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+
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__)"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>&1The 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>&1Ask a first question with python3 TenSeiAi.pyz ask "<your question>" --offline.
Linux x86_64
You need first
- Runtimes:
Python 3.12+
Install numpy dependency via pip --user
python3 -m pip install --user numpy && python3 -c "import numpy; print(numpy.__version__)"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 --helpThe 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?" --offlineAsk a first question with python3 TenSeiAi.pyz ask "<your question>" --offline.
What it does
- Answer questions offline on your CPUTested
How to use it
- Run
python3 TenSeiAi.pyz ask "<your question>" --offline. - Read the answer printed in the terminal.
- Run
- Run a local OpenAI-compatible APITested
How to use it
- Start the server with
python3 TenSeiAi.pyz serve --port <port>. - 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>"}]}'. - Read the reply in the JSON response under choices, message, content.
- Start the server with
- Chat in the terminal or a web consoleNot shown working
- Pull in live web research when askedNot tested
How far pickfit got
macOS arm64
- Installs
- Starts
- 1 of 4 features work
- Works offline
Linux x86_64
- Installs
- Starts
- 2 of 4 features work
- Works offline
Other systems
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'