[HN Gopher] Show HN: ArchGW - An intelligent edge and service pr...
___________________________________________________________________
Show HN: ArchGW - An intelligent edge and service proxy for agents
Hey HN! This is Adil, Salman and Jose and and we're behind archgw
[1]. An intelligent proxy server designed as an edge and AI gateway
for agents - one that natively know how to handle prompts, not just
network traffic. We've made several sweeping changes so sharing the
project again. A bit of background on why we've built this
project. Building AI agent demos is easy, but to create something
production-ready there is a lot of repeat low-level plumbing work
that everyone is doing. You're applying guardrails to make sure
unsafe or off-topic requests don't get through. You're clarifying
vague input so agents don't make mistakes. You're routing prompts
to the right expert agent based on context or task type. You're
writing integration code to quickly and safely add support for new
LLMs. And every time a new framework hits the market or is updated,
you're validating or re-implementing that same logic--again and
again. Putting all the low-level plumbing code in a framework gets
messy to manage, harder to update and scale. Low-level work isn't
business logic. That's why we built archgw - an intelligent proxy
server that handles prompts during ingress and egress and offers
several related capabilities from a single software service. It
lives outside your app runtime, so you can keep your business logic
clean and focus on what matters. Think of it like a service mesh,
but for AI agents. Prior to building archgw, the team spent time
building Envoy [2] at Lyft, API Gateway at AWS, specialized NLP
models at Microsoft Research and worked on safety at Meta. archgw
was born out of the belief that rule-based, single-purpose tools
that handle the work around resiliency, processing and routing
prompts should move into a dedicated infrastructure layer for
agents, but built on the battle-tested foundational of Envoy Proxy.
The intelligence in archgw comes from our fast Task-specific LLMs
[3] that can handle things like agent routing and hand off,
guardrails and preference-based intelligent LLM calling. Here are
some additional details about the open source project. archgw is
written in rust, and the request path has three main parts: *
Listener subsystem which handles downstream (ingress) and upstream
(egress) request processing. * Prompt handler subsystem. This is
where archgw makes decisions on the safety of the incoming request
via its prompt_guard hooks and identifies where to forward the
conversation to via its prompt_target primitive. * Model serving
subsystem is the interface that hosts all the lightweight LLMs
engineered in archgw and offers a framework for things like
hallucination detection of our these models We loved building this
open source project, and our belief is that this infra primitive
would help developers build faster, safer and more personalized
agents without all the manual prompt engineering and systems
integration work needed to get there. We hope to invite other
developers to use and improve Arch. Please give it a shot and leave
feedback here, or at our discord channel [4] Also here is a quick
demo of the project in action [5]. You can check out our public
docs here at [6]. Our models are also available here [7]. [1]
https://github.com/katanemo/archgw [2] https://www.envoyproxy.io/
[3] https://huggingface.co/collections/katanemo/arch-function-66...
[4] https://discord.com/channels/1292630766827737088/12926307682...
[5] https://www.youtube.com/watch?v=I4Lbhr-NNXk [6]
https://docs.archgw.com/ [7] https://huggingface.co/katanemo
Author : honorable_coder
Score : 104 points
Date : 2025-07-12 23:55 UTC (1 days ago)
(HTM) web link (github.com)
(TXT) w3m dump (github.com)
| mutant wrote:
| Huh, this is pretty dope. I tried this example
| https://github.com/katanemo/archgw/blob/main/demos/samples_p...
|
| And was pleased with what I was able to do. Thanks
| sparacha wrote:
| That's an example of what the edge component could do. Did you
| give the preference-based automatic routing a try?
| mutant wrote:
| No, but I've already put this at the top of my tinker pile.
| I'm sure I will soon
| isuckatcoding wrote:
| I'm still new to this ecosystem but is this something you'd use
| together with langchain or does it replace some use cases there?
| honorable_coder wrote:
| What's missing right now are our guides showing how well ArchGW
| integrates with existing frameworks and tools. But the core
| idea is simple: it offloads low-level responsibilities--like
| routing, safety, and observability--that frameworks like
| LangChain currently try to handle inside the app. That means
| less bloat and more clarity in your agent logic.
|
| And importantly, some things just can't be done well in a
| framework. For example, enforcing global rate limits across
| LLMs isn't realistic when each agent instance holds its own
| local state. That kind of cross-cutting concern needs to live
| in infrastructure--not in application code.
| ethan_smith wrote:
| ArchGW complements langchain rather than replacing it -
| langchain handles agent orchestration/reasoning while ArchGW
| provides the infrastructure layer for prompt processing,
| guardrails and routing across your entire system.
| honorable_coder wrote:
| This ^
| jufter wrote:
| Was going to ask how this integrates into Envoy but dug into the
| code it looks like proxywasm which must mean
| `envoy.bootstrap.wasm` ?
| honorable_coder wrote:
| We're using proxy-wasm and compiling to wasm32-wasip1, then
| mounting the .wasm binaries into Envoy as HTTP filters via
| envoy.filters.http.wasm. The line you're referring to:
|
| vm_config: runtime: "envoy.wasm.runtime.v8" code: local:
| filename: "/etc/envoy/proxy-wasm-plugins/prompt_gateway.wasm"
|
| ...is where the integration happens. There's no need to modify
| envoy.bootstrap.wasm; instead, Arch loads the WASM modules at
| runtime using standard Envoy config templating. The filters
| (prompt_gateway for ingress, and llm_gateway for egress sit in
| the request path and do things like prompt inspection, model
| routing, header rewrites, and telemetry collection.
| markanton wrote:
| Nice project but there are several dozens of "AI/LLM gateways"
| now.. all kind doing the same thing. Kong AI gateway [1] was
| maybe the first to attack the LLM traffic governance and is
| indeed far ahead in both features and adoption. Trying to
| understand the value add and differentiator here, since it's a
| problem kinda solved already.
|
| [https://github.com/Kong/kong]
| honorable_coder wrote:
| There are a few critical differences. archgw is designed as a
| data plane for agents - handling and processing ingress and
| egress (prompt) traffic to/from agents. Unlike frameworks or
| libraries, it runs as a single process that includes edge
| functionality and task-specific LLMs, tightly integrated to
| reduce latency and complexity.
|
| Second, it's about where the project is headed. Because archgw
| is built as a proxy server for agents, it's designed to support
| emerging low-level protocols like A2A and MCP in a consistent,
| unified way--so developers can focus purely on high-level agent
| logic. This borrows from the same design decision that made
| Envoy successful for microservices: offload infrastructure
| concerns to a specialized layer, and keep application code
| clean. In our next big release, you will be able to run archgw
| as a sidecar proxy for improved orchestration and observability
| of agents. Something that other projects just won't be able to
| do.
|
| Kong was designed for APIs. Envoy was built for microservices.
| Arch is built for agents.
| chatmasta wrote:
| fwiw, if I were evaluating these proxies against each other,
| I would be intrigued by the solution built by people from the
| Envoy team. Envoy is great software and I'm sure there are
| many lessons you took from building it.
|
| It looks like you're even building on Envoy as the foundation
| for the system which just makes it more compelling.
| honorable_coder wrote:
| Its a core dependency for rate limiting, traffic shaping,
| fail over detection. Its cluster subsystem is super
| convenient for local LLM calls too. We'll write up a blog
| on the lessons because there were many. For example, for
| intelligent routing decisions we can't create an upstream
| connection to a cluster based on route paths or host -
| Envoy forces a more static binding. This doesn't work when
| you are making decisions about a prompt and have to inject
| more dynamic flow control.
| fosk wrote:
| MCP is simply an API protocol, like GraphQL or gRPC.
|
| And since everything is an API, Kong also supports MCP
| natively (among many other protocols, including all LLMs):
| https://konghq.com/blog/product-releases/securing-
| observing-...
| honorable_coder wrote:
| MCP implementation is trivial - I agree. But A2A will
| require a mesh like structure. Meaning its not just about
| north/south traffic. It will be about east/west traffic as
| agents coordinate with each other. That communication and
| coordination among agents will need to be robust and that's
| where a sidecar proxy built on top of Envoy will offer
| certain properties in a first-class way that Kong can't
| easily support today.
|
| This was the insight behind Envoy's initial design. Handle
| north/south and east/west traffic equally well as a
| universal data plane.
___________________________________________________________________
(page generated 2025-07-14 23:02 UTC)