Arch

Build fast, specialized agents with intelligent infra

302 followers

Build fast, specialized agents with intelligent infra

302 followers

Visit website

LLMs

•

AI Infrastructure Tools

•

Observability tools

Arch is an intelligent gateway for agents. An AI-native, open source infrastructure project to help developers build fast, hyper-personalized agents in mins. Arch is engineered with specialized (fast) LLMs to transparently integrate prompts with APIs (function calling), to add safety, routing and observability features in secs - so that developers can focus on what matters most.

Free

Launch tags:Open Source•Developer Tools•Artificial Intelligence

Launch Team / Built With

Render Sandboxes: a computer for every agentRun untrusted code safely. Idle sandboxes cost nothing

Promoted

Plano

Maker

📌

Hello PH! My name is Salman and I work on Arch - an open source infrastructure primitive to help developers build fast, personalized agent in minus. Arch is an intelligent prompt gateway engineered with (fast) LLMs for the secure handling, robust observability, and seamless integration of prompts with your APIs - all outside business logic. Arch is built on (and by the contributors of) Envoy 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. 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 of prompts and LLM interactions in a centralized way. ⭐ Core Features: 🏗️ Built on Envoy: Arch runs alongside application servers, and builds on top of Envoy's proven HTTP management and scalability features to handle ingress and egress traffic related to prompts and LLMs. 🤖 Function Calling: For fast agentic and RAG apps. Engineered with SOTA.LLMs to handle fast, cost-effective, and accurate prompt-based tasks like function calling, and parameter extraction from prompts. Our models can run under <200 ms!! 🛡️ Prompt Guard: Arch centralizes prompt guards to prevent jailbreak attempts and ensure safe user interactions without writing a single line of code. 🚦 Traffic Management: Arch manages LLM calls, offering smart retries, automatic cut over, and resilient upstream connections for continuous availability between LLMs or a single LLM provider with multiple versions 👀 OpenTelemetry Tracing, Metrics and Logs : Arch uses the W3C Trace Context standard to enable complete request tracing across applications, ensuring compatibility with exiting observability tools, and provides metrics to monitor latency, token usage, and error rates, helping optimize AI application performance. - Visit our Github page to get started (and ⭐️ the project 🙏) : https://github.com/katanemo/arch - To learn more about Arch our docs: https://docs.archgw.com/ A big thanks 🙏 to my incredibly talented team who helped us to our first milestone as we re:invent infrastructure primitives for Generative AI.

Report

2yr ago

Plano

Maker

@alex_tartach Thanks Alex - building this was a lot of fun, and its early days for us. Packing intelligence in infrastructure to help developers build fast agents (faster than before) is the ultimate goal

Report

2yr ago

Impressive work - At Meta we have the same core belief that safety of agents is paramount and as much as possible if we can tackle those concerns early in the request path the better - Arch feels like a great fit for responsible and safe AI - not to mention the other super powers it offers developers. One quick question: can you elaborate more about the prompt guard model, I see that you guys fined tuned it over the prompt guard from Meta?"

Report

2yr ago

Plano

Maker

@sarmad_siddiqui Thank you! Yes, Arch uses purpose-built LLMs for guardrails The Arch-Guard collection of models can be found here. https://huggingface.co/collectio.... We fine-tuned over Meta's prompt guard and the optimization was to improve TPR (+4%) without impacting FPR. This was for the jailbreak use case, and the next set of baseline guardrails will include toxicity, harmfulness, etc.

Report

2yr ago

@salman_paracha awesome I know my holiday season plans now!!!!

Report

2yr ago

Opengeni

What's a personalised agent? Web chatbot or personal assistant or? This field is moving so fast, it's hard to know what terms means these days. Thanks 🙏

Report

2yr ago

Plano

Maker

@sentry_co personalized means to customize the agent to be unique. Most agents are just summarizing over some data. With Arch you can build something very tailored like creating ad campaigns via prompts or updating insurance claims - and offer generative summaries in the same experience

Report

2yr ago

LastMile AI

Congrats on the launch! Really great project -- I believe in the premise of a gateway that consolidates a lot of the infrastructure work needed for any LLM project.

Report

2yr ago

Plano

Maker

@saqadri Thanks Sarmad - really appreciate you taking the time to dig deeper on the project, and believing in the premise

Report

2yr ago

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.

Report

2yr ago

Plano

Maker

@junr03 Deeply appreciate your help and support. You are a critical part of our journey and couldn't have built this without you Jose!

Report

2yr ago

Arch

Maker

@junr03 thanks Jose

Report

2yr ago

Arch

Maker

Hello! My name is Adil Hafeez, and I am the Co-Founder at Katanemo and the lead developer behind Arch. Previously I worked on Envoy at Lyft. Arch is engineered with purpose-built LLMs, it 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 of prompts and LLM interactions in a centralized way - all outside business logic. Here are some additional key details of the project, * Built on top of Envoy and is written in rust. It runs alongside application servers, and uses Envoy's proven HTTP management and scalability features to handle traffic related to prompts and LLMs. * Function calling for fast agentic and RAG apps. Engineered with purpose-built fast LLMs to handle fast, cost-effective, and accurate prompt-based tasks like function/API calling, and parameter extraction from prompts. * Prompt guardrails to prevent jailbreak attempts and ensure safe user interactions without writing a single line of code. * Manages LLM calls, offering smart retries, automatic cutover, and resilient upstream connections for continuous availability. * Uses the W3C Trace Context standard to enable complete request tracing across applications, ensuring compatibility with observability tools, and provides metrics to monitor latency, token usage, and error rates, helping optimize AI application performance. We love arch, love open source and would love to build alongside the community. Please leave a comment or feedback here and I will be happy to answer!

Report

2yr ago

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!

Report

2yr ago

Plano

Maker

@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

Report

2yr ago

1 2 3

Reviews