Kevin William David

Arch - Build fast, hyper-personalized agents with intelligent infra

by•
Arch is an intelligent infrastructure primitive to help developers build fast, personalized agents in mins. Arch is a gateway engineered with LLMs to seamlessly integrate prompts with APIs, and to transparently add safety and tracing features outside app logic

Add a comment

Replies

Best
José Ulises Niño Rivera
Hi I am Jose, current owner of Pukka Built. I contracted with Katanemo to help the team get Arch off the ground. It was great to bootstrap Arch alongside Adil and Salman as they get to launch it for developers and platform teams. As someone who built Envoy at Lyft, I can attest to the durability of Envoy as a design choice. For those who need efficient, reliable handling of LLM requests, Arch is a strong addition to the stack. For the same reasons the out of process architecture for Envoy was a solid design choice, Arch benefits as well: giving teams more control over how prompts are managed without impacting existing services.
Salman Paracha
@junr03 Deeply appreciate your help and support. You are a critical part of our journey and couldn't have built this without you Jose!
Adil Hafeez
@junr03 thanks Jose
Huzaifa Shoukat
Congrats on the launch! Love the speed and ease Arch brings to building personalized agents. Quick question: How does Arch handle data privacy and security?
Salman Paracha
@ihuzaifashoukat We engineered small LLMs that are exceptional for specific tasks around safety. For example, the Arch-Guard model (86M) offers state-of-the-art (SOTA) peformance for jailbreak scenarios.
Jai from Worksaga
Congratulations to the team on the launch of Arch! This tool sounds exciting for developers. Building fast, personalized agents in minutes is impressive
Salman Paracha
@jai_singhal Deeply appreciate the kind words. Would love for you to try it out and offer feedback!
Simon Peter Damian
Congrats on your launch 🚀🚀🚀 --- Arch seems cool and promising. I haven't tried it out yet, but I do have a few questions. Langchain currently dominates this space, I see your pitch, but Arch doesn't seem to fit in the toolbox for users new to building GenAI apps. It does have its benefits for prompt-heavy applications, but I don't see the appeal for users new to building GenAI apps except that these folks aren't your target audience.
Salman Paracha
@theterminalguy Simon thanks for the question. Langchain and Arch are better together - for all the business logic around agents like chunking data, chaining calls to LLMs before returning a final response Langchain will continue to offer developers the fine-grained control over the business logic of agents. Arch handles all the crufty work that can be transparently managed outside business logic like guardrails, end-to-end tracing, and being able to route calls to APIs based on the true intent of the user prompt in under 300 ms - Arch is uniquely intelligent, distributed and out of process giving time back to developers to think about their differentiation.
Simon Peter Damian
@salman_paracha thanks for explanation. I'll give it a try this weekend
Michael van Dijken
This is a cool project and great to see it come to fruition. We are working on a GenAI-based tool that will involve a front-end of sorts (lets call it an agent), and likely leverage several LLMs on the back-end - depending on the type of request. Is this a good use case for Arch and if so, I'd love to get my team engaged here. Thanks @salman_paracha and team!
Salman Paracha
@michael_pmm_nerd that's exactly one of the core use cases for Arch. Would love to show the team how we can help them move faster with Arch
Munna Aziz
Congrats, Salman and the Arch team! 🎉 Arch sounds like a powerful solution for making prompt management and observability in AI-driven applications much more efficient. Love the focus on secure handling, robust traffic management, and fast function calling—perfect for anyone scaling agent-based and RAG apps.
Sheharyar Mehmood
Great work guys. Congrats on launching this.
Naveed Zafar
Cool demo. Looks very promising and I'd love to give it a try over the weekend. Congratulations on the launch folks 🚀🚀
Mari Bu
Wow grate job! I like it! Could we modeling agent based models on it?