AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
LLM Infra/
ollaya
ollaya logo

ollaya

Active·★ 1.5k·Apache-2.0·Updated 2026-11-21

Ollaya serves a specific kind of model: decision models that read a state, such as a message, ticket or any JSON, plus typed questions (choice, score or yes/no) and return calibrated probabilities in a single forward pass. They never generate text, so answers come back in milliseconds. A support message can be scored for intent, urgency, frustration, refund request and churn risk in one call.

The workflow mirrors Ollama: ollaya serve runs a daemon, and run, pull, list, ps, show, rm, cp, stop and create behave as you would expect. Its /v1/systemone, /v1/decisions and /v1/models endpoints are wire-identical to TypeSafe's hosted Jev API, so the TypeSafe SDK and existing Jev clients work by changing the base URL. Ollaya publishes only small ONNX graphs; weights load from each author's Hugging Face repository, pinned to a commit and checked by sha256, and GGUF models run on llama.cpp.

For agents, ollaya mcp exposes the models to Claude Code, Cursor and other MCP clients, and a skill teaches agents when to use them. The README's recommended model is a 4B-class model that wants an NVIDIA GPU; on CPU the smaller laya router models are the suggested start.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-11-15.

License
Apache-2.0
Latest release
v0.18.0 · 2026-10-25
Last commit
2026-11-10
Contributors
16
Forks
92
Open issues and PRs
15
First published
2026-09-23

Source: GitHub, npm and PyPI public APIs.

#decision-models#self-hosted#onnx#llama-cpp#mcp#classification#api-server
$ Install
$ curl -fsSL https://ollaya.dev/install.sh | sh
↗ Visit site★ GitHub
01

Features

01Ollama-style CLI: serve, run, pull, list, ps, show, rm, cp, stop and create
02Wire-compatible with TypeSafe's Jev API, so the official SDK works by changing the base URL
03Weights load from each author's Hugging Face repo, pinned to a commit and sha256-verified
04ollaya mcp serves the models to Claude Code, Cursor and other MCP clients
05Modelfiles bake a question set into a custom model
02

Why choose it

+Classification-style decisions in milliseconds without generating text, with calibrated probabilities.
+Drop-in local replacement for TypeSafe's Jev API: point the SDK at Ollaya and pick an open model.
+Weights come straight from their authors, commit-pinned and sha256-verified, never re-hosted.
03

Trade-offs

!A niche tool: useful only if you need typed decisions, not text generation.
!The recommended model wants an NVIDIA GPU; CPU-only setups fall back to smaller models.
!Closely tied to the TypeSafe/Jev ecosystem and its wire format.
04

Maintenance check

ActiveChecked: 2026-11-10
Last commit
2026-11-06
Commits, last 90 days
100+
Releases, last 90 days
27
Latest release
v0.18.0 (2026-10-25)
Open issues
11
Recent issues with at least one comment
1/3
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 0, 0, 0, 0, 125, 58, 40, 18, 80, 10, 8, 0

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

Most discussed open issues

  • #80 Decima 2.3: decima-guard (new), decima-agent 2.3, and the choice-window fix you found9 comments · 2026-10-18
  • #79 Support Drex (nace-ai/drex-v2.0): Qwen3.6-35B-A3B MoE with a Kev pointer head, GGUF2 comments · 2026-10-17
  • #165 Support hs-decide-1-flash1 comments · 2026-11-04
  • #170 Feature Request: Gate model pulls0 comments · 2026-11-10
  • #168 please support adding remote open ai compatible endpoint0 comments · 2026-11-09

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

05

Compatibility

Linux / macOS
Daemon + CLI
Verified via docs
NVIDIA GPU
CUDA
Verified via docs
Claude Code
MCP
Verified via docs
Cursor
MCP
Verified via docs
06

Quick start

1
$ curl -fsSL https://ollaya.dev/install.sh | sh
07

Use cases

↳Triaging support tickets by intent, urgency and churn risk locally
↳Replacing a hosted Jev endpoint with self-hosted open models
↳Giving agents fast yes/no or multiple-choice judgments without text generation
08

Alternatives

⚡Top VS:
VStuui★1.2k→VSboxlite★2.7k→VSODS★7.9k→VSaskimo★552→
tuui logo
tuui★ 1.2k
A desktop MCP client designed as a tool unitary utility integration, accelerating AI adoption through the Model Context Protocol (MCP) and enabling cross-vendor LLM API orchestration.
VSCompare→
boxlite logo
boxlite★ 2.7k
The micro-VM for AI agents — light enough to embed on your laptop, elastic enough to power an agentic cloud.
VSCompare→
ODS logo
ODS★ 7.9k
ODS V3 Pre-Release: Public testing and refinement ahead of the official V3 launch. Turn your PC, Mac, or Linux box into a private AI server.
VSCompare→
askimo logo
askimo★ 552
AI desktop app for chat, RAG, Skills, MCP tools, and agents. Support multiple LLMs (Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM, Gemini, OpenRouter)
VSCompare→
blockbench-mcp-plugin logo
blockbench-mcp-plugin★ 635
Adds MCP server to Blockbench
agenta logo
agenta★ 4.9k
Agenta is a workspace where you and your team build agents and automations.
VSCompare→
MCPJungle logo
MCPJungle★ 1.6k
Self-hosted MCP Gateway and Registry for AI agents
VSCompare→
nanoMuse logo
nanoMuse★ 3.6k
nanoMuse: an open-source personal agent for every device you own. One agent with a name and a look of its own that does things, keeps working while the app is closed, remembers you, and asks before anything you cannot undo. On Android, iPhone and iPad, Windows / macOS / Linux and in the browser; your phone's screen and your computer as its hands.
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Maintenance check05Compatibility06Quick start07Use cases08Alternatives
ollaya-dev /
ollaya
↗

Ollama for decision models: pull open classifiers by name and serve them locally behind a Jev-compatible API

1.5k92Apache-2.0
Last commit1d ago
StatusActive
CategoryLLM Infra
Contributors16
Latest releasev0.18.0
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.