hof

Ah, deterministic abstraction layer vs. workflow framework vs. ide. So much for always use lambda expressions in macros and never have to worry about mutex issues. > What's missing for a true deterministic .... agreed upon common reference monoid / starting point > What is stopping us from such language, visualization or construction method? ADA Spark, Gleam_otp/Elixir/Erlang_otp aren't main stream. All programing languages don't interact natively with BEAM. Domain/subject area using DAL in/for/with is missing. OBS studio[0] might be more easy for producing live video streaming/production. Dynebolic[1] is an OS distribution geared for multimedia production. vs. DAL's for banking / stock market transactions. vs. DAL's used in PX4 [2] & ways to add to / expand a DAL [3] ------------------------------------ [0] : https://obsproject.com/ [1]

I've built something like this, check out the code gen feature https://hofstadter.io | https://github.com/hofstadter-io/hof It's built around CUE + text/template (template authoring is the more painful part)

Are you this guy? https://github.com/hofstadter-io/hof/tree/_next Third time I've seen CUE mentioned in this context in as many days.

Being one of CUE's biggest fans, I will definitely be interested! I have another thing in hof that is closer to this, also CUE + Dagger https://github.com/hofstadter-io/hof/tree/_next/examples/env https://github.com/hofstadter-io/hof/tree/_next/lib/env I'm gearing up for a major rewrite into a new project, based on a bunch of learning and a desire to remove a ton of cruft that accumulated over 10+ years. I still debate if I want to wrap existing tools (tf, helm, etc...) or go for a full sail replacement. Dagger handles a lot of the tooling earlier in the CI process, mainly thinking CD here. Argo-* is our bain lately... You might find the code gen aspects of hof interesting, I opted for Go's text/template, which you can also use from CUE if you wanted to have more literate (imo) code gen in your project.

The breadcrumbs start here: https://github.com/hofstadter-io/hof/tree/_next/lib/agent (my personal developer swiss army knife) I'm gearing up for a major rewrite, there is a lot of cruft in there from nearly 10 years of my experiments and explorations :]

I use open weights and harnesses not tied to a single vendor, I definitely do not touch anything the two US Big Ai labs puts out. I'm not interested in handing power and control of humans most significant technology to the same class of people that brought us the technologies that created our mess of a digital ecosystem. I switched to pi while I go refresh my personal/custom harness, though that may be a bit off, there are more important things to work (and burn tokens) on https://github.com/hofstadter-io/hof/tree/_next/lib/agent

I was solving your problem.before LLMs with my personal developers Swiss army knife (hof gen/CUE+templates). I'm somewhat keen to see how I can capture the agent markdown I want in many places, like project init, in CUE via embed and modules I can import and version, skipping the need for a markdown dependency cycle management system. https://github.com/hofstadter-io/hof (sharing because it has sloppy parts and that/I.S. shouldn't stop you from sharing!)

> Any other Go-based AI / LLM tools folks are happy with? I can throw my hat into the ring, built on ADK, CUE, and Dagger (all also in Go); CLI, TUI, and VSCode interfaces. It's my personal / custom stack, still need to write up docs. My favorite features are powered by Dagger, sandbox with time travel, forking, jump into shell at any turn, diff between any points. Good entrypoint folder: https://github.com/hofstadter-io/hof/tree/_next/lib/agent

The Dagger TUI is pretty sweet. They have an awesome renderer for OTEL spans (how they emit and view the steps). Built on the Charm suite, it is a better way (imo) to define, build, and run containers and containerized workflows (not at scale). I back my agents and sessions with it for superpowers beyond sandboxing. My personal CLI/TUI is https://github.com/hofstadter-io/hof and starts from a CUE centric developer experience. The above is also a part of it

The next step to this is using a better tool to access containers (BuildKit), like Dagger, where you can track every step as a new container layer, time travel, share via registries... This has been my setup since early this year, not even that much code: https://github.com/hofstadter-io/hof/tree/_next/lib/agent/se... The bigger effort is making it play nice with vscode so you can browse and edit the files and diffs.

Yeah, you do want to massage them a bit, and I'm on some older ones before they became so split, but this is definitely the model for subagents and more tools. Most of my custom agent stack is here, built on ADK: https://github.com/hofstadter-io/hof/tree/_next/lib/agent

I like ADK, it's lower level and more general, so there is a bit you have to do to get a "claw" like experience (not that much) and you get (1) a common framework you can use for other things (2) a lot more places to plug in (3) four SDKs to choose from (ts, go, py, java... so far) It's a lot more work to build a Copilot alternative (ide integration, cli). I've done a lot of that with adk-go, https://github.com/hofstadter-io/hof

I have all this with my custom agent setup too I think you are overreaching in your dismissal of everything else out there. There are 1000s now, you are not the first to think of or implement any of this. It's within https://github.com/hofstadter-io/hof if you are curious I prefer a world where more people do what we have, but don't try to make it into a money making endeavor. Let uniqueness and individuality flourish over winner takes all, Big AI decides how we use this tech. More indie please

I just added a TUI built on Charm for my custom agent. I primarily use it for two things. 1. Navigating all my chat sessions and doing admin work. It's super fast to push a single key to go in and see what it was about before deleting it. 2. Testing out features and code changes without the web UI / vs code extension complexity. 3. Places where I cannot connect VS Code. I still want to chat and see diffs, a TUI is much easier than a CLI for this. It also has a CLI, basically three interfaces (CLI, TUI, GUI (vscode/webapp)) to the core features of my personal swiss army knife (https://github.com/hofstadter-io/hof)

Dagger has a similar feature: https://docs.dagger.io/getting-started/types/secret/ Same idea with more languages on OCI. I believe they have something even better in the works, that bundles a bunch of things you want in an "env" and lets you pass that around as a single "pointer" I use this here, which eventually becomes the sandbox my agent operates in: https://github.com/hofstadter-io/hof/blob/_next/.veg/contain...