Updated Nov 10, 2026
855 projects, posts and guides about Jev, the System One model from TypeSafe AI. Each entry links to its source and shows the cost and speed its author reported.
Diogo Almeida
@CompleteSkeptic
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x cheaper (w/ output tokens free) • Frontier composable intelligence optimized for decisions AFAICT the shortest path to AI-based economic revolution
Newest first, 365–398 of 1072. All 1072 in curated order
Neha Sharma
@hellonehha
As Jev (@typesafeai) is the talk of the town, and people are having fun finding new use cases for it. I built a real-time demo of smart AI agent routing for anyone working on AI tools, agents, or products. this is what I have done for one of my project. https://youtu.be/c8qV0f4XnRY
XRouting and model choice
Archive
@ArchiveExplorer
Holy crap, who the hell did this?!! Someone open-sourced a Jev-powered second brain for AI agents and lets you plug it straight into your own agent. GitHub's already at 925 stars, repo's called Hermes-Jev-Skills. You just run one install command, and Jev takes over every tiny decision your agent burns premium tokens on. Which model answers, which skill to load, which memories matter, what survives when context gets cut. Give it your computer or browser and it'll pick the next click, but only from actions you already marked safe. It'll sort your inbox into lanes, strip hidden prompt injections out of search results, and triage every message in ~0.4 seconds. Claude Code and Codex support - they threw that in too. No dependencies, no patching Hermes core, and your API key never touches the agent Link's right here: http://github.com/kerpopule/hermes-jev-skills The catch? Jev itself is a paid cloud API. The skills run on your machine; the decisions don't. But hey, a decision costs a fraction of a cent, everything fails open if Jev goes down, and your expensive model finally gets to do only the thinking. Who needs a damn frontier model picking which file to open!
Theo - t3.gg
@theo
This is a terrible compaction strategy that fundamentally doesn't understand how compaction and context management work. Seems like a lot of people are confused so let's break this down. 1. Compaction isn't a filter The role of compaction is to clean up history to keep the agent focused, not just deleting noise. It should be used sparingly when context gets too long, not constantly to keep context small. 2. Jev doesn't even know what it's deciding on! Models use the context of the thread to decide what to keep or not keep in a summary. This implementation goes through on a "line-by-line" (per tool call) basis to decide what should be left or deleted. Not only does this 32k token context model know very little of what happened before, but (in this implementation) it doesn't even know what the result of the tool call is! Deleting these things randomly will keep the model from knowing what it's tried and dooms you to end up in "stupid loops" where the model keeps trying the same thing over and over. 3. You're giving up the reasoning entirely Frontier models from OpenAI, Anthropic, XAI, and Google do not share reasoning traces over the API. They share encrypted payloads, which Jev cannot see (and often will drop). Anthropic is even stricter with this, requiring you to preserve the entire history in order to get any of the reasoning data. As a result, using this in Claude Code guarantees the model will act way dumber. 4. Models are tuned on their compaction flows For the last year, Frontier Labs have been including compaction and long runs as part of the training process. These models have learned ways to compact that are more effective than any rudimentary solution. Fun fact: If you switch models in Codex and compaction is necessary, compaction will run on the model that was previously used in the thread. 5. Cache writes are more expensive than cache reads. Cache writes are the biggest cost by far for agents. I often see cache write costs go over 60% of my total LLM spend in my personal use of Claude Code and Codex. Cache writes are insanely expensive when data earlier in the history is changed (because the old cache is invalidated when things change at the top). Every history edit requires a cache rewrite for ANY data past the history edit. If your history is "1,2,3,4,5,6" and you delete "2", you have to rewrite "3,4,5,6". This is more expensive than leaving "2" in the history. Good news. Since we're already killing all of the reasoning tokens by doing this stupid compaction strategy, the rewrite cost won't actually be that high because the model is missing so much data! 🙃🙃 6. The implementation is hot garbage. > "Whatever is not kept is deleted permanently, but the assistant can always re-run a tool or re-read a file." Good luck with that one. To be clear: this is a cool experiment and I find it genuinely interesting. That said, if you think this style of bs filtering on a probability threshold is actually a compaction strategy, I highly recommend you just use the defaults in tools like Claude Code and Codex. You're much less likely to hurt yourself that way.
Guidex.com
Theo on why per-tool-call filtering is not compaction: lost reasoning, higher cache-write costs and agents stuck in loops.
GitHubOpen source
A source-backed field guide to TypeSafe’s System One model.
AbdelStark
592
GitHubOpen source
Examples indexed by the decision each one makes.
kydlikebtc
601
GitHubOpen source
Curated Jev resources and runnable examples for typed decisions.
AppitStudio
104Guideyoutube.com/@GregIsenberg
Greg Isenberg and Ryan Vogel on the Startup Ideas Pod: what Jev is, the businesses it unlocks, and how to call it today through the Vercel AI Gateway.
GitHubSDKs and integrations
A provider-neutral System One runtime for TypeScript and Pi.
iamaamir
73
Guideyoutube.com/@syntaxfm
CJ from Syntax explains how Jev works, then demos browser use, classification, code review, a model router and a chat bot with no LLM.
GitHubRouting and model choice
Typed IntentSpec contracts as the input layer for routers.
angel291592
538
GitHubOpen source
Four decision-quality tools on Jev, with code keeping the final say.
klauswg
15
GitHubOpen source
A self-hosted API for Laya, compatible with the Jev API format.
1Panel-dev
103Guideyoutube.com/@vogeldev
Ryan Vogel runs Jev on 100 and then 1,000 of his emails: category, priority, spam and reply predictions.
Guideyoutube.com/@AICodeKing
AICodeKing tests support routing, refund detection, prompt-injection resistance and browser automation.
GitHubAgents and browsers
A research design for a Jev-native agent system.
6Mikao9
GitHubOpen source
A local proxy that answers typed LLM decisions with a Laya head.
bladedevoff
70Guideyoutube.com/@retriever-ai
Retriever AI tests Jev on real browser tasks: where it worked, where it struggled, and how they will use it next to larger models.
Guideyoutube.com/@NidhiSinghAttri
Nidhi Singh’s setup: one terminal, three AI subscriptions, and Jev picks the model for Claude Code, Codex and Cursor.
GitHubSDKs and integrations
80+ TypeScript recipes for agents, retrieval and verification.
agencyenterprise
20
Guideyoutube.com/@avb_fj
Neural Breakdown with AVB takes Jev apart and looks at architectures for models that predict JSON. The video starts at 6:57.
GitHubAgents and browsers
PickAn LLM proposes, Jev answers, code decides, every step leaves a receipt.
TypeSafe AI
30
GitHubBenchmarks and evals
Calibration-aware reinforcement learning for decision systems.
weitianxin
Same directory, different order: the entries added most recently, rather than the curated order the home page opens in. The date on a card is the day it was added here, not the day its author published it — this directory is newer than most of the work in it.