MyFocalAI
Aggregates AI news from curated sources, scores relevance with LLM, and serves a dashboard.
Tested on Linux
Use it
Linux x86_64
You need first
- Runtimes:
Python 3.12+ - System packages:
uv,Docker,Ollama
Shallow clone repo (provides start.sh, deps installed by start.sh via uv sync)
rm -rf my-focal-ai && git clone --depth 1 https://github.com/YanCheng-go/my-focal-ai.git my-focal-ai
Check that it works
cd my-focal-ai && uv run ainews --helpThe output should contain “MyFocalAI”.
First thing to try
cd my-focal-ai && uv run ainews list-sourcesFrom the project folder, run ./start.sh --no-score to start the server, then open http://localhost:8000/ in your browser.
What it does
- Collect AI content from curated sourcesTested
How to use it
- Run
uv run ainews list-sourcesin the project folder to see the configured sources. - Start the server with
./start.sh --no-score. - Fetch the collected items with
curl -sf http://localhost:8000/api/items.
- Run
- View your news on a personal web dashboardTested
How to use it
- Start the server with
./start.sh --no-scorein the project folder. - Open http://localhost:8000/ in your browser to see the dashboard.
- Get the items as JSON with
curl -sf http://localhost:8000/api/items.
- Start the server with
- Score how relevant each item is with an LLMNot tested
How far pickfit got
Linux x86_64
- Installs
- Starts
- 2 of 3 features work
- Works offline
Good for
- aggregate AI content from curated sources
- score feed relevance using LLM
- serve personal news dashboard
How pickfit tested it
Each run starts from a clean machine and follows the steps above. How pickfit verifies
Linux x86_64
Its service answers requests
- Replayed from scratch
- Works offline
- Checked on 30 Oct 2026
- Version 0.8.0
Differences the test machine hit
- README: Prerequisites: uv and Docker
In the test: Docker missing only warns and continues; --no-score works without Docker