AI · alternatives · 2026
24 alternatives to Fructose – LLM calls as strongly typed functions
Hi HN! Erik here from Banana (formerly the serverless GPU platform), excited to show you what we’ve been working on next: Fructose Fructose is a python package to call LLMs as strongly typed functions. It uses function type signatures to guide the generation and guarantee a correctly typed output, in whatever basic/complex python datatype requested. By guaranteeing output structure, we believe this will enable more complex applications to be built, interweaving code with LLMs with code. For now, we’ve shipped Fructose as a client-only library simply calling gpt-4 (by default) with json…
Fructose is a Python package that enables developers to call large language models as strongly typed functions. It uses function type signatures to guarantee that LLM outputs match requested data structures, whether… Below are 24 products that do a similar job, ranked by how close each is in meaning and then by launch-day votes. Fructose – LLM calls as strongly typed functions launched in 2024; newer entries below may have overtaken it.
- 1
This is a Python package that allows you to write function signatures to define LLM queries. This makes it easy to mix regular code with calls to LLMs, which enables you to use the LLM for its creativity and reasoning while also enforcing structure/logic as necessary. LLM output is parsed for you according to the return type annotation of the function, including complex return types such as streaming an array of structured objects. I built this to show that we can think about using LLMs more fluidly than just chains and chats, i.e. more interchangeably with regular code, and to make it…
2023 · github.com · its alternatives →
- 2
Outlines is a Python library that focuses on text generation with large language models. Brandon and I are not LLM experts and started the project a few months ago because we wanted to understand better how the generation process works. Our original background is probabilistic, relational and symbolic programming. Recently we came up with a fast way to generate text that matches a regex (https://blog.normalcomputing.ai/posts/2023-07-27-regex-guide...). The basic idea is simple: regular expressions have an equivalent Deterministic-Finite Automaton (DFA) representation. We…
2023 · github.com · its alternatives →
- 3AT
Hey HN! Erik here from banana.dev We’ve trained a small(ish) language model on structured extraction, and today we’re launching a playground for it at https://anythingtojson.com. Give it a try! This model continues our work on structured generation, following last week’s launch of Fructose[1], a python client for strongly-typed LLM responses. There seem to be two distinct halves of the problem intended to be solved by Fructose and structured generation: 1. the reasoning ability of the model, such as performing chain of thought, creative acts, and natural language tasks. In a way,…
2024 · anythingtojson.com · its alternatives →
- 4
Hey HN, I've been using GPT a lot lately in some side projects around data generation and benchmarking. During the course of prompt tuning I ended up with a pretty complicated request: the value that I was looking for, an explanation, a criticism, etc. JSON was the most natural output format for this but results would often be broken, have wrong types, or contain missing fields. There's been some positive movement in this space, like with jsonformer (https://github.com/1rgs/jsonformer) the other day. But nothing that was plug and play with GPT. This library consolidates…
2023 · github.com · its alternatives →
- 5
Hi HN, Jack here! I'm one of the creators of MonkeyPatch, an easy tool that helps you build LLM-powered functions and apps that get cheaper and faster the more you use them. For example, if you need to classify PDFs, extract product feedback from tweets, or auto-generate synthetic data, you can spin up an LLM-powered Python function in <5 minutes to power your application. Unlike existing LLM clients, these functions generate well-typed outputs with guardrails to mitigate unexpected behavior. After about 200-300 calls, these functions will begin to get cheaper and faster. We've seen 8-10x…
2023 · github.com · its alternatives →
- 6
Python library for creating data pipelines with chain functional programming - EntilZha/PyFunctional
2017 · github.com · its alternatives →
- 7
I've been playing around with https://github.com/zphang/minimal-llama/ and https://github.com/tloen/alpaca-lora/blob/main/finetune.py, and wanted to create a simple UI where you can just paste text, tweak the parameters, and finetune the model quickly using a modern GPU. To prepare the data, simply separate your text with two blank lines. There's an inference tab, so you can test how the tuned model behaves. This is my first foray into the world of LLM finetuning, Python, Torch, Transformers, LoRA, PEFT, and Gradio. Enjoy!
2023 · github.com · its alternatives →
- 8
a python-like language with hindley-milner-like type system, which is compiled to c - alehander92/Airtight
2015 · github.com · its alternatives →
- 9
A library adding some anti-Pythonic syntatic sugar to Python - czheo/syntax_sugar_python
2017 · github.com · its alternatives →
- 10
An experimental Python-to-C transpiler and domain specific language for embedded high-performance computing - zanellia/prometeo
2021 · github.com · its alternatives →
- 11
An experimental language which adds functional programming features to Go. - albrow/fo
2018 · github.com · its alternatives →
- 12
A functional programming and concurrency library for Python: algebraic abstractions (Semigroups, Monoids, Functors, Applicatives, Monads), immutable data types, and message-passing concurrency, all designed as composable, type-safe values. - kamalfarahani/katharos
Aug 2026 · github.com · its alternatives →
- 13
Library for interacting with LLVM IR in pure Go. Contribute to llir/llvm development by creating an account on GitHub.
2017 · github.com · its alternatives →
- 14
Functional Reactive Programming Library for JavaScript - santoshrajan/frpjs
2016 · github.com · its alternatives →
- 15
A modern syntax for the λ-calculus. Contribute to VictorTaelin/Caramel development by creating an account on GitHub.
2015 · github.com · its alternatives →
- 16FS
Hi HN! I've been working on the fuse programming language, it's a statically typed purely functional language with higher-kinder types and ad-hoc polymorphism. It compiles to the GRIN whole-program optimizer, producing LLVM-generated native code. Fuse supports ADTs, Generics, Type Methods, Traits, Pattern matching etc. all in a functional style with no mutations. I’ve been developing the language for 5 years, with code written in Scala. I’ve started coding the language from the base of System F that was implemented as part of the book: Types and Programming Languages (tapl). And then…
Aug 2026 · fuselang.org · its alternatives →
- 17
Recently, I write an interpreter for subset of Python using Go. I haven't seen source code of CPython, all is just written according to my understanding of Python so there may be some unusual things. Hope you can play fun with it. Any suggestion is welcome, glad to get some feedback.
2023 · github.com · its alternatives →
- 18
We've been building data pipelines that scrape websites and extract structured data for a while now. If you've done this, you know the drill: you write CSS selectors, the site changes its layout, everything breaks at 2am, and you spend your morning rewriting parsers. LLMs seemed like the obvious fix — just throw the HTML at GPT and ask for JSON. Except in practice, it's more painful than that: - Raw HTML is full of nav bars, footers, and tracking junk that eats your token budget. A typical product page is 80% noise. - LLMs return malformed JSON more often than you'd expect, especially with…
Mar 2026 · github.com · its alternatives →
- 19
Bash4LLM is a single-file Bash wrapper for interacting with LLMs from the terminal. I created it because I wanted something simple that worked without installing Python, Node, or any other runtime. It uses only Bash, curl, and jq. You can send prompts, start a small chat, process files line by line, stream output, and save session metadata in JSON format. I tried to make it safe and predictable: no use of the system /tmp, no use of eval. Groq is supported by default, and other providers can be added with dedicated Bash scripts in the extras/providers/ folder. Example: echo…
Jun 2026 · github.com · its alternatives →
- 20
GitHub: https://www.github.com/fizzbee-io/FizzBee Traditionally, formal methods are used only for highly mission critical systems to validate the software will work as expected before it's built. Recently, every major cloud vendor like AWS, Azure, Mongo DB, confluent, elastic and so on use formal methods to validate their design like the replication algorithm or various protocols doesn't have a design bug. I used TLA+ for billing and usage based metering applications. However, the current formal methods solutions like TLA+, Alloy or P and so on are incredibly complex to…
2024 · fizzbee.io · its alternatives →
- 21
Python utilities for writing cross-version compatible libraries - tmkontra/compatlib
2021 · github.com · its alternatives →
- 22
A strictly typed utility library. Contribute to MathisBullinger/froebel development by creating an account on GitHub.
2022 · github.com · its alternatives →
- 23
Hey HN! After years of wrestling with Lodash's quirks and bundle size issues, I decided to build something better. SuperUtilsPlus is my attempt at creating the utility library I wish existed. What makes it different? TypeScript-first approach: Unlike Lodash's retrofitted types, I built this from the ground up with TypeScript. The type inference actually works the way you'd expect it to. Sensible defaults: Some of Lodash's decisions always bugged me. Like isObject([]) returning true - arrays aren't objects in my mental model. Or isNumber(NaN) being true when NaN literally stands for "Not a…
2025 · github.com · its alternatives →
- 24
A Pascal to LLVM compiler in Haskell . Contribute to sam46/Paskell development by creating an account on GitHub.
2020 · github.com · its alternatives →
Also compare
- Magentic – Use LLMs as simple Python functions alternatives
- LLMs can generate valid JSON 100% of the time alternatives
- Anything To JSON – a language model for structured extraction alternatives
- GPT-JSON – Structured and typehinted GPT responses in Python alternatives
- MonkeyPatch – Cheap, fast and predictable LLM functions in Python alternatives
- Python library for functional programming alternatives
Ranked by how close each launch is in meaning, then by votes. Prices were read from each product’s own site when checked and can change. Refine with your own description →