Edd Mann

over the last month or so i’ve been digging into how coding agent harnesses actually work. looking at tools like claude code, codex, opencode, and especially pi from @badlogicgames, it’s been interesting to peel back the layers and see the patterns underneath them 👀 i learnt a lot in particular from looking at how pi has been architected. as a result, i ended up building my own coding agent harness in python and documenting the rings that build around a minimal agent loop to create the kinds of systems we’re starting to see more of: - providers - tools + permissions - sessions + state - context strategy + compaction - prompts + skills - plugins + extensions - delivery the post walks through those layers piece by piece, along with the accompanying code and diagrams. if you’re curious about how these systems are structured under the hood, hopefully this is useful. post: eddmann.com/posts/around-t… code: github.com/eddmann/my-own…

have really enjoyed using this tool recently! initial analysis and breakdown of semantic features within a system to then go on and review in parallel is very useful. thanks @steipete

I setup MCP server for Garmin so I asked Claude to analyze my bike training and give me recommendations It did and suggested 5 workouts I can start doing It then created them in my account Super cool Thanks for the MCP @edd_mann 👏

@DilyanDimitrov that's awesome! really glad to see you're finding it useful 🙏

we've been increasingly using agents for production operations on Deno Deploy Open sourcing what we built to sleep easier while these things run 24/7 I wrote about our motivation here deno.com/blog/clawpatrol

@ashleyhindle oh man, i've had that happen to me just now too! back to gpt 5.5 i go...

Tempted to stop my Claude subscription because every time I open it and type out a long ass thought, it replies with Please run /login · API Error: 401 Invalid authentication credentials Why is it logging me out every 40 seconds?! But 'claude auth status' says it's all good?! 🧐

been spending some time going through PRs across my OSS projects recently. just released garmin connect mcp server v1.0.1 🎉 it’s now published on PyPI, so you can run it directly with: uvx garmin-connect-mcp repo: github.com/eddmann/garmin… #opensource #mcp #claudeai #garmin #python

Cloudflare's security team spent the last few weeks testing Anthropic's Mythos against fifty of our own repositories. What we learned about offensive AI, why faster patching is the wrong reaction, and what the architecture around vulnerabilities has to look like next. cfl.re/49BRUqW

@MrSimonBennett looking forward to seeing the results!

Sample Products ordered PCB designs on the way too. Lets see if I can build a real product

@ashleyhindle that is pure magic! 🪄😎

SSH is now my signup form. GitHub auth, but easier than OAuth Vask gets your public SSH key, checks it against your GitHub account, creates you a websocket app, then prints your Pusher-compatible websocket credentials 💪 ssh gh_username@vask.sh No redirect. No dashboard.

love the new pi website design! @badlogicgames @mitsuhiko 🖌️🎨

my new favourite thing recently has been exploring codebases through mermaid diagrams. being able to generate up-to-date architectural overviews - then zoom into the specific parts of the system i care about at that moment - has been incredibly useful 👌

@ashleyhindle this along with the html agent output movement makes it so much easier to digest stuff!

Back in the day 👴 I hated diagrams - "just gimme an indented bullet point list!" - but now I can't get enough of mermaids 🧜 😅

@lucasmeijer oh man i know the feeling, that's a great lib!

I wish I had learned about diffs.com this morning instead of just now.

it's too easy to get distracted, i've been using @jsonresume as the source for multiple themes of my cv, letting the frontend design skill run wild! haha

til about `await using` in ts for auto. async cleanup thanks to @mattpocockuk’s sandcastle project 🙏 developer.mozilla.org/en-US/docs/Web…

for your enjoyment: github.com/badlogic/gpt-2… GPT-2's architecture is really really simple to understand mechanically. Modern arch's are obviously more complex, but the basic principles are largely the same still. study it! openai.com/index/better-l…

you can outsource your thinking but you cannot outsource your understanding

you can outsource your thinking, but you can’t outsource your understanding

@dillon_mulroy flakey tests, tests with commitment issues.

i hate flakey tests i hate flakey tests i hate flakey tests i hate flakey tests i hate flakey tests i hate flakey tests i hate flakey tests i hate flakey tests i hate flakey tests i hate flakey tests i hate flakey tests i hate flakey tests