Before building SquidMesh, I was experimenting Gleam (because of the types) and built this basic job runner (hit the wall on recovery strategy but decided to stop as there were other libs doing the same with heartbeat) GitHub - ccarvalho-eng/kairos: A background job runner for Gleam. · GitHub
After spending a weekend coding in Gleam, I started missing Elixir 
It doesn’t have the same ecosystem (ORMs, Database adapters, etc) so code can look more complex than it actually is.
Btw you’ll not regret if you move to Codex. It’s way more “reliable” or at least it’s stricter following instructions. Eventually it even refuses to make bad choices we give it.
One of my colleagues is telling me the same. Not like I don’t believe it but I spent months building processes and memories of Claude so lifting that to another LLM is a substantial task, and our app is vibe-coded enough to need a lot of guard-rails. Losing those and having to reinvent them from scratch is just a “nope!” from me, though I admit there is a work process during which I could lift all the rules and transfer them to a vendor-neutral file i.e. AGENTS.md. But that does not help with literal 60-ish Claude memories that document many different processes / daily ways of working / gotchas and dangers / non-obvious patterns in our codebase / aspirational refactors so we don’t allow certain slop again (even if we can’t yet refactor it out) etc.
But again, just can’t find the time. I guess I should just say “frak it” and then find the time.
Did a quick skim. Actually I can see where you got certain inspirations. 
Projects like these are mostly learning opportunities. We are blessed to be able to experiment without putting our living spaces on fire. So yep, let’s abuse the freedom!
That’s a real and tangible negative as you found out. I just don’t have the time or even the inclination anymore to be an early adopter of programming languages and I am fine with it.
Libraries and frameworks are another matter. SquidMesh already looks very useful.
Same. Every time I write a Golang program, I facepalm: “Why do these people have a half-implemented OTP runtime with a bunch of footguns? And then they introduce 20 linters to prohibit the usage of 3rd party libraries that fix these idiosyncrasies, even? WTF is wrong with these people?”.
Golang can be so much better if most of the community would just adopt N libraries as de facto standards and finally move on. Which of course reminds me of this wisdom:
Rust is much better, but discoverability of good libraries is very difficult; you have to be in circles and talk to people and be in Discord servers. Too much comms overhead for my taste. But Rust is still strictly and much better if you are willing to put on the elbow grease.
Squid Sonar has some controls now (not read-only anymore): GitHub - dark-trench/squid_sonar: Durable Workflow Dashboard · GitHub
It’s not published yet to hex.pm as squid-mesh was not published too. Will push a new release next week
Actor-based visibility was added to main GitHub - dark-trench/squidie: Durable Workflow Runtime · GitHub
SLA contract is in the works
released Squid Mesh 0.1.0.
This is the first non-prerelease package, and the docs now frame the project around the
supported 0.1.x journal runtime instead of the old early-development warning.
Main things included since the last beta:
Hex: squid_mesh | Hex
Docs: squid_mesh v0.1.0 — Documentation
Release notes: Release v0.1.0 · dark-trench/squidie · GitHub
The core stance is still the same: Squid Mesh is embedded in the host app, keeps workflow state
durable through Jido journals, and leaves queue delivery, leasing, alerting, and operational
rollout as host-owned boundaries.
Some minor updates:
Some minor Squid Sonar features: runtime workflow execution and resume, replay, cancel, approve, etc controls
i started laying the foundations and milestones for https://github.com/dark-trench/squid_studio (the visual editor)
it should help identify the remaining gaps in squidie to support visual editors
also, new name → new logo 
