
Highlights
- Reviews a whole passage, then sentences and smaller reading steps, highlighting source text and drawing confirmed connections between exact source occurrences.
- Each decision batch is sent PASSAGE_JEV_SAMPLES times (default 2, range 1-5) and averaged because Jev answers are not deterministic.
- Average is the equal-weight mean across reading steps and peak is the largest count; estimated demand can exceed the selected 1-5 slot budget.
- Confidence is Low, Moderate, or Unavailable and is not an empirically calibrated percentage; incomplete checks leave Provisional Jev estimates.
- Runs at http://127.0.0.1:8765 with Python 3.12 and Node 22; macOS gets Setup.command and Start.command, and the key stays on the local server.
Quickstart
bash
git clone https://github.com/AustinAWay/Working-Memory-Jev.git
cd Working-Memory-Jev
python3 -m venv .venv
.venv/bin/python -m pip install -r requirements.lock
cd web
npm ci
npm run build
cd ..
cp .env.example .env
.venv/bin/python run.pyWatch out
README and license reviewed 2026-10-15. The app calls itself an experimental teaching aid and states its slot estimates are not validated measurements of memory or calibrated probabilities of overload; analysis sends the passage and learner context to TypeSafe, and the Working Memory Jev License is custom terms rather than an open-source license.
Questions about this entry
Short answers drawn from the linked project or page.
It helps educators inspect where instructional text may ask a learner to hold too many ideas or relationships at once, by estimating demand per reading step and comparing it against a selected slot budget of 1 to 5.
It runs on localhost but calls the real Jev API: a local parser proposes reading steps and exact source occurrences, and Jev makes bounded choices about familiarity, grouping, and relationships. Each decision batch is sampled and averaged.
Average is the equal-weight mean across reading steps, peak is the largest count, and both compare against the 1-5 slot budget, which estimates can exceed. Confidence labels are Low, Moderate, or Unavailable, not calibrated percentages.
Python 3.12, Node.js 22 with npm, and your own TypeSafe/Jev API key in .env. Build the web frontend with npm ci and npm run build, then run .venv/bin/python run.py and open http://127.0.0.1:8765.
Scope is English instructional prose: formulas, code, ambiguous references, implicit prerequisites, and incorrect assumptions about the learner can produce poor results, and changing the source or learner context requires a new analysis.
One check can make many Jev requests, and provider pricing, quotas, and billing apply separately; the UI's cost estimate is not an invoice. Setting PASSAGE_JEV_SAMPLES=1 halves requests at the cost of noisier decisions.
Free for individuals and non-commercial use; an organization with more than one employee or any commercial use needs written permission first by emailing the author, under the Working Memory Jev License rather than an open-source license.
More Jev resources like this
An English reading tutor for Chinese learners: R2T2 streaming ASR transcribes as you read aloud with a 160 ms step and committed text that only grows, then Jev answers closed questions per mismatched word — same word or not, error category, sentence score.
Jev Tools & CLIs#community#catalog-import#madewithjev
Community
wquguru/dashengJavaScript
wquguru/dashengJavaScriptOpen-source tool that automatically optimizes the instructions and decision criteria of TypeSafe Jev Choice definitions from labeled data, searching with EvoPrompt or GEPA and scoring candidates with a normalized Brier score.
Jev Tools & CLIs#community#catalog-import#logicrw
Latitude is an open-source observability platform for AI agents: one line of telemetry captures traces, failing traces group into tracked signals, and fixes are dispatched to coding agents and replayed against real traces.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
latitude-dev/latitude-llmTypeScript
latitude-dev/latitude-llmTypeScriptToolkit, knowledge base and local dashboard for building with Jev via OpenRouter Alpha Decisions or the TypeSafe Direct API: a zero-dependency SQLite request log, a localhost REST server and Python CLI demos.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
rileycarney/jevtoolsHTML
rileycarney/jevtoolsHTMLA source-visible Android vision control prototype where a vision agent reads screenshots, a text-only supervisor plans, and TypeSafe JEV chooses among candidate actions; an ADB executor runs them under a local web console.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
ztrrtuo/jev-phonecontrolPython
ztrrtuo/jev-phonecontrolPythonMaykana's free tool that lets a cheap AI test a web app like a person: write checks in plain sentences, Jev picks the next step from a short list, and below 80% confidence it stops and hands over to a human instead of clicking. A DeepSeek vision pass reports visual defects.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
elshinq/jevaluateJavaScript
elshinq/jevaluateJavaScriptFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.