Skip to content
PN Scripts

AI

Your AI assistant, on your own computer

PN Scripts Assistant is a free, open-source assistant that learns your projects and documents and answers from that memory. It needs no database server, no containers and no cloud account, and what it learns stays on your disk.

  • Go
  • SQLite
  • Ollama
  • WebKitGTK
  • whisper.cpp

Source code on GitHub under the MIT license. PN Scripts can adapt it for your project.

What it solves

The gap

Cloud assistants send your questions to someone else's servers and lose your context between sessions. A plain local chat window keeps your data private, but it knows nothing about your files or projects.

What it is

One Go program and one SQLite file. It uses a model you run in Ollama, learns from your code and documents with your approval, and answers with real file paths. What it learns never leaves your computer.

How you use it

Install it, point it at Ollama and ask. The first run finds Ollama, offers to install a model and asks where to keep the memory.

Ollama runs the language model. PN Scripts Assistant adds the long-term memory, the tools and the interface, and stores everything it learns in one file on your disk.

Who it is for

Use it when

  • You want a local assistant that already knows your projects, instead of an empty chat.
  • Your personal or client data must not be sent to a hosted AI model.
  • You want voice answers at home and optional Home Assistant control, without a cloud account.

Built for

  • Developers who already run Ollama.
  • Anyone who wants a private assistant on their own computer, with optional voice.
  • People who want to move the memory to another disk or computer and keep everything it learned.

Privacy is enforced in code

What PN Scripts Assistant has learned about you never leaves your computer, in any mode and with any setting. There is no telemetry. If the privacy setting holds an unknown value, for example a typo, it is treated as private.

private Default

Nothing. Local model, local embeddings, no web access.

research

Search queries only. Conversations and memory stay here.

open

What you type may go to a third-party model. Memory stays here.

What it does

Remembers your projects

It recalls what it already knows about your projects and documents. Ask "Where does that project live?" and you get the real path on your disk.

Learns with your approval

It scans your code and documents and, after a conversation, suggests what is worth remembering. Anything it inferred waits for your approval. Facts it can check against the disk are saved automatically.

Works with files and tools

It can read files, list folders, run commands, search the web and control a smart home through Home Assistant. Every action is recorded, and a file it changed can be restored. In the Permissions panel you choose whether it asks every time, asks only about actions you have not allowed yet, or acts freely.

Shows a map of its memory

The interface draws a live map of what it has stored, grouped by how closely related the items are. You see what it knows at a glance.

Voice conversation

In conversation mode it listens until you stop talking, answers, reads the answer aloud and listens again. Speech recognition and speech output both run locally. Voice can ask questions but cannot take actions, so a misheard sentence cannot change anything.

Speed on an ordinary CPU

Without a graphics card, replies are slow. These figures are measured, so you know what to expect. The length of the prompt accounts for almost all of the reply time.

Prompt

~10 tok/s

Four cores, 7B model

Reply

~2.5 tok/s

Generation on CPU

Spoken turn

~40 s

Listen, answer, speak

Model loaded

6.8 s

15.8 s if the model reloads

Only a GPU, or open mode with a hosted model, changes the order of magnitude. Even in open mode, what PN Scripts Assistant has learned about you stays on your computer. Set OLLAMA_MAX_LOADED_MODELS to 2, or Ollama reloads the chat model before every reply.

Specs

Vendor
PN Scripts
Type
Software
Platforms
Go
Latest version
v0.2.2
Pricing
Free
License
MIT
Deployment
Self-hosted
Maturity
Early release, v0.2.2
Support
Community

Releases

  1. v0.2.2

    Release notes (opens in a new tab)
  2. v0.2.1

    Release notes (opens in a new tab)
  3. v0.2.0

    Release notes (opens in a new tab)

Stack

  • Go
  • SQLite
  • Ollama
  • WebKitGTK
  • whisper.cpp

Install PN Scripts Assistant

Download a release from GitHub or build it from source with Go. You also need Ollama with a chat model and nomic-embed-text. The first run checks what is missing and offers to install it. Free and open source under the MIT license, on GitHub. PN Scripts can adapt it for your project.

Source code on GitHub under the MIT license. PN Scripts can adapt it for your project.

Questions

In private mode, nothing. Research mode sends search queries only. Open mode may send what you type to a third-party model. What PN Scripts Assistant has learned about you never leaves your computer, in any mode, and no setting changes that.

Ollama with a chat model and nomic-embed-text. On Linux the native window needs libwebkit2gtk-4.1 and libgtk-3; on macOS and Windows the interface opens in your browser. Voice is optional: speech-dispatcher, espeak-ng or piper to speak, and whisper.cpp to listen. The first run checks all of this and offers to install what it can.

On a CPU without a GPU, yes. Measured on four cores with a 7B model: about ten tokens a second to read the prompt and two and a half to write the answer. A spoken turn takes around 40 seconds. A GPU, or open mode, changes the order of magnitude, and the memory still stays on your computer.

No. Voice can ask questions but cannot take actions, because spoken turns are sent without tools. Anything that changes a file has to be typed.

In a folder marked with a .brain-root.json file. PN Scripts Assistant looks for that marker on every mounted drive, so the memory can live on an external disk. Without one, it creates a folder under ~/.local/share. Settings are kept next to the data in brain.conf.

Download it from the GitHub repository linked on this page. It is free and open source under the MIT license. If you want it adapted for your team or project, PN Scripts can do that as paid work.