AI UP LAB面向任务的 AI 实践资源AI resources for real tasks
收藏Saved
更多More
StarStar
ollaya-dev ollaya-dev 官方 Official 社区 showcase Community showcase + 精选 + Featured

Ollaya：本机跑开源决策模型（Jev / Laya 相邻） Ollaya: run open decision models locally (Jev / Laya-adjacent)

Ollaya: run open decision models locally (Jev / Laya-adjacent)

HN 首页 https://ollaya.dev/ — 作者定位「像 Ollama 跑 LLM 一样，本机跑开源决策模型」。拉 Laya / decider / NLI / GLiClass 等开源权重，本地 daemon 提供 TypeSafe 兼容的 /v1/systemone；官方称可改 TYPESAFE_BASE_URL 指向本机，现有 Jev 客户端不用改代码。延迟对比数字（如 Laya 8–10ms、Jev hosted 236–276ms）一律标官网自述 / 第三方基准，本库未复跑。 the site says existing Jev clients work by pointing TYPESAFE_BASE_URL at localhost. Latency comparisons (e.g. Laya 8–10ms, Jev hosted 236–276ms) are site or third-party claims — not re-run here. not a separate card.

Playwright 实拍 ollaya.dev 首屏，裁 3:2 Playwright capture of ollaya.dev above the fold, cropped to 3:2

来源Sources

官方模型页 Official model page Ollaya 官网 Ollaya homepage ollaya-dev 2026年9月25日 Sep 25, 2026 https://ollaya.dev/ 官方模型页 Official model page GitHub：ollaya-dev/ollaya（Apache-2.0） GitHub: ollaya-dev/ollaya (Apache-2.0) ollaya-dev https://github.com/ollaya-dev/ollaya 产品主页 Product home Ollaya 模型目录 /search Ollaya model catalog /search ollaya-dev https://ollaya.dev/search 社区 showcase Community showcase Hacker News：Ollaya – Ollama for open-source, Jev-style decision models Hacker News: Ollaya – Ollama for open-source, Jev-style decision models Hacker News 2026年9月25日 Sep 25, 2026 https://news.ycombinator.com/item?id=49848269

为什么推荐Why we recommend it 边界：速度 / 对照数字是官网与第三方基准自述，本库未复跑；未实测 MCP / 桌面端。第三方 Ollaya Web UI 无 license，不另开卡。 Boundary: speed / comparison figures are site or third-party claims, not re-run here; MCP / desktop app not tested. Third-party Ollaya Web UI has no license — no separate card.

核验记录：来源、抓取与截图说明Verification log: sources, checks, and captures

收录理由：HN 首页热帖（核对 483pts），把站内已收的 Jev / Laya 补上「本机 Ollama 式」运行时，可直接试。预览为 Playwright 实拍官网首屏裁 3:2。 （item 49848269，2026-09-25 ~18:33Z，Algolia 核对 483pts） （item 49855683） 仓库 ollaya-dev/ollaya 于 2026-09-26 gh api：Apache-2.0、296★。 官网与仓库均 HTTP 200。 另有当日 Show HN Ollaya Web UI 为第三方 Web UI，无 license、1★，不单独开卡。Why: HN front-page post (483pts at check time) that adds a local Ollama-style runtime next to catalogued Jev / Laya — tryable. Preview is a Playwright capture of the homepage above the fold, cropped to 3:2. (2026-09-25 ~18:33Z, 483pts on Algolia at check time) (item 49855683) HN front-page item 49848269 at https://ollaya.dev/ — pitched as “Ollama for open decision models.” It pulls open weights such as Laya / decider / NLI / GLiClass and serves a local TypeSafe-compatible /v1/systemone daemon; Repo ollaya-dev/ollaya on the 2026-09-26 gh api: Apache-2.0, 296★. Site and repo both HTTP 200. Same-day Show HN Ollaya Web UI is a third-party UI with no license and 1★;

要点（官方称 / 社区称）Highlights (vendor / community claims)

  • 作者称：本机 pull / serve 开源决策模型，单次前向返回校准概率，不生成文本；CLI 命令风格对齐 Ollama（serve / run / pull / list）。 Author claim: pull and serve open decision models locally; one forward pass returns calibrated probabilities, no text generation; CLI mirrors Ollama (serve / run / pull / list).
  • 作者称：提供 TypeSafe 兼容的 /v1/systemone；把 TYPESAFE_BASE_URL 指到 http://localhost:11435 即可用官方 SDK 打本机。 Author claim: speaks TypeSafe’s /v1/systemone; point TYPESAFE_BASE_URL at http://localhost:11435 and the official SDK talks to the local server.
  • 官网延迟表自述：RTX 4090 上五问请求，Laya 约 8–10ms；对照栏写 TypeSafe Jev hosted API 中位 236–276ms（含网络，来自第三方基准页）。本库未复跑。 Site latency table claim: five-question request on an RTX 4090, Laya about 8–10ms; comparison cell lists TypeSafe Jev hosted API median 236–276ms (includes network, from third-party benchmarks). Not re-run here.
  • 仓库 Apache-2.0；权重仍从各作者 Hugging Face 仓按 commit + sha256 拉取，Ollaya 自称不重托管。桌面端 / CLI / Docker 均有，详见官网 Platforms。 Repo is Apache-2.0; weights are pulled from each author’s Hugging Face repo pinned by commit + sha256 — Ollaya says it does not re-host them. Desktop / CLI / Docker are listed on the site Platforms table.

同板相关Related on this board

同一看板上互相关联的卡：社区 demo 指回它跑的模型，模型指向值得看的 demo。Cards linked on this board: a community demo points back to the model it ran on; the model points to demos worth a look.

Strands Agents Strands Agents 官方 Official 社区 showcase Community showcase

Strands Decider 2B：一个小的开源决策模型，只做选择题和打分 Strands Decider 2B: a small open decision model that picks an option or gives a score

Strands Decider 2B: a small open decision model that picks an option or gives a score

Strands Decider 2B 是 Strands Agents 放出的一个小决策模型。它不写文章。你给它一段现状和几个允许的答案，它为每个答案打一个概率，也可以按一个分数尺打分。仓库写它大约 19 亿参数，基于 Qwen3.5-2B 改来，拿掉了原来用来生成文字的那一层，换上一个大约一百万参数的小头。代码和权重以 Apache-2.0 发布，可以在自己的 CPU 或显卡上跑。官博是 2026-10-01，仓库现在指向的参考版本是 v21，更早的 v19 仍在。本库没有安装，也没有复跑仓库里的分数。 Strands Decider 2B is a small decision model from Strands Agents. It does not write prose. You give it a situation and the answers you allow, and it returns a probability for each one, or a score on a scale. The repo says it has about 1.9 billion parameters, starts from Qwen3.5-2B, removes the layer that used to generate text, and adds a small head of about a million parameters. Code and weights are Apache-2.0, and it can run on your own CPU or GPU. The blog is dated 2026-10-01. The repo’s reference version now is v21, and the earlier v19 is still published. This library did not install it and did not re-run the repo’s scores.

厂商公告Vendor announcement 2026年10月1日 Oct 1, 2026 4 官方 · 1 社区 4 official · 1 community
kouhxp kouhxp 官方 Official 社区 showcase Community showcase

Gutsy：本机 CPU 可跑的 0.8B Jev 兼容决策模型 Gutsy: 0.8B Jev-compatible decision model for local CPU

Gutsy: 0.8B Jev-compatible decision model for local CPU

kouhxp 开源的 gutsy-0.8b（v0.4）：把 Qwen3.5-0.8B 微调成决策模型，不生成自由文本。你送一段状态（文本或 JSON）和 typed questions（yes/no、choice、score），它为每个选项返回校准概率；choice / score 还带 reject。运行时 gutsy-inference 走 llama.cpp，默认可在普通 CPU 上起本地 HTTP；接口刻意对齐 Jev / System One（`/v1/systemone` 等），现有客户端多半只换 base URL。权重在 Hugging Face kouhxp/gutsy（Q8_0 与 Q4_K_M GGUF），代码与权重 README 写 Apache-2.0。JevBench / 评测表与延迟是作者自测，本库未复跑。同板与 Jev、Laya、Clef、Jeeves、Ollaya 相邻；Cases 已有本机 Jeff 与 Onesie CLI。 kouhxp’s open gutsy-0.8b (v0.4) fine-tunes Qwen3.5-0.8B into a decision model that does not generate free text. You send a state (text or JSON) plus typed questions (yes/no, choice, score) and get a calibrated probability for every option; choice / score answers also carry reject. The gutsy-inference runtime uses llama.cpp and can serve a local HTTP API on an ordinary CPU. The API deliberately matches Jev / System One (`/v1/systemone` and related), so many existing clients only need a new base URL. Weights live on Hugging Face kouhxp/gutsy (Q8_0 and Q4_K_M GGUF); README says Apache-2.0 for code and weights. JevBench / eval tables and latency are author self-tests, not re-run here. On this board it sits next to Jev, Laya, Clef, Jeeves, and Ollaya; Cases already lists local Jeff and the Onesie CLI.

厂商公告Vendor announcement 2026年10月1日 Oct 1, 2026 2 官方 · 1 社区 2 official · 1 community
TypeSafe AI TypeSafe AI 官方 Official 社区 showcase Community showcase + 精选 + Featured

Jev / System One Models（TypeSafe AI） Jev / System One Models (TypeSafe AI)

Jev / System One Models (TypeSafe AI)

TypeSafe AI 于 2026-09-15 发布的首个公开 System One Model。面向软件内决策而非聊天：输入非结构化状态，输出类型安全的结构化决策，并附带校准概率与置信度。官方称新架构 + 并行采样 + Reinforcement Learning for Calibrated Decisions（RLCD）；目前为早期访问；速度、价格与评测倍率均为厂商自述，本库未复跑其工作流评测。 TypeSafe AI’s first public System One Model, announced 2026-09-15. Built for in-software decisions rather than chat: unstructured state in, type-safe structured decisions out with calibrated probabilities and confidence. Vendor claims a new architecture, parallel sampling, and Reinforcement Learning for Calibrated Decisions (RLCD); currently early access; speed, pricing, and eval multipliers are all vendor claims, and the workflow evals were not re-run by this library.

厂商公告Vendor announcement 2026年9月15日 Sep 15, 2026 2 官方 · 1 社区 2 official · 1 community
ConvAI Innovations ConvAI Innovations 官方 Official 社区 showcase Community showcase

Laya：开源 System 1 决策引擎（对照 Jev） Laya: open-source System 1 decision engine (Jev-adjacent)

Laya: open-source System 1 decision engine (Jev-adjacent)

作者称 Laya 是非自回归、亚 35ms 的开源 System 1 决策模型族（Apache 2.0 权重），提供 choice / score / noul 三类结构化决策与多语路由；对照站内已收录的 TypeSafe Jev。基准、延迟、与 Jev 对比数字一律标「作者称 / 第三方整理」，本库未复跑。HN 讨论：https://news.ycombinator.com/item?id=49765348（2026-09-19）。 Author presents Laya as an open-weight non-autoregressive System 1 decision family (Apache 2.0) with choice/score/noul primitives and multilingual routing; sits next to catalogued TypeSafe Jev. Latency/benchmark/Jev-comparison figures are author or third-party claims — not re-run here.

厂商公告Vendor announcement 2026年9月19日 Sep 19, 2026 1 官方 · 2 社区 1 official · 2 community
PostHog PostHog 官方 Official 社区 showcase Community showcase + 精选 + Featured

Jeeves：带推理的开源 Jev 风格决策模型（PostHog） Jeeves: open Jev-style decision model with reasoning (PostHog)

Jeeves: open Jev-style decision model with reasoning (PostHog)

HN https://github.com/PostHog/jeeves — MIT：PostHog 开源的「会先想再决定」的 Jev 风格分类器。README：基于 Qwen3.5-9B（LoRA + pointer head），SFT + CISPO 训练，带 block-4 diffusion drafter；同一请求支持 noul / choice / score，API 与 Jev 同形（`/v1/systemone`）。作者表（thinking、greedy、2560-token 上限；Kev-9B / Jev 列为 Kev 公布数字）：Test overall 0.889 vs Kev 0.822 / Jev 0.857；JevBench overall（231 public）0.935 vs Jev 0.866；JevBench hard 0.865 vs Jev 0.730。延迟自述：无 thinking 约 0.3 s/请求，有 thinking 中位约 3.3 s（单 H100）；需 CUDA（Hopper 才用 FP8 kernel）。权重 https://huggingface.co/PostHog/jeeves。README 写 Inspired by Kev。公开仓与 HF 晚间 GET 200。本库未复跑基准、未代下权重。 README: Qwen3.5-9B with LoRA + pointer head, trained with SFT + CISPO, plus a block-4 diffusion drafter; same request supports noul / choice / score via a Jev-shaped /v1/systemone API. Author table (thinking, greedy, 2560-token cap; Kev-9B / Jev columns are Kev-published): Test overall 0.889 vs Kev 0.822 / Jev 0.857; JevBench overall (231 public) 0.935 vs Jev 0.866; JevBench hard 0.865 vs Jev 0.730. Latency claim: about 0.3 s/request without thinking, ~3.3 s median with it on one H100; needs CUDA (Hopper for the FP8 kernel). Weights at https://huggingface.co/PostHog/jeeves. README says Inspired by Kev. Public repo and HF evening GET 200. Benchmarks not re-run here; weights not downloaded for you.

厂商公告Vendor announcement 2026年9月29日 Sep 29, 2026 2 官方 · 1 社区 2 official · 1 community
Cloudflare Cloudflare 官方 Official 社区 showcase Community showcase

Clef：Cloudflare 开源决策模型（含 Clef-Flash） Clef: Cloudflare open-weight decision models (incl. Clef-Flash)

Clef: Cloudflare open-weight decision models (incl. Clef-Flash)

Cloudflare 发布开源决策模型 Clef，以及更小的 Clef-Flash。它们不生成自由文本：读入一段状态和一组带类型的问题，为每个允许的答案返回概率。Workers AI 上的模型 id 是 @cf/cloudflare/clef（27B）和 @cf/cloudflare/clef-flash（9B）。官方称接口与 Jev / System One 同形，问题类型仍是 noul / choice / score，并带视觉编码器，状态可以是文本、JSON、图像或视频。权重在 Hugging Face，许可 Apache-2.0。HF 卡写 Clef 由 Qwen/Qwen3.8-27B 后训练、Clef-Flash 由 Qwen/Qwen3.5-9B 后训练，这是厂商 / HF 口径。官博还宣布 RL 微调：先由 forward-deployed engineer 动手，之后再做成自助平台——按路线图记，不是已经核过的产品深度。Decision Index、延迟和工作流分数一律是厂商自述，本库未复跑。同板与 Jev、Laya、Jeeves、Ollaya 相邻；Cases 里已有本机 Jeff 和命令行 Onesie。 Cloudflare released the open-weight decision model Clef and the smaller Clef-Flash. They do not generate free text: they read a state plus typed questions and return a probability for every allowed answer. On Workers AI the ids are @cf/cloudflare/clef (27B) and @cf/cloudflare/clef-flash (9B). The vendor says the API matches Jev / System One, with noul / choice / score questions and a vision encoder, so state can be text, JSON, images, or video. Weights are on Hugging Face under Apache-2.0. The HF cards say Clef is post-trained from Qwen/Qwen3.8-27B and Clef-Flash from Qwen/Qwen3.5-9B — a vendor / HF claim. The blog also announces RL fine-tuning: hands-on with a forward-deployed engineer first, then a later self-serve platform. That is a roadmap, not a product depth this library verified. Decision Index, latency, and workflow scores are vendor claims and were not re-run here. On this board it sits next to Jev, Laya, Jeeves, and Ollaya; Cases already lists local Jeff and the Onesie CLI.

厂商公告Vendor announcement 2026年10月1日 Oct 1, 2026 4 官方 · 1 社区 4 official · 1 community