emson
Re:
on Friday July 03, 2026 @05:41AM (#48772990)
Wooo that's so cool... it seems to be private?
Re:
on Thursday July 02, 2026 @12:41PM (#48764027)
Fantastic! You should open source it
Re:
on Thursday July 02, 2026 @12:40PM (#48764008)
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!!)
Re:
on Thursday July 02, 2026 @12:36PM (#48763967)
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!
Re:
on Thursday July 02, 2026 @11:33AM (#48763158)
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
Re:
on Thursday July 02, 2026 @11:31AM (#48763132)
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!
Re:
on Thursday July 02, 2026 @11:26AM (#48763063)
It has sensible defaults just do /pomo start
It’s only if you want to customise it. Also CC will do it for you. It’s very agent friendly
Re:
on Thursday July 02, 2026 @11:16AM (#48762926)
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!
Re:
on Thursday July 02, 2026 @11:12AM (#48762873)
Ah nice thanks. Love tmux, incidentally I came across this the other day as an alternative to Ghostty: https://supacode.sh/
Re:
on Thursday July 02, 2026 @11:09AM (#48762846)
Oh that’s an idea? Could use hooks or something?
Re:
on Thursday July 02, 2026 @11:09AM (#48762837)
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
Re:
on Thursday July 02, 2026 @09:51AM (#48761651)
Ooo that's cool thank you. That's really useful!
My other CLI project was: https://github.com/emson/pymodoro
Re:
on Thursday July 02, 2026 @08:01AM (#48760087)
3 weeks ago I had a nasty accident and fractured my vertebrae. As I lay in bed I needed something to take my mind off it all so built "Claudoro".
Claudoro is a pomodoro timer built right into the Claude Code status line, as well as can be directly controlled from Claude Code and the CLI. A few years ago I built "pymodoro" which was great, but recently I felt I needed something embedded in the tools I actually use, and I also wanted something that was flexible, and I could tweak and nudge.
Anyway I hope it is useful to you, and I'd love some feedback on how to improve it.
Thank you...!
PS this is a write up all about how it works etc: https://benemson.com/blog/agents/claudoro-pomodoro-timer-cla...
Re:Consolidated AI First Startup Guide
on Tuesday June 02, 2026 @06:27AM (#48368327)
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!
Anatomy of a GitHub Sponsor Memecoin Consent Gap
Re:Anatomy of a GitHub Sponsor Memecoin Consent Gap
on Wednesday May 06, 2026 @05:09PM (#48041881)
So I’m an idiot. Somehow I fell into this and now feel guilty. So I figured I’d write it up so that it doesn’t happen to anyone else.
Re:My Agent Memory Library Helps Write Indie Articles
on Sunday May 03, 2026 @04:10PM (#48000883)
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
My Agent Memory Library Helps Write Indie Articles
Re:My Agent Memory Library Helps Write Indie Articles
on Sunday May 03, 2026 @04:08PM (#48000862)
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
Re:Elfmem: Evolving Agent Memory
on Friday May 01, 2026 @05:39PM (#47980753)
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
Re:Elfmem: Evolving Agent Memory
on Friday May 01, 2026 @05:33PM (#47980687)
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.
Elfmem: Evolving Agent Memory
Re:We replaced RAG with a virtual filesystem for our AI documentation ...
on Saturday April 04, 2026 @03:14AM (#47636694)
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!
Re:I built a better, human like memory, for Agents
on Monday March 30, 2026 @09:10AM (#47573837)
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!!
I built a better, human like memory, for Agents
Show HN: Word Pulse, Connect pulsing letters (Svelte 5, Moby list)
https://scrambleletters.com/apps/word-pulse
I built Word Pulse as a fun, educational word game for my family. It’s a browser game where you connect letters on a pulsing grid to form words and try to keep things in equilibrium.Play it: https://scrambleletters.com/apps/word-pulseHow it’s built: Svelte 5 for the UI, with a custom word check pipeline based on the Moby word list (preprocessed into a fast lookup structure). All gameplay runs...
Show HN: Elf0 – Build and run AI agent workflows in YAML (CLI)
Hi HN — I built Elf0, a command-line tool to define and run AI agent workflows in YAML. It helps you iterate on small multi-step "agents" without scaffolding a whole codebase.The agent patterns described in Anthropic's article was an inspiration: https://www.anthropic.com/engineering/building-effective-age... I then used Nvidia's AgentIQ YAML spec as inspiration.Why: I keep bumping into tasks...
Show HN: Pymodoro – CLI Pomodoro Timer
https://github.com/emson/pymodoro
I should have been building something else, then totally got Yak shaving and made this simple little Pomodoro timer. Before you ask, yep it was vibe coded... sorry. Anyway it's really simple and fun to use, so I thought I'd share. All written in Python, and uses `uv` so you can do a `uvx` tool install globally. Enjoy...
Re:What is currently the best LLM model for consumer grade hardware? I...
on Friday May 30, 2025 @08:01AM (#44135318)
Good question. I've had some success with Qwen2.5-Coder 14B, I did use the quantised version: huggingface.co/Qwen/Qwen2.5-Coder-14B-Instruct-GGUF:latest
It worked well on my MacBook Pro M1 32Gb. It does get a bit hot on a laptop though.