HackerReposA FIELD GUIDE TO OPEN SOURCE
ProSponsor the shelf♧ 0
← Back to top all-time
hofstadter-io
hof
Go2020–2026
hofstadter-io / hof

hof

A developer experience centered on CUE. Unifies schemas, data models, deterministic and agentic code generation, workflow and task engine, dagger powered environments, coding assistant, and vscode extension; woven together on the CUE lattice. Squint harder if you can't see the cube :]

4Distinct people
117Mentions
1Explicit recommenders
616GitHub stars
REPOSITORY AT A GLANCE

What to know before exploring

What it is

A developer experience centered on CUE. Unifies schemas, data models, deterministic and agentic code generation, workflow and task engine, dagger powered environments, coding assistant, and vscode extension; woven together on the CUE lattice. Squint harder if you can't see the cube :]

GitHub

Where it is used

No documented product use was verified in the last source check.

What people are saying

> 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.…

verdverm used a recommendation phrase. 2 indexed comments match. This is a phrase match, not a verdict.

No classified warning is attached to this page. Read the discussions before treating silence as approval.

Also in these discussions

Mentioned in the same Hacker News threads. That is not proof they are substitutes.

This week on Hacker News

Nov 9–Nov 16 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/16/2026, 2:19:09 PM UTC.

No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.

Mentions over time

HN mentions by year117 dated mentions

Observed mentions: 2020-02-25 14:26:22 UTC to 2026-10-30 21:26:40 UTC.

01020302020-01-01 00:00:00 UTC to 2021-01-01 00:00:00 UTC (exclusive): 25 mentions; 2 submissions, 23 comments20202021-01-01 00:00:00 UTC to 2022-01-01 00:00:00 UTC (exclusive): 15 mentions; 0 submissions, 15 comments2022-01-01 00:00:00 UTC to 2023-01-01 00:00:00 UTC (exclusive): 12 mentions; 0 submissions, 12 comments2023-01-01 00:00:00 UTC to 2024-01-01 00:00:00 UTC (exclusive): 27 mentions; 0 submissions, 27 comments20232024-01-01 00:00:00 UTC to 2025-01-01 00:00:00 UTC (exclusive): 10 mentions; 1 submissions, 9 comments2025-01-01 00:00:00 UTC to 2026-01-01 00:00:00 UTC (exclusive): 6 mentions; 0 submissions, 6 comments2026-01-01 00:00:00 UTC to 2027-01-01 00:00:00 UTC (exclusive): 22 mentions; 0 submissions, 22 comments. Incomplete calendar period.2026*

* An incomplete calendar period is marked with an outlined bar. Its count is not directly comparable with a full period.

Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.

View mention counts and date ranges
UTC ranges include their start and exclude their end. Select a period to filter the source evidence.
PeriodStart (UTC)End (exclusive, UTC)MentionsSubmissionsComments
20202020-01-01 00:00:00 UTC2021-01-01 00:00:00 UTC25223
20212021-01-01 00:00:00 UTC2022-01-01 00:00:00 UTC15015
20222022-01-01 00:00:00 UTC2023-01-01 00:00:00 UTC12012
20232023-01-01 00:00:00 UTC2024-01-01 00:00:00 UTC27027
20242024-01-01 00:00:00 UTC2025-01-01 00:00:00 UTC1019
20252025-01-01 00:00:00 UTC2026-01-01 00:00:00 UTC606
2026 (partial)2026-01-01 00:00:00 UTC2027-01-01 00:00:00 UTC22022

What Hacker News says

27 sources
I was surprised out how you can define arbitrary grammars using arbitrary formulation and it would follow it. Of course you have to redo the prompt every time there is an update... such a pain https://github.com/hofstadter-io/hof/blob/_dev/flow/chat/pro... What surprised me is that you don't need all those "fancy" specialty libraries to do this (like MS/Guidance), I originally did this before they came out, and they seemed to limit the possibilities
In Ask HN: What's the most compelling AI prompt result you've seen?
fair enough Yeah, declarative DAGs 101 lol(?) Does python code get generated from the Yaml, or does python code load the Yaml and do Airflow tasks? I never thought specifying DAGs in airflow / python was that difficult. What problem is this solving? I have a thing that does CUE + text/template = anything maybe what you are describing is like the prior Yaml based input we used to use? [1] https://github.com/hofstadter-io/hof [2] https://docs.hofstadter.io/getting-started/code-generation/#...
In That's a Lot of YAML
It's still unclear to me if that is the right direction or a scalable solution. Seeing how far prompt engineering can get you on this from (specifying the grammar as a one/few shot) does pretty well, it seems like something that could be better handled at training/refining time? My general feeling is that it is inserting a specific and complicated cog, and probably has to be tweaked for each model (as they all have their little quirks) Curious what you think having been working directly on these things? From my experience, you can get an LLM to follow a "grammar" for pretty much anything, without it being an actual grammar spec in one of the many formats. You can pretty much make it up. Here's an example of us getting CUE out of a model by giving "tricking" the LLM to generate JSON with less syntax (a subset of both CUE and JSON). Bonus,
Read the rest
fewer quotes and commas meant fewer tokens. We turn this into JSON afterwards, works surprisingly well https://github.com/hofstadter-io/hof/blob/_dev/flow/chat/pro...
In Guidance: A guidance language for controlling large language models
Yea, in particular for this project, they have created a bespoke templating system. You can get the same thing with Go text/templates by adding chat function(s) as custom a helper: https://github.com/hofstadter-io/hof/blob/_dev/lib/templates... As a developer of these things, I don't get why they want to put so much effort into the mundane parts rather than focusing on the interesting parts. These things are mostly just the same as any other workflow or API call: https://github.com/hofstadter-io/hof/blob/_dev/flow/chat/cmd... (unless you get into the python and (i.e.) start messing with the logits or token probabilities)
In Guidance: A guidance language for controlling large language models
It was originally developed at Google, but Marcel is no longer there, there is a team and company behind it now. The language is going to a foundation (still waiting for update from the CUE team), fun fact, it started as a fork of Go (for the lexer, parser, and a bunch of goodies in that source tree) CUE's history is from borg, borgfig, GCL, but takes the approach Marcel always wanted to if not tied to the existing practices in a large company, namely Typed Feature Structures and logical programming (no overrides, layering, inheritance, general recursion) We're about to release a TUI for working with CUE, and hoping that it will make learning much easier for people. We do a lot with Cuetorials, but there is only so much you can do on a website (/rant WASM limitations). Using the Go SDK is the way to unlock CUE super powers. https://github
Read the rest
In The Power of Prolog
This is more a coordination problem, semver doesn't really matter here, except as a good enough standard or guardrail for most. It's going to get broken from time to time, and that is fine. The CUE Unity project is an interesting take on how to "solve" the bigger issue of breaking changes or regressions. https://github.com/cue-unity/unity Basically, the idea is that users can register their project, tests, or benchmarks in Unity. The project maintainers can then test new code against these projects before releasing, or even before pushing a commit, because a regression is found for example. This works by injecting the version (or local code) into the dependency management system. For CUE, this is a `go mod edit`, or setting up the environment with the cli at version / local. How this is set up and managed isn't as important as getting the
Read the rest
process in place and making it an easy workflow for both sides. Hence why I call it a coordination problem. We have a similar project Harmony, inspired by Unity, powered by Dagger. https://github.com/hofstadter-io/hof/tree/_dev/ci/harmony (it's really just a dagger pipeline that has a few flags and loops over data in a file)
In Semver violations are common, better tooling is the answer
The Dagger CLI has 2 amazing visuals 1. Normal mode, a DAG graph that displays as your builds run 2. Experimental UI on top of the DAG, allowing you to navigate and expand build step logs We are working on something similar based on Vito's amazing work for hof/flow We just put out an infinite nested panel implementation for a terminal UI, not necessarily output or logging, but allows one to create custom dashboards of widgets in a TUI https://github.com/hofstadter-io/hof/tree/_dev/lib/tui/modul... There are screenshots on my X profile, @verdverm
In Ask HN: Great examples of terminal output or logging
CUE is another interesting language to use from within Go, and is rather natural, given CUE is implemented in Go, but you can also do way more cool things with CUE via the Go API. We're using CUE to validate and transform data, as input to code gen, the basis for a DAG task engine, and more https://cuelang.org | https://pkg.go.dev/cuelang.org/go@v0.6.0/cue | https://cuetorials.com/go-api (learn about CUE) https://github.com/hofstadter-io/hof (where we are doing these things)
In Jacobin: A more than minimal JVM written in Go
low-code doesn't necessarily mean drag-n-drop, though that is typically the association in people's minds To us, low-code is really about creating simpler, or higher up the logical stack, abstractions, and then generating the implementation. Our take is not so far off from yours, where we take a code first approach. Users declaratively define their application in CUE and then get most of the code. Rather than providing hooks, we let the user write directly in the output code. Unlike Refine, we enable our tool to continue to aid the developer beyond the initial scaffold phase, allowing things like the data model to update and the user gets new database migrations to be auto-generated and applied. We also make it really easy for anyone to create and share these application blueprints or generators (as we call them). In this way, the user ca
Read the rest
n select any mix of technology and make starterkits or addons for any application, not just webapps. For example we have users (ops team) injecting and maintaining CI & k8s files into their service fleets (dev team). This is a case where we see low-code, as a term, more generally. https://github.com/hofstadter-io/hof
In Launch HN: Refine (YC S23) – Open-source platform for enterprise web apps

Showing the 15 most recent of 27 sources. Enable JavaScript to search and browse every indexed mention.

MAKE YOURSELF AT HOME

A few shortcuts

/
Search the collection
?
Open this guide
Esc
Close dialogs and navigation

Your saved repositories and interests stay in this browser.