over the last month or so iโve been digging into how coding agent harnesses actually work.
looking at tools like claude code, codex, opencode, and especially pi from @badlogicgames, itโs been interesting to peel back the layers and see the patterns underneath them ๐
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 weโre 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 youโre curious about how these systems are structured under the hood, hopefully this is useful.
post: https://t.co/IXioaCtd7b
code: https://t.co/7m5By427gL
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 ๐
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 https://t.co/hzBAZFdhZK
been spending some time going through PRs across my OSS projects recently.
just released garmin connect mcp server v1.0.1 ๐
itโs now published on PyPI, so you can run it directly with:
uvx garmin-connect-mcp
repo: https://t.co/tBKcHftSuw
#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. https://t.co/RSrRtIhgaV
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 ๐
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
for your enjoyment:
https://t.co/agn3BP6PJy
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!
https://t.co/j7mCk3PaQ7