pickfit

BrowseMCP servers

ollaya-dev/ollaya

Local Jev-compatible API server that pulls and serves open decision models for typed, calibrated answers in milliseconds.

Tested on Linux

Use it

Linux x86_64

You need first

  • Runtimes: docker
  1. Download install script from ollaya.dev

    curl -fsSL https://ollaya.dev/install.sh -o /tmp/install.sh
  2. Run install script to install ollaya to ~/.local

    bash /tmp/install.sh

Check that it works

ollaya --version 2>&1; ollaya -v 2>&1
ollaya help 2>&1

The output should contain “Run open decision models locally”.

First thing to try

ollaya serve
curl -s http://127.0.0.1:11435/api/tags 2>&1; echo "---"; curl -s http://127.0.0.1:11435/api/ps 2>&1; echo "---"; curl -s http://127.0.0.1:11435/v1/models 2>&1

Add it to your agent

claude mcp add ollaya -- ollaya mcp
JSON for Claude Desktop, Cursor and other clients
{
  "mcpServers": {
    "ollaya": {
      "command": "ollaya",
      "args": [
        "mcp"
      ]
    }
  }
}

What it does

  • Expose models to AI agents via MCP server
    Tested
  • Pull and serve open decision models locally via CLI and daemon
    Not shown working
  • Serve TypeSafe Jev-compatible API at /v1/systemone
    Not tested
  • Return calibrated probabilities for typed decisions without generating text
    Not tested

How far pickfit got

Linux x86_64

  1. Installs
  2. Connects
  3. 1 of 4 features work
  4. Works offline

Windows: the project says it runs there; pickfit hasn’t tried it.

Good for

  • serve open decision models locally behind a Jev-compatible API

An alternative to TypeSafe Jev and Ollama.

How pickfit tested it

Each run starts from a clean machine and follows the steps above. How pickfit verifies

Linux x86_64

An MCP client called one of its tools

  • Replayed from scratch
  • Works offline
  • Checked on 2 Nov 2026
  • Version 0.18.0

An MCP client handshake over stdio listed 4 tools, and a call to list_models returned a result.

Differences the test machine hit

  • README: curl -fsSL https://ollaya.dev/install.sh | sh
    In the test: Download script first to /tmp/install.sh, read it, then run bash /tmp/install.sh; install auto-falls back to ~/.local without root

How to read a tool card

Stitching
pickfit installed this tool itself. Everything under the stitches comes from that run. A tool pickfit has not run never gets stitches.
Verified on your OS
The install steps ran on the system you chose. “Ran on Linux only” means it has not been run on yours yet.
macOS, Linux and WindowsWhere it ran
Green OS marks: pickfit ran the install steps there. Grey ones: the README says it runs there, and pickfit has not tried.
How far the run got
Installs and starts, its main function works, its service answers, it produces model output. A window means a desktop app opened; a plug, an MCP client used it. The mark sits beside the run’s result, under “Why it fits and how we know” and in “How pickfit tested it”.
Visual check
pickfit looked at screenshots of the app. Green: it looks right. Amber with a number: things that look wrong; open it to see them. Grey and dashed: not checked yet.
Known vulnerabilities
Known high or critical vulnerabilities (OSV.dev) in what it installs. Green: none known. Red with a number: how many; open it for the list, and read it before you install. Grey and dashed: not checked, which does not mean safe.
About the run
The day it ran, and the version that ran.
Source of a reason
Every reason a pick fits rests on one profile field. Open the reason to see the field and the value it relies on.
Hidden gem
High quality, little known.
Quality and popularity
Two scores out of 100. Quality: how well it installed and worked when pickfit tried it, and how good its install docs and upkeep are. Popularity: from stars, downloads and Hacker News.
Features checked
Of the main features the README advertises, how many the run actually exercised (green), and how many failed (red). Grey ones were not checked, and the card says why.
Not verified
A well-known tool Fitz mentions from general knowledge. No run record, no steps, no score.