A local server that reads next-token probabilities from a fine-tuned Spark model and returns Choice, Score, and Noul answers with zero generated tokens.
Organization repository on GitHub
The open, local take on Jev: typed decisions from an LLM, without generating a single token
Repo stats from the GitHub API, cached Sep 2026.Homepage
uv sync --locked
uv run rizzo download
uv run rizzo serveWatch out
Apache-2.0. Independent of TypeSafe; it does not claim to reproduce Jev's architecture or RLCD. The 4B Q8_0 download is about 4.4 GB.
Posts, threads, and videos about this entry from around the web.
Hacker News: Jev implemented in 25 lines of Python
bashbjorn400 points · 128 commentsJev in 25 Lines of PythonRead the thread on Hacker NewsHacker News: Kev: a tiny Jev-like family built on Qwen3.5
tosh458 points · 199 commentsKev: Tiny Jev-like family of decision models built on top of Qwen3.5Read the thread on Hacker NewsHacker News: Show HN: OpenDecision, a local decision model with a Doom demo.
dwa35926 pointsShow HN: OpenDecision – a 400M zero-shot model makes local decisions, plays DoomRead the thread on Hacker NewsX: deepseek-v4.1-flash-jev
you can make any open source model behave like jev with just a bit of inference engineering. it's shockingly easy. to prove it, we built a new endpoint we're calling deepseek-v4.1-flash-jev. see the demo below. here's how it's done: sglang (an inference engine) offers a Show more
Glossary definitions related to this entry.
Mushroom-Systems/lichenPython
khimaros/verdictPython
feder-cr/jevPythonOriginal write-ups that draw on this entry.
Posts from builders shipping with Jev right now.
Instant compaction with Jev
found the perfect use case for @typesafeai Jev: instant compaction in 2026, why is compaction still a summarization prompt? Jev can make it instant by scoring every tool call and dropping what’s irrelevant
A Claude session from 1M to 86K tokens
This is actually insane. This uses @typesafeai Jev model, as a plugin in Claude to review all the un-nesseasary tool calls, and it takes 1s to run! Like, literally, 1 second to take my Claude session from nearly 1M to ... 86K tokens! 😮 Ask your claude to install it and be Show more
found the perfect use case for @typesafeai Jev: instant compaction in 2026, why is compaction still a summarization prompt? Jev can make it instant by scoring every tool call and dropping what’s irrelevant
Vercel's fx safety reviewer, 18x faster
We're seeing extraordinary results from @typesafeai. Default mode in 𝚏𝚡 is auto, with a safety reviewer analyzing every command. That reviewer runs on GPT Luna today. Jev is up to 18x faster (p95) *and* more accurate. It's coming to @vercel AI Gateway and likely new default.
We benchmarked fx auto mode (safety) classifier with @typesafeai's Jev. tl;dr: ~5-18x faster and more accurate than 𝚐𝚙𝚝-𝟻.𝟼-𝚕𝚞𝚗𝚊, our current top choice
Jev lands on OpenRouter
Jev by @typesafeai is now on OpenRouter, in beta. Jev is a System One model. Instead of generating text, it takes your app's state plus a typed question and returns a typed decision with a probability attached. There is no JSON prompting, parsing layer, and nothing to validate Show more
700 leads scored for $0.09
JEV is INSANE. We gave it 700 high-intent leads and personalised outreach messages. In 40 seconds, it predicted how each message would perform, assigned a confidence score and detected lead-message mismatches. All for just $0.09. JEV can also score leads, analyse buying Show more
Beating Gemini Flash Lite on an eval
Ran @typesafeai's Jev against an existing classifier eval that previously used Gemini 2.5 Flash Lite. It won both on quality (saturated the eval) and speed (6x)
