Your robot fren that reacts to Internet Capital Markets using Alphakek Fractal knowledge engine as its brain.
Project description
Openfren
Proof-of-Concept. Your robot fren that reacts to changes in Internet Capital Markets using Alphakek Fractal knowledge engine as its brain. Free and open source.
TODO
- Fractal 2 integration
- Voice commands
- Conversation mode
- Face tracking
- Emotion recognition
- Face recognition (local, on-device)
Installation
Using uv (recommended for dev):
uv sync
From PyPI (runtime only):
pip install openfren
Configuration
- Environment variables (only these are configurable):
AIKEK_API_TOKEN— required. Obtain one at https://app.alphakek.aiAIKEK_QUESTION— optional, default: "crypto market sentiment now, one line"
You may pass environment variables directly or via a .env file. See env.example for a template.
Run
If you don't have the physical robot yet, first start the simulation:
uv run reachy-mini-daemon --sim --scene minimal
If you have a robot, just start the daemon:
uv run reachy-mini-daemon
Then start Openfren:
uv run openfren
Test
uv run pytest
Notes
- Developed and regularly tested on Linux. macOS/Windows should work (best‑effort), but are not as thoroughly validated.
- Requires Reachy Mini hardware or the simulator daemon.
Development
See DEVELOPMENT.md for architecture overview and contributor/developer details.
Credits
- Reachy Mini by Pollen Robotics
- Emotions dataset:
pollen-robotics/reachy-mini-emotions-library
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file openfren-0.1.0.tar.gz.
File metadata
- Download URL: openfren-0.1.0.tar.gz
- Upload date:
- Size: 113.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: uv/0.9.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
867858472b2ba85b5dc6d6aa6c30d2847d7d3e85fa829a8ccf0e834e820b9561
|
|
| MD5 |
0b5bed4ab236ac30947ee59b6f4524c2
|
|
| BLAKE2b-256 |
aa41300e3b537670106e5291756c5914bcaf5b6f25fb561712725d5ee6549c03
|
File details
Details for the file openfren-0.1.0-py3-none-any.whl.
File metadata
- Download URL: openfren-0.1.0-py3-none-any.whl
- Upload date:
- Size: 11.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via: uv/0.9.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
483d8f9da6b834e4bfc29ac123eb0a0f440689113dc0f1ac25df10fefe8e0058
|
|
| MD5 |
da49e9c319d453338424b682d353ff73
|
|
| BLAKE2b-256 |
6a4c8a031aee9b0993c2b5b195a33ae3f30bf299664698ac46451cfd90ec7679
|