A self-hosted AI workspace · 3.4.1
3.4.1 is available. Released on main.
What changed in 3.4.1 ·
Get v3.4.1.
Your model. Your memory. Your machine.
Research the web, write and run code, and schedule recurring work from one browser workspace. Keep project context and reusable memory across sessions, delegate tasks to workers, and see what ran. Local models, cloud APIs, or both.
$ git clone --branch main https://github.com/calvincs/Pernix.git && cd Pernix $ python3 -m venv .venv && . .venv/bin/activate $ pip install -r requirements.txt && python run.py
Bring your own model. Runs commands on its host; use a dedicated VM or container. Setup & safety.
What it does
01Light coding
Small fixes and scripts, tested as it goes. Not built for large projects.
file_read·file_edit·bash02Research
Reads sources and saves a report with links.
search_web·browse_web·file_write03Schedules
Runs a prompt on a timer and notifies you.
schedule_job·0 7 * * 1-504Memory
Saves what it learns as Markdown you can edit.
remember·recall·data/memories/05Skills
Markdown how-tos. It proposes fixes you can review and undo.
data/skills/<name>/SKILL.md06Helpers & tools
Parallel helper agents, MCP servers, a browser, a REST API.
spawn_worker·await_workers·mcp_add_server
Get started
- 01
Use a VM, container or spare machine with Python 3.11+.
- 02
Pick a model: Ollama, OpenRouter, OpenAI or any compatible server.
- 03
Run the commands, open
localhost:8090, then Settings → Providers & models.
$ git clone https://github.com/calvincs/Pernix.git $ cd Pernix $ python3 -m venv .venv && source .venv/bin/activate $ pip install -r requirements.txt $ python run.py Pernix → http://127.0.0.1:8090
Fork it. Read it. Make it yours.
Pernix is a working tool, built for daily use and shared openly — use it, learn from it, build on it.