ollaya
by ollaya-dev
Jev-compatible API server for open decision models. Ollama for decision models: pull and serve 25 model families (Laya, pplx-decider, Clef, Winnow, coba...) locally or self-hosted behind /v1/systemone. The TypeSafe SDK works unchanged: set its base URL and pick an open model. CLI, desktop app, Docker, MCP server, public bench.
1,388stars
84forks
Rust
Added 10/24/2026
30 days in the Featured rail · terms & refunds
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
MCP Serverscalibrationdecision-modeldecision-modelsinference-serverjevjev-alternativejev-compatiblelayallama-cpplocal-inferencemcp-servermodel-servingollamaonnxruntimerustself-hostedsystem-onesystemonetyped-decisionstypesafe
Maintainer of this skill?
Automated security scan — not a certification.
Installation
# Add to your Claude Code skills
git clone https://github.com/ollaya-dev/ollayaGetting Started
Guides for using mcp servers skills like ollaya.
- Best MCP Servers in 2026Category-by-category picks: databases, dev tools, productivity, browser automation.
- What is an AI Skills Marketplace?Definitions, how marketplaces work, and how to choose between them in 2026.
- Getting Started with AI SkillsFirst-time install walkthrough for Claude Code, Codex CLI, and ChatGPT.
Security ReportVerified
Last scanned: 10/24/2026
{
"issues": [
{
"file": ".claude/skills/checklist-design/SKILL.md",
"line": 37,
"type": "prompt-injection",
"message": "Possible instruction-override phrase: \"ignore your previous instructions\"",
"severity": "medium"
},
{
"file": "README.md",
"line": 33,
"type": "remote-install",
"message": "Install command (remote install script piped to a shell — review the source before running): \"curl -fsSL https://ollaya.dev/install.sh | sh\"",
"severity": "low"
},
{
"file": "skills/ollaya-decisions/SKILL.md",
"line": 54,
"type": "remote-install",
"message": "Install command (remote install script piped to a shell — review the source before running): \"curl -fsSL https://ollaya.dev/install.sh | sh\"",
"severity": "medium"
}
],
"status": "PASSED",
"scannedAt": "2026-10-24T08:40:20.874Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}Compare with similar skills
See how ollaya compares with popular alternatives.
A decision model reads a state (a message, an email, a ticket, any JSON) plus typed questions
(choice, score, noul) and returns calibrated probabilities in a single forward pass, in
milliseconds. It never generates text. Ollaya pulls these models by name and serves them from a
local daemon behind a self-hosted, Jev-compatible API (TypeSafe's /v1/systemone wire format),
so the TypeSafe SDK and existing Jev clients work unchanged once they point at Ollaya and name an
open model.
curl -fsSL https://ollaya.dev/install.sh | sh
ollaya run winnow:e4b --preset triage "Third time this year you've double-charged me. Refund it today or I'm cancelling and moving to a competitor."
intent refund ███████████████░ 0.91
is_urgent yes ███████████████░ 0.92
frustration 2.89 / 3 very angry or using stron… ██████████████░░ 0.86
refund_requested yes ████████████████ 0.99
churn_risk yes ████████████████ 0.99
Or ask your own questions: ollaya run kev --ask "Is a refund requested?" --ask "Which team?" --choice billing --choice sales < ticket.txt.
winnow:e4b is the recommended model: 0.724 accuracy on typed decisions (TypeSafe reports 0.738 for its Jev) and 113 ms for five questions on an RTX 5090. It is a 4B-class language model, so without an NVIDIA GPU start with laya: laya:multilingual answers five questions in 516 ms on a CPU. All models and their numbers: ollaya.dev/search.
A self-hosted, Jev-compatible API
What is a Jev-compatible API? An HTTP API that takes the same requests as TypeSafe's hosted
Jev (a state plus typed questions at POST /v1/systemone) and returns the same answers, so
TypeSafe's SDK and any client written for Jev work against it unchanged. Ollaya's /v1/systemone,
/v1/decisions and /v1/models are wire-identical to TypeSafe's (as typesafe-sdk 0.7.1 defines
them), served from your own machine with open models.
Migrating from Jev. Point the SDK at Ollaya and pick an open model:
export TYPESAFE_BASE_URL=http://localhost:11435
export TYPESAFE_API_KEY=local # any non-empty value
export TYPESAFE_DEFAULT_MODEL=winnow:e4b # instead of "jev-latest"
Details, including proxies and warm-up: TypeSafe compatibility.
| Ollaya | TypeSafe Jev | Ollama | |
|---|---|---|---|
| Runs on | Your machine or server | TypeSafe's cloud | Your machine or server |
| Jev API | /v1/systemone, /v1/decisions, /v1/models |
The original | /v1/systemone |
| Models | Open decision models from Perplexity, Cloudflare, PostHog, Bespoke Labs and others | Jev (closed) | Its own GGUF builds of nine decision models (0.40, October 2026) |
| Probabilities | Each author's calibration | TypeSafe's | Raw softmax |
| Your data leaves the machine | No | Yes | No |
| License | Apache-2.0 | Proprietary, hosted | MIT |
The FAQ compares Ollaya and Ollama in more detail, measured on the same GPU.
Features
- One binary.
ollaya serveruns the daemon;ollaya run,pull,list,ps,show,rm,cp,stopandcreatework the way they do in Ollama. If the daemon isn't running, the CLI starts it. - TypeSafe-compatible.
POST /v1/systemone,/v1/decisionsandGET /v1/modelsare wire-identical to TypeSafe. The official SDK works unchanged when you setTYPESAFE_BASE_URL=http://localhost:11435. - Native API.
/api/decideadds routing information and timings./api/pullstreams NDJSON progress, and there are/api/tags,/api/show,/api/psand more. See docs/api.md. - Weights come from their authors. Ollaya publishes only small ONNX graphs, about 3 MB each.
These graphs read the original weight files (usually
model.safetensors) from the author's Hugging Face repository, pinned to a commit and verified by sha256. Models whose authors publish GGUF files (winnow,jevk5,jeb) run that file itself on llama.cpp. Ollaya never re-hosts weights. - For agents.
ollaya mcpserves the models to Claude Code, Claude Desktop, Cursor and other MCP clients (claude mcp add ollaya -- ollaya mcp, or one click in Cursor), and theollaya-decisionsskill teaches agents when and how to use them (npx skills add ollaya-dev/ollaya --skill ollaya-decisions). - Routers.
layadetects the script and language of each request, then answers withlaya:enorlaya:multilingual. - Modelfiles. You can bake a question set into your own model:
Then runFROM laya QUESTIONS ./triage.json PARAMETER precision fp32ollaya create triage -f Modelfileandollaya run triage "…". - Fast and exact.
- Hardware: ONNX Runtime on CPU, and CUDA on NVIDIA GPUs. GGUF models run on llama.cpp: CPU, ROCm/HIP on AMD GPUs, Vulkan on Windows (any vendor's GPU; an integrated one when you name it), CUDA on NVIDIA GPUs, and Metal on Apple silicon.
- Precision: ONNX uses fp16 on GPU and fp32 on CPU when available; GGUF keeps its model quantization on either device.
- Accuracy: fp32 exports give the same decision as the PyTorch reference on 100% of 2,383 questions per checkpoint.
Models
| Model | What it is |
|---|---|
winnow:e4b |
Recommended. EldanRing's Winnow-E4B, a Gemma 4 fine-tune run from the author's Q8_0 GGUF on llama.cpp |
credence:e4b, credence:e4b-calibrated |
Txoka's MiCA refinements of Winnow-E4B, Q8_0: accuracy-focused and public-calibration variants; see the measured tradeoffs in the family documentation |
laya |
Router: picks laya:en or laya:multilingual by language |
laya:en |
English decision model (ModernBERT-large, 421M) |
laya:multilingual |
100+ languages (mmBERT-base, 322M) |
laya:typed-decisions |
Fine-tuned on the typed-decisions workflows |
decider, decider:4b, decider:0.8b |
Mapika's Qwen3.5 decoders, 2B (the default), 4B and 0.8B |
decider:2b-vision |
Mapika's Qwen3.5-2B vision-language decider: questions about an image (--image, images on /api/decide) as well as the state |
kev, kev:0.8b, kev:9b |
Jared Palmer's Kev: a LoRA and a pointer head on Qwen3.5 (4B by default, 0.8B, 9B), calibrated |
decision |
Decision 1.0 Eos by the vLLM Semantic Router contributors: a fine-tuned Qwen3.5-0.8B with an endpoint head, 16k-token rows |
qwen3guard |
Qwen3Guard-Gen-0.6B safety guard with built-in questions: safe, controversial or unsafe, and the category |
nli, nli:modernbert-large |
Moritz Laurer's zero-shot NLI classifiers (DeBERTa-v3-large, ModernBERT-large) |
gliclass |
Knowledgator's instruction-following zero-shot classifier (DeBERTa-v3-large) |
von |
Victor Hugo Panisa's Von 1.1 (ModernBERT-large): every option scored at its own marker, 8k-token context |
winnow |
EldanRing's Winnow-12B, the larger sibling of winnow:e4b |
clm |
Contrastive-LM's CLM-v0.1-8B: the Qwen3-8B encoder and two projection heads score options by similarity, with questions and options cached. Built for agent, game and tool-calling states |
jevk5 |
alibiserikbay's JevK5 v0.3, a Qwen3.5-4B fine-tune run from the author's Q8_0 GGUF on llama.cpp, up to 16 options |
nimble, nimble:9b-v3 |
Bespoke Labs' Nimble v2: a LoRA on Qwen3.5-9B that reads the whole request as a JSON schema and scores option codes, with the author's temperature, up to 255 options. nimble:9b-v3 is v3 (non-commercial license) as the author's Decision Index engine serves it |
strands-decider |
Strands Agents' Strands Decider: a LoRA and a pointer head on Qwen3.5-2B base, every option scored at the end of its own line, calibrated per question type; up to 255 options |
pplx-decider |
Perplexity's pplx-decider-flash v1.2: Qwen3.5-4B distilled from its 27B decision models, every question in one sequence and read at its own marker, calibrated; up to 255 options |
jeb, jeb:4b, jeb:27b |
Jason Brashear's Jebadiah (AINode): LoRAs merged into Qwen3.5 (9B by default, 4B) and Qwen3.8-27B, run from the authors' GGUF on llama.cpp with their per-type temperatures |
jeeves |
PostHog's Jeeves-9B without its reasoning chain: Qwen3.5-9B (LoRA merged) and a pointer head |
clef |
Cloudflare's Clef-Flash: Qwen3.5-9B, fully post-trained, with a joint schema head that scores every question's options in one forward pass, with no fitted temperature |
cygnet |
blockbrain-ai's Cygnet: frozen Gemma 4 12B IT (Q8_0 GGUF) with a letter-readout prompt and temperature 3.4 |
snap |
logitlab's snap1-2b: MiniCPM5-2B fine-tuned on the prompt of emnlmn's snap engine, run from the |
Frequently Asked Questions
What is ollaya?
ollaya is an open-source mcp servers skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by ollaya-dev. Jev-compatible API server for open decision models. Ollama for decision models: pull and serve 25 model families (Laya, pplx-decider, Clef, Winnow, coba...) locally or self-hosted behind /v1/systemone. The TypeSafe SDK works unchanged: set its base URL and pick an open model. CLI, desktop app, Docker, MCP server, public bench. It has 1,388 GitHub stars.
Is ollaya safe to use?
Yes. ollaya passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
How do I install ollaya?
Clone the repository with "git clone https://github.com/ollaya-dev/ollaya" and add it to your Claude Code skills directory (see the Installation section above).
What programming language is ollaya written in?
ollaya is primarily written in Rust. It is open-source under ollaya-dev on GitHub, so you can review or fork the full source.
Are there alternatives to ollaya?
Yes. SkillsLLM lists many other MCP Servers skills you can browse and compare side by side. Open the MCP Servers category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh ollaya against similar tools.
Comments (0)
to leave a comment.
No comments yet. Be the first to share your thoughts!
Related Skills
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
208,446
61,219
TypeScript
MCP Serversaiapis
A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io
148,158
9,751
Rust
AI Agentsai-toolsclaude-code
An open-source AI agent that brings the power of Gemini directly into your terminal.
107,576
14,774
TypeScript
AI Agentsaiai-agents
Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
89,383
13,725
TypeScript
AI Agentsagentai
🕷️ A Web Scraping framework that handles everything from a single request to a full-scale crawl! Don't be shy, join here: https://discord.gg/EMgGbDceNQ and follow here for daily tips and tricks: https://x.com/Scrapling_dev
89,374
9,217
Python
MCP Serversaiai-scraping
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
84,415
5,359
Rust
AI Agentsagentic-codingai-coding
Popular in MCP Servers
Top skills in this category by stars
⭐AI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts.🎯 告别信息过载，你的 AI 舆情监控助手与热点筛选工具！聚合多平台热点 + RSS 订阅，支持关键词精准筛选。AI 智能筛选新闻 + AI 翻译 + AI 分析简报直推手机，也支持接入 MCP 架构，赋能 AI 自然语言对话分析、情感洞察与趋势预测等。支持 Docker ，数据本地/云端自持。集成微信/飞书/钉钉/Telegram/邮件/ntfy/bark/slack 等渠道智能推送。
63,148
24,910
Python
MCP Serversaibark