https://github.com/tomelliot/all-ears
Granola started clamping down on downloading your notes without paying for a subscription, and I got sick of all the barely maintained GUIs on top of various local models (MacWhisper ).All-Ears is a set of composable tools to transcribe and summarise meetings. - A daemon that records audio sources - `transcribe` to transcribe the audio (with diarisation) - `cleanup` to clean the transcription,...
Request URL
https://roboticsregistry.net/api/v1/access/request/
Request Method
POST
Status Code
500 Internal Server Error
Granola are cracking down on their auth and I can no longer pull my meeting notes out and put them in Obsidian (my plugin is gonna have to be deprecated: https://github.com/tomelliot/obsidian-granola-sync/).That means I'm gonna need a different meeting transcription/summary pipeline. There's a cambrian explosion of meeting transcription tools...
also, such a smart idea to build the excel runtime alternative. remember us when you get snapped up by a lab for a training environment.
https://obsidian.md/plugins?search=granola
Over 550 installs! I didn't expect other folks to use it, but it turns out other people also wanted to have their Granola notes + transcripts in Obsidian.It's my first open source project, so it's cool to have some people using it, and even submitting issues and PRs.If you use Obsidian + Granola, and have suggestions for how to make it even better, I'd love to hear it.
https://obsidian.md/plugins?search=granola
I made a community plugin to get notes out of Granola and into Obsidian.It syncs the transcript and the generated note.Thanks to the AI coding robots for doing 90% of the typing.If it's your jam contributions are welcome: https://github.com/tomelliot/obsidian-granola-sync
https://github.com/modelcontextprotocol/registry/
The full details on how they're thinking about this ecosystem:
https://github.com/modelcontextprotocol/registry/discussions...
I’ve been messing around with MCP servers to get a feel for the ecosystem. I’m seeing a real issue, and I’m not sure what solutions are possible with the architecture - am I missing something?The LLM always sits in the middle of any pipeline. That means you’ll always have potentially messy and lossy translation in between every tool call (not to mention incredibly slow/wasteful compared to...
Do you support using a different no code front end?
I did the same thing with building something in excel - I didn't think as hard about the retirement portion though and just matched it to my previous pension contributions from when I was employed, so that's a great addition.
One thing I have in my sheet that I find helpful: A comparison with an equivalent annual salary at an employer. For example I have a day rate that is a rough approximation to match the annual salary I'd like to have if I were employed by someone - taking into account that the day rate needs to include sick days, holidays, the employer's share of insurance and pension contributions that I now pay etc.