SelfJev is an open 4B decisions model you host yourself. Ask typed questions about any text (yes/no, pick one, pick any, score) and get calibrated probabilities. Jev-compatible: point TypeSafe's SDK at your server with two env vars. Fine-tune it on your data.
No comment highlights available yet. Please check back later!
About SelfJev on Product Hunt
“Jev-compatible self-hosted decisions mode”
SelfJev launched on Product Hunt on September 30th, 2026 and earned 75 upvotes and 1 comments, placing #20 on the daily leaderboard. SelfJev is an open 4B decisions model you host yourself. Ask typed questions about any text (yes/no, pick one, pick any, score) and get calibrated probabilities. Jev-compatible: point TypeSafe's SDK at your server with two env vars. Fine-tune it on your data.
SelfJev was featured in Open Source (68.9k followers), Artificial Intelligence (479.9k followers) and GitHub (41.4k followers) on Product Hunt. Together, these topics include over 171.4k products, making this a competitive space to launch in.
Who hunted SelfJev?
SelfJev was hunted by Julien Wuthrich. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how SelfJev stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Julien Wuthrich
Hi Product Hunt 👋 I’m Julien, maker of SelfJev.
I love decision models like TypeSafe’s Jev.
Instead of asking an LLM to write an answer and then parsing it, you ask a typed question like:
→ “Does the customer want a refund?”
→ “Which team should handle this?”
…and get a calibrated probability back.
They’re fast, cheap, and don’t hallucinate output formats.
The problem: some teams can’t send sensitive text to someone else’s API — support tickets, medical notes, contracts, internal data.
So I built SelfJev: an open decision model you run on your own GPU.
🧩 What it does
4 answer types
Noul → P(yes)
Choice → pick one
Score → ordered scale
Multi → pick any
🔌 Jev-compatible API
Already using TypeSafe’s Python SDK?
Just point:
TYPESAFE_BASE_URL
TYPESAFE_API_KEY
to your SelfJev server.
No application code changes.
🌳 Shared computation
SelfJev reads the document once, then reuses that computation across all questions and answer choices using a shared-prefix tree.
So asking many questions about the same document costs little more than asking one.
🎯 Fine-tuning
Fine-tune on your own labels with:
selfjev finetune
Or use the OpenAI-style HTTP fine-tuning API.
🚀 Self-hosting
Run locally:
pip install "selfjev[serve]" && selfjev serve
Works on a 24 GB GPU.
Or deploy to AWS with:
selfjev deploy aws up
📊 How good is it?
On our evaluation suites:
Text decisions: SelfJev-4B 95.7% vs Jev 97.2%
AI-response review: SelfJev-4B 93.1% vs Jev 92.5%
These are our own suites with AI-authored labels, not a universal benchmark or ranking.
Every evaluation report is available in the repo, and the dataset is public on Hugging Face as Decision Bench.
🔒 What SelfJev is not
It’s not a hosted service.
There’s no SelfJev cloud.
You run the model. Your data stays with you.
The code is Apache-2.0, and I’ve also made the full research journal public — including the experiments and dead ends.
I’d love to hear what decisions you’d use SelfJev for, and especially where it gets them wrong. 🙂
model -> https://huggingface.co/Jwuthrich