AI · alternatives · 2026

24 alternatives to Arch-Function: 3B parameter LLM that beats GPT-4o on function calling

Hi HN! My name is Salman Paracha. I aam the the Founder/CEO of Katanemo - the organization behind the open source Arch GW (an intelligent gateway for prompts - https://github.com/katanemo/arch). Today, we are making the (SOTA) LLMs engineered in Arch GW for function calling scenarios available under an OSS license that borrows from Llama's community license. What is function calling? Function calling helps developers personalize apps by calling application-specific operations via user prompts. This involves any predefined functions or APIs you want to expose to…

Below are 24 products that do a similar job, ranked by how close each is in meaning and then by launch-day votes. Prices are shown for the 1 we have checked on their own sites, 1 of them free or with a free tier. Arch-Function: 3B parameter LLM that beats GPT-4o on function calling launched in 2024; newer entries below may have overtaken it.

1
Arch▲314
Hey HN — I’m Adil from Katanemo (with Salman, Shuguang, and Meiyu) We previously shared an early version of this project as ArchGW. Based on customer feedback, the scope expanded from “LLM routing and model access” into something broader: delivery infrastructure for agentic applications. We renamed it to Plano and reworked the architecture accordingly. The problem On-the-ground AI practitioners will tell you that calling an LLM is not the hard part. The really hard part is delivering agentic applications to production quickly and reliably, then iterating without rewriting system code every…
2024 · github.com · its alternatives →
2
Arch-Router – 1.5B model for LLM routing by preferences, not benchmarks▲66
Hi HN — we're the team behind Arch (https://github.com/katanemo/archgw), an open-source proxy for LLMs written in Rust. Today we're releasing Arch-Router (https://huggingface.co/katanemo/Arch-Router-1.5B), a 1.5B router model for preference-based routing, now integrated into the proxy. As teams integrate multiple LLMs - each with different strengths, styles, or cost/latency profiles — routing the right prompt to the right model becomes a critical part of the application design. But it's still an open problem. Most routing systems fall into two…
2025 · its alternatives →
3
TensorZero▲307
Hi HN! We're Gabriel & Viraj, and we're excited to open source TensorZero. To be a little cheeky, TensorZero is an open-source platform that helps LLM applications graduate from API wrappers into defensible AI products. 1. Integrate our model gateway 2. Send metrics or feedback 3. Unlock compounding improvements in quality, cost, and latency It enables a data & learning flywheel for LLMs by unifying: • Inference: one API for all LLMs, with <1ms P99 overhead • Observability: inference & feedback → your database • Optimization: better prompts, models, inference strategies • Experimentation:…
2025 · github.com · its alternatives →
4
Arch – an intelligent prompt gateway built on Envoy▲31
Hi HN! My name is Adil Hafeez, and I am the Co-Founder at Katanemo and the lead developer behind Arch - an open source project for developers to build faster, generative AI apps. Previously I worked on Envoy at Lyft. Engineered with purpose-built LLMs, Arch handles the critical but undifferentiated tasks related to the handling and processing of prompts, including detecting and rejecting jailbreak attempts, intelligently calling “backend” APIs to fulfill the user’s request represented in a prompt, routing to and offering disaster recovery between upstream LLMs, and managing the observability…
2024 · github.com · its alternatives →
5
Symphony – Use GPT-4 to call functions in sequence▲93
Hey HN! I'm excited to introduce Symphony – a toolkit designed to help developers write functions and let GPT-4 call them in whatever sequence that makes most sense based on conversation. I've been quite amazed[1] by GPT-4's recent ability to both detect when a function needs to be called and to respond with JSON that adheres to the function's signature. Since developers currently append descriptions of functions to API calls[2], I often found myself wishing for a toolkit that would automatically create these descriptions as I added and debugged functions during development. You can get…
2023 · symphony.run · its alternatives →
6
Why write code if the LLM can just do the thing? (web app experiment)▲436
I spent a few hours last weekend testing whether AI can replace code by executing directly. Built a contact manager where every HTTP request goes to an LLM with three tools: database (SQLite), webResponse (HTML/JSON/JS), and updateMemory (feedback). No routes, no controllers, no business logic. The AI designs schemas on first request, generates UIs from paths alone, and evolves based on natural language feedback. It works—forms submit, data persists, APIs return JSON—but it's catastrophically slow (30-60s per request), absurdly expensive ($0.05/request), and has zero UI…
Nov 2025 · github.com · its alternatives →
7RY
Route your prompts to the best LLM▲298
Hey HN, we've just finished building a dynamic router for LLMs, which takes each prompt and sends it to the most appropriate model and provider. We'd love to know what you think! Here is a quick(ish) screen-recroding explaining how it works: https://youtu.be/ZpY6SIkBosE Best results when training a custom router on your own prompt data: https://youtu.be/9JYqNbIEac0 The router balances user preferences for quality, speed and cost. The end result is higher quality and faster LLM responses at lower cost. The quality for each candidate LLM is predicted ahead of time…
2024 · unify.ai · its alternatives →
8
Magentic – Use LLMs as simple Python functions▲283
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 →
9
Arch – an intelligent prompt gateway built on Envoy▲21
Hi HN! My name is Adil Hafeez, and I am the Co-Founder at Katanemo and the lead developer behind Arch - an open source project for developers to build faster, generative AI apps. Previously I worked on Envoy at Lyft. Engineered with purpose-built LLMs, Arch handles the critical but undifferentiated tasks related to the handling and processing of prompts, including detecting and rejecting jailbreak attempts, intelligently calling “backend” APIs to fulfill the user’s request represented in a prompt, routing to and offering disaster recovery between upstream LLMs, and managing the observability…
2024 · github.com · its alternatives →
10
LLM Gatewayfree tier▲296
I built an OpenAI-compatible LLM gateway that routes requests to OpenAI, Anthropic, Ollama, vLLM, llama-server, SGLang... anything that speaks /v1/chat/completions. Single Go binary, one YAML config file, no infrastructure. It does the things you'd expect from this kind of gateway... semantic routing via a three-layer cascade (keyword heuristics, embedding similarity, LLM classifier) that picks the best model when clients omit the model field, weighted round-robin load balancing across local inference servers with health checks and failover. The part I think is most…
2025 · llmgateway.io · its alternatives →
11
DigitalOcean Functions▲250
Run functions on demand, scale automatically
2022 · digitalocean.com · its alternatives →
12
lambdaprompt – build, compose and call templated LLM prompts▲9
For the past few months I've been building a lot of things with LLMs (GPT-3, Codex, etc.) as I've been trying to push them to their limits (especially towards applying them to the tabular data domain) When working on this, I've found there are some common patterns for solving problems (templating, chaining, functional-programming style operations, etc.) As I've iterated, I've come to believe that a functional style interface is likely going to power a new wave of systems I'm calling "prompt-machines"(systems where the core new unit of work is a "named" LLM prompt, extending the "function"…
2022 · github.com · its alternatives →
13
Fructose – LLM calls as strongly typed functions▲218
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…
2024 · github.com · its alternatives →
14AG
Arch GW – Distributed gateway for agents, engineered with small LLMs▲7
Hi HN My name is Salman and I work on Arch GW - the intelligent gateway designed to protect, observe, and personalize LLM applications with your APIs. https://github.com/katanemo/arch Our team built Envoy Proxy at Lyft, and re-imagined it with the belief that: Prompts are nuanced and opaque user requests, which require the same capabilities as traditional HTTP requests including secure handling, intelligent routing, robust observability, and integration with backend (API) systems for personalization – all outside business logic. Engineered with purpose-built LLMs, Arch…
2024 · docs.archgw.com · its alternatives →
15
Open-source real time data framework for LLM applications▲92
Hey HN, I am the founder of Tensorlake. Prototyping LLM applications have become a lot easier, building decision making LLM applications that work on constantly updating data is still very challenging in production settings. The systems engineering problems that we have seen people face are - 1. Reliably process ingested content in real time if the application is sensitive to freshness of information. 2. Being able to bring in any kind of model, and run different parts of the pipeline on GPUs and CPUs. 3. Fault Tolerance to ingestion spike, compute infrastructure failure. 4. Scaling compute,…
2024 · getindexify.ai · its alternatives →
16
Phospho – Text Analytics for LLM Apps (Posthog for Prompts)▲59
Hello HN! Pierre and Paul here. We are building an open source text analytics tool for user inputs and LLM app outputs The repo is https://github.com/phospho-app/phospho and landing is https://phospho.ai Most people building with LLMs today don’t have quantified evaluation and usage metrics on the interactions between users and their product. The only solution is to read every message (or a sample) to get a sense of what is going on. You can't improve your product without understanding who your users are and how they are using it. Nobody would launch a website…
2024 · github.com · its alternatives →
17IG
Interactive Graph by LLM (GPT-4o)▲45
Data automation and visualization platform for spreadsheet users.
2024 · columns.ai · its alternatives →
18
LLM-Term – Simple Rust-based CLI assist tool▲32
Current AI-assisted CLI tools are often part of larger systems and work better on Linux. I built llm-term to address these. It's a Rust-based tool that compiles into a single binary file. You only need to download the binary, add it to your PATH, and configure your OpenAI key to get started. While llm-term offers an option for gpt-4o, it works great with gpt-4o-mini. So it's not costly. I appreciate any feedback or suggestions.
2024 · github.com · its alternatives →
19LF
LLM Function Calling Library to Interact with File, Shell, Git and Code▲5
Hey HN, I built SWE-Kit, LLM toolkit (Function callable tools) which makes building agents specialised in coding like Devin very easy. I noticed a typical pattern while building local agents: creating & perfecting LLM tools to interact with system or codebase was the repeated and time-consuming. We created a layer that simplifies building agents that can interact with code, file system, git, shell and allows you to quickly solve for a wide variety of coding agent use cases. Aren’t there open coding agents already? Well, yes, but most folks would want to solve their specific use case like a…
2024 · swekit.dev · its alternatives →
20PF
Playground for OpenAI Function Calling▲51
Hey everyone, I'm Petr. I'm excited to share LangTale Playground (https://langtale.ai/playground), a first-of-its-kind tool enabling anyone to experiment with OpenAI function calls without coding. Born out of a hackathon project, it's now a part of our broader LangTale platform aimed at tackling common developer challenges with Language Learning Models (LLM). These include prompt integration, testing and debugging, version control, auditing, and usage/cost management. Here's our tech stack: Next.js by Vercel, Tailwind CSS, OpenAI, PlanetScale's Vitess database, and the…
2023 · langtale.ai · its alternatives →
21
Litellm – Simple library to standardize OpenAI, Cohere, Azure LLM I/O▲62
I built this library because langchain was too bloated and I needed a simple abstraction to call multiple LLM APIs. litellm has two functions - completion(), embedding()
2023 · github.com · its alternatives →
22
Superflows – open-source AI Copilot for SaaS products▲37
Henry, Matt and James here – we’re building an open source toolkit that makes it easy to integrate an LLM-powered copilot that talks to your API into software products. It works by calling API endpoints which you choose to expose to it. This lets the chatbot complete tasks within your software in response to natural language queries. It’s also open source, so you don’t have to send user data to another 3rd party. We support Llama 2, but we haven’t fine-tuned Llama 2 yet (coming soon) so highest accuracy is seen with GPT-4 or fine-tuned GPT-3.5 (much faster). We started working together 2…
2023 · github.com · its alternatives →
23
LLMWare – Small Specialized Function Calling 1B LLMs for Multi-Step RAG▲51
Hi, I was a corporate lawyer for many years working with a lot of financial services and insurance companies. In practicing law, I noticed there was a lot of repetition in the tasks I was working on even as a highly paid attorney that could be automated. I wanted to solve the problem of dealing with a lot information and data in a practical way, using AI. This motivated me to start AI Bloks/LLMWare with my husband, who had a deep background in software and is a very early adopter of AI. We have been on this journey with our open source project LLMWare for the past 4 months, producing a…
2024 · github.com · its alternatives →
24PF
Playground for OpenAI API with function calls▲12
I was frustrated that open ai's playground lacks function calls, so I wrote my own more similar to ChatGpt! Now I can: * use the same models I program against * have access to function calls * can see how much it's costing me Side benefit: I can share my API key with a friend so they can use Gpt3.5 & 4 as open ai took their deposit but still labelled their account as free tier - mistakes happen. Prerequisite: an open ai api key https://github.com/acover288/playgpt Use at your own risk as I blindly installed npm packages.
2023 · gpt342.s3.us-east-1.amazonaws.com · its alternatives →

Also compare

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 →