pickfit

BrowseLocal AI tools

TenSeiAi

Mixture-of-Experts language model and offline AI engine in pure Python and NumPy.

Tested on macOS and Linux

Use it

macOS arm64

You need first

  • Runtimes: Python 3.12+
  1. install numpy dependency with --break-system-packages for Homebrew Python 3.15

    python3 -m pip install --user --break-system-packages numpy 2>&1 | tail -n 20; python3 -c "import numpy; print(numpy.__version__)"
  2. download TenSeiAi.pyz 81 MB release artifact

    curl -fL -o TenSeiAi.pyz "https://github.com/Koustubh12345/TenSeiAi/releases/latest/download/TenSeiAi.pyz" 2>&1 | tail -n 20; ls -lh TenSeiAi.pyz; python3 --version

Check that it works

python3 TenSeiAi.pyz ask "What is the difference between a process and a thread?" --offline 2>&1

The output should contain “A **process** is an independent executing program”.

First thing to try

python3 TenSeiAi.pyz ask "What is the difference between a process and a thread?" --offline 2>&1

Ask a first question with python3 TenSeiAi.pyz ask "<your question>" --offline.

Linux x86_64

You need first

  • Runtimes: Python 3.12+
  1. Install numpy dependency via pip --user

    python3 -m pip install --user numpy && python3 -c "import numpy; print(numpy.__version__)"
  2. Download TenSeiAi.pyz release binary

    curl -fL -o TenSeiAi.pyz "https://github.com/Koustubh12345/TenSeiAi/releases/latest/download/TenSeiAi.pyz" && python3 -c "import numpy; print(numpy.__version__)"

Check that it works

python3 TenSeiAi.pyz --help

The output should contain “ask ask one question”.

First thing to try

python3 TenSeiAi.pyz ask "What is the difference between a process and a thread?" --offline

Ask a first question with python3 TenSeiAi.pyz ask "<your question>" --offline.

What it does

  • Answer questions offline on your CPU
    How to use it
    1. Run python3 TenSeiAi.pyz ask "<your question>" --offline.
    2. Read the answer printed in the terminal.
    Tested
  • Run a local OpenAI-compatible API
    How to use it
    1. Start the server with python3 TenSeiAi.pyz serve --port <port>.
    2. Send a chat request with curl -s http://127.0.0.1:<port>/v1/chat/completions -H "Content-Type: application/json" -d '{"model": "tensei-1", "messages": [{"role": "user", "content": "<your text>"}]}'.
    3. Read the reply in the JSON response under choices, message, content.
    Tested
  • Chat in the terminal or a web console
    Not shown working
  • Pull in live web research when asked
    Not tested

How far pickfit got

macOS arm64

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

Linux x86_64

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

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

Good for

  • answer questions offline on CPU
  • solve mathematics and logic tasks
  • synthesize code and algorithms

How pickfit tested it

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

macOS arm64

Its main function works

  • Replayed from scratch
  • Works offline
  • Checked on 1 Nov 2026
  • Version v1

Differences the test machine hit

  • README: python3 -m pip install --user numpy
    In the test: python3 -m pip install --user --break-system-packages numpy required on Homebrew Python due to PEP 668
  • README: curl download then python3 TenSeiAi.pyz serve --port 8765
    In the test: serve binds to 127.0.0.1:8765 and exposes OpenAI-compatible /v1/chat/completions and /v1/models

Linux x86_64

It produces model output

  • Replayed from scratch
  • Works offline
  • Checked on 30 Oct 2026
  • Version v1

Differences the test machine hit

  • README: derived candidates uv tool install numpy / pipx install numpy
    In the test: python3 -m pip install --user numpy so numpy is importable by python3; uv tool / pipx isolated envs leave ModuleNotFoundError: No module named 'numpy'

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.