User repository on GitHub
Find me a charging stop. Code does the arithmetic, Jev judges the prose.
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Demos & Experiments
Find me a stop
An EV charging-stop planner: describe your situation in one sentence, set origin, destination, battery and arrival time, code filters candidates from Open Charge Map, and Jev picks the stop that fits your request.
- Stars
- 0
- Language
- TypeScript
- Reading time
- 2 min
- Published by
- Community
- Author
- Suv4o
- Last verified
- Oct 2026
- Languages
- TypeScript
- Platforms
- API
- Capabilities
- Open source
Highlights
- Code does the arithmetic and only ever rules chargers out; the winning stop always comes from Jev.
- Candidates are fetched from Open Charge Map in a box around your journey, then shortlisted before Jev decides.
- Example prompt: driving to Geelong at 9% battery, late, with a sleeping kid, and no dodgy stops.
- Jev is TypeSafe AI's System One model: it answers structured questions with typed answers and probabilities instead of generating text.
Watch out
README and GitHub metadata reviewed 2026-10-17; the excerpt stops inside the 'How It Works' steps, so the shortlisting rules, the Jev request shape and setup instructions are not visible, and no license is listed. The article link is commented out.
Questions about this entry
Short answers drawn from the linked project or page.
An EV charging-stop planner built with Jev: describe your situation in one sentence, choose origin, destination, battery level and arrival time, and it finds the charger on your route that best fits.
The README's rule is 'code filters, Jev picks': code does all the arithmetic and only ever rules chargers out, and the winning stop always comes from Jev.
Code fetches chargers from Open Charge Map within a box around your journey, then shortlists them before the Jev decision step; the captured excerpt stops before the shortlisting details.
Jev is TypeSafe AI's System One model: it does not generate text but answers structured questions with typed answers and probabilities, in a single request per trip.
One example is: 'I'm at 9% heading to Geelong with my kid asleep in the back. It's late and I don't want to stop anywhere dodgy.', showing that free-text context feeds the choice.
The README contains a commented-out link to an article titled 'Is Jev Just Hype, or a Genuinely Different Kind of AI?', to be uncommented once live; it is not an active link in the captured text.
GitHub metadata lists TypeScript, 0 stars and 0 forks, created and last pushed 2026-10-06, with no license recorded in the digest.
More Jev resources like this
Three TypeScript demos built on one pattern for students: Jev answers a typed question with a probability, your code decides what to do, and Claude works only where it is needed. Demos cover Jira triage, pre-flight checks and PR routing.
Jev Demos & Experiments#community#github#demo
Community
soyjorgepilo/jev-demoTypeScript
soyjorgepilo/jev-demoTypeScriptA TypeScript WebGL lab that explains a JEV-style decision architecture layer by layer, from user intent and context through a decision core with scoring, policy and confidence to execution and output.
Jev Demos & Experiments#community#github#typescript
Community
pandeeswaran-08/jevTypeScript
pandeeswaran-08/jevTypeScriptA pilot build of the Parking Operations Decision Layer PRD: the support desk, agent guard and shared decision layer send each item to Jev as typed questions in one call, then rules and a confidence gate route it to AUTO, REVIEW, HUMAN or BLOCKED with an audit log.
Jev Demos & Experiments#community#github#typescript
A travel rebooking demo that classifies a trip disruption, checks itinerary feasibility, and ranks concrete rebooking options against a traveler's ordered preferences, returning ordered choices with probabilities.
Jev Demos & Experiments#community#typescript#travel
Community
A Chinese-language e-commerce customer-service demo on FastAPI, LangGraph and React: adaptive retrieval routing with hybrid BM25-plus-vector search, and intent classification switchable between TypeSafe Jev's structured choice interface and DeepSeek.
Jev Demos & Experiments#community#github#python
Community
gbh1234/Adaptive-ragPython
gbh1234/Adaptive-ragPythonA TypeScript SDK demo for Jev, TypeSafe's System One model: 14 numbered scenarios teach how to prepare state, write questions and use answers, with root examples that ask whether a customer message sounds frustrated and flag it for review.
Jev Demos & Experiments#community#github#typescript
Community
gopinav/jev-demoTypeScript
gopinav/jev-demoTypeScriptFrom 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.