search
Jev
Trends
- 1
Ollaya is a project being discussed on Hacker News, described as 'Ollama for open-source, Jev-style decision models'. The framing suggests a tool that makes decision-making models as easy to run locally as Ollama made large language models, though the single post title gives little detail. With 537 likes and a high rank, commenters appear interested in the analogy to Ollama, but the posts collected do not explain what the tool actually does or why it is generating attention.
- 2Thousands welcome cycling students in Kragujevac ahead of Serbian election●Thousands welcome cycling students in Kragujevac ahead of Serbia’s Oct. 25 election
Crowds of thousands lined the streets of Kragujevac, Serbia, to welcome students arriving by bicycle, an event taking place shortly before the country's October 25 election. The student cycling procession drew widespread attention, with reports noting the warm reception in the central Serbian city as political campaigning intensifies nationwide.
- 3Stanford and Nvidia release CLM-8B agent model▼Stanford and Nvidia's open CLM-8B caches reusable agent actions and runs up to 9x faster than Jev in tests
Stanford University and Nvidia have open-sourced CLM-8B, an AI model built for software agents that caches reusable actions instead of recomputing them. In tests the model ran up to nine times faster than Jev, a comparable agent system. The open release is drawing attention for offering large speed gains on agentic workloads, an area where inference cost is a major bottleneck for developers.
- 4
Jev Plays Pokémon Red is a project shared on Hacker News under the 'Show HN' format, where makers present their own work. Based on the link, it appears to be a web-based experiment centered on playing the classic Game Boy game Pokémon Red, though the posts collected do not include comments explaining exactly how it works or what the creator built. Readers on Hacker News often respond to these nostalgia-driven technical projects with curiosity about the implementation.
Repos
- Contrastive-LM/CLM
- jev-chat/jev-chat-jarvis 装在手机上的对话副驾:在 QQ / X / 飞书里读懂对方、给出候选回复、一键填入输入框,发不发由你。非侵入,只读屏幕,不 hook 不改包。
- nokia-applied-research/AnyJev Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating, welc
- anishfn/shapeshift An input that becomes what you mean: one text box that morphs into the right UI as you type. Powered by TypeSafe Jev, wo
- jaredpalmer/kev Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own
- v-modal/awesome-jev-tools A curated list of tools built for Jev — TypeSafe AI's System One model for typed decisions.
- browser-use/jev-ultrafast Fastest and cheapest web agent
- bespokelabsai/nimble Local typed decisions, contrastive data curation, and model evaluation.
- heyjunpenn/awesome-jev A verified, community-maintained catalog of 916 open-source projects built with Jev.
- yibie/awesome-jev A curated list of public projects, integrations, and discussions built on Jev — TypeSafe AI's System One model for
- kerpopule/hermes-jev-skills Jev-powered model routing, memory, compaction, skill selection, computer and browser use for Hermes agents (also Claude
- TianyuCodings/NanoJev A nano replica of Jev: parallel decisions, dynamic candidates, and an end-to-end training pipeline.
- TheoLeeCJ/SemIf-OpenJev Semantic ifs from open models, on a 3090 at home. Independent; not affiliated with Jev or TypeSafe.
- wfzyx/von The open-source System One decision model. Sub-15ms, non-autoregressive, local drop-in alternative to TypeSafe Jev.
- kyle-pena-nlp/jevchat Turns Jev into a chatbot
- Avinash-jetwani/jevmem Automatic project memory for Claude Code. Also works with Cursor and Codex.
- awlevin/typesafe-computer-use Computer use for about $0.0002 a step: OCR the screen, classify the next action with TypeSafe, click. macOS.
- Parcha-ai/agentrun The Agentrun Workflow DSL
- egma-ai/jev-code-reviewer Review behavior, not just diffs. Jev prioritizes human attention; OpenAI explains the changes. Local CLI + agent skill +
- tamaratran/fast-jev-compaction Claude Code plugin that replaces the compaction summary with Jev decisions: every tool call and result is scored in one