Concierge - Framework for Building Agentic Web Interfaces
Hey HN, We’re building Concierge, An open source framework that allows you to build Agentic Applications, letting LLMs navigate, interact, and transact with your service It's a declarative framework which makes it easy for you to create Microservices for AI agents. You can expose your existing web offerings to LLMs. To support navigation you can use several abstractions like Stages, Tasks, Workflows and more. These specify the rules and guiding principles of how an Agent interacts with the service. It's especially useful when you want to expose complex business logic with thousands of APIs,…
In plain words
Concierge is an open-source framework for building applications that allow large language models to navigate, interact with, and conduct transactions on web services. It uses a declarative approach with abstractions like Stages, Tasks, and Workflows to define how AI agents should interact with complex business logic and APIs. The framework is designed for developers who need to expose existing web services to LLMs with clear rules and guiding principles governing agent behavior.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hey HN, We’re building Concierge, An open source framework that allows you to build Agentic Applications, letting LLMs navigate, interact, and transact with your service It's a declarative framework which makes it easy for you to create Microservices for AI agents. You can expose your existing web offerings to LLMs. To support navigation you can use several abstractions like Stages, Tasks, Workflows and more. These specify the rules and guiding principles of how an Agent interacts with the service. It's especially useful when you want to expose complex business logic with thousands of APIs, and want to provide context on how these can be used/called. For example building an Amazon for agents. With Concierge, you can several rules or "guiding principles" on how you want an Agent to interact with your service. We are calling this new concept as Agentic Web Interfaces, would love to know what you think! You can find the repository here: https://github.com/Agentic-Web-Interfaces/concierge Some features we are excited about: 1. UI Dashboard to track costs, top business services, usage and analytics. 2. Replay ability to allow you to track and debug user sessions. 3. Ability to self-host or use our managed hosting.
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, November 2025
the whole month →
- IB
Life & fun · Nov 2025 · bitsnpieces.dev
- BBoing▲782
Life & fun · Nov 2025 · boing.greg.technology