@javisantana There is

@mervenoyann Nice! Are there plans to integrate smolagents with MCP servers?

@CasazzaNY @marktenenholtz @firecrawl_dev It usually overloads it, I was usually `curl`ing it locally and then grepping for something with lots of extra context lines. That said, I've been changing my workflow since Cursor got the agent mode.

@marktenenholtz @CasazzaNY @firecrawl_dev Just a simple crawler running on GitHub Actions! There are many CLI tools that let you do that in one command too.

@CasazzaNY @marktenenholtz @firecrawl_dev I have a small repo where I generate a docs.txt file each day for some of the projects I work most with!

RT @PyDataGRX: ¡No te pierdas el 11º MeetUp de PyData Granada el 20/02/2025! 🤖 Exploraremos Agentes IA y Pacientes Virtuales. Ven a Novatec…

@chrisalbon Remember to take breaks every 20 minutes (around ~12 hours IRL) or so!

@themylesfiles @huggingface @DataPolars @duckdb Do you know if there are issues for these? Looking forward to being able to read Parquet files in Marimo using Polars / DuckDB!

A benefit of keeping a Personal Knowledge Base with lots of tips is that these files are excellent prompts for LLMs! - - - -

I've found Cursor Agent to be a much more useful tool with these tricks. I've seen it do web searches to check documentation, use `uvx` to run CLI Python commands, and even follow random links in with `markitdown` to learn more about a topic.

@victorianoi Sharing also a recent short but useful video on how Community Notes work.

@victorianoi Also, all community notes data is public!

@javisantana @nicoritschel recent sqlctx is an amazing tool in that direction!

@matsonj @hamiltonulmer That's on a GH issue, right? Not in VS Code. Need to catch up on Copilot Workspaces.

@matsonj @hamiltonulmer Please expand. How are you using it? Is it by creating issues in GH?

RT @BCiechanowski: Moon –

@frasergeorgew @haro_ca_ @CasazzaNY @DataPolars There is an initiative for that!