Have you tried analysing all your prompts, and then telling it to "figure out" what custom skills might improve your prompts?
I do actually have another project I'm working on that does this... it's been super useful for seeing how I prompt, what Skills I use and getting them to evolve and improve (I know Hermes does some of this, but it's been interesting rolling my own - will release soon!!)
Nice! I love Cal Newport. I've definitely found spinning up multiple Claude Code instances eats into your focus, and you can "lose yourself" quite quickly.
I find I use pomodoros more as nudges, and use the "beeps" to bring me back if I'm in the browser or something. but yeah... it's a trap for sure!
Me too. Also it’s good to get decent reports that can be used for other things. For example the logs help me fill in my time sheets. Also it forces me to take breaks
Thanks for sharing. I was stuck in a Greek hospital for 8 days with 2 fractured vertebrae, before I could get home.
It’s easy to get into a spiral, but putting your mind to build something really helps.
I do hope your ribs and collar bone is getting better?
I’ve been lucky, as it will heal but could have been really bad. Phew!
Mmm apols. You’d think I’d have learned my lesson by now, but it’s just so seductive to have it write for you.
I got burned with this very HN post for doing just that, but they kindly let me rewrite it.
Will tweak it. Thanks for the feedback!
Fantastic. I think these small productivity tools embedded in harnesses is pretty powerful.
I especially like that you can get the AI to use it and also just pop into the CLI.
Also nice to generate useful web dashboards etc
These are my "LLM Wiki" notes, I've been using to build a central resource of "how to build an AI First Startup"
If you've got any other tips *I'd love to hear them* - thank you!
Over the last few days I've added peer-to-peer communication, using a simple message passing and status checks... no need for complicated hooks etc.
One repo agent found a bug and told the curator repo agent what it was, and it went ahead and fixed it
Over the last few months I've been quietly adding more features to elfmem my "evolving" agent memory library ( https://github.com/emson/elfmem ). I'm now able to use it in Claude Code et al. to curate my repos, and even write indie articles based off my obsidian vault. Anyway this article explains how. I'd love a comment, or even a github star! Thanks Ben
This has been a fascinating project. I've had the chance to explore some really original ideas. Things like: blocks that can be calibrated, mind blocks that can be used to simulate other agent behaviors, graphs, dreaming, frames that return a SELF or ATTENTION, etc. group of memory blocks, and peer to peer message passing.
All this has led to a really powerful agent framework you can use today.
I'd love a comment... thanks! Ben
Agents need memory that evolves. Memory blocks should degrade or get promoted over time, this opens up agents as repo curators... magic then happens if they can then talk to each other.
This is interesting as there is definitely a middle ground for agent memory. On the openclaw side you have a single MEMORY.md file on the other you have RAG and GraphRAG.
I wonder if Agent memory should be more nuanced? When an agent learns something how should it promote or degrade these memory blocks - you don’t want a trading agent memorising a bad trading pattern, for example.
Also the agent might want to recall semantically similar memories, but it might also want to retrieve block relationships or groups of blocks for different purposes.
We’ve been exploring all these concepts with “elfmem” (sELF improving MEMory): https://github.com/emson/elfmem
Would love your feedback!
Thanks so much for the comment! Yes, I initially had LiteLLM gateway and backed it out after the security issues.
Memory is becoming a crucial part of agents and there isn't a one size fits all solution - unfortunately. I found I wanted to replicate things like SOUL.md but in a way that could "evolve", so this project has "frames" which is just a collection of tagged / filtered memory blocks which can be used to identify specific concepts.
It also allows the agent to use "outcomes" to calibrate it's own memory blocks, which is really powerful.
Anyway I think "cognitive loops" are going to become more relevant, and will be an art. Thanks again... let me know how you get on!!