Cased – protect any command line tool in minutes
We’re shipping an execution model that sits between LLM code generation and autonomous agents. The LLM generates only the glue logic between two deterministic interfaces: - a UI schema the frontend knows how to render - a constrained runtime interface exposed by the backend, from specific functions like list_comments to broader primitives like a restricted http_call Both interfaces are fixed, typed, and inspectable. The LLM can’t invent UI components or backend capabilities. It only composes what already exists. This is adjacent to A2UI, but the cut is different. A2UI renders agent actions…
Cased – protect any command line tool in minutes launched on February 9, 2021 with 5 votes and more than 50% of that year's launches. The site was still online in September 2026, 5 years on.
What it does
Identify and fix problems faster than ever, improving MTTR and reducing downtime. Connect data from any source to Cased and get visualizations and insights. Every deploy is different. Cased analyzes each deploy and monitors for anomalies, new bugs, and performance issues. Create and trigger custom agents to automate routine tasks and busy work. Dozens of integrations with the tools your team is familiar with. Now with superpowers. See how Cased can help your team ship code to production faster, safer, and smarter. Streamlined GitHub PR automation for modern AI applications in Typescript. Easy, Pythonic API for managing GitHub Pull Requests, used by Cased extensively. A highly configurable…from cased.com
In the maker’s words, at launch
We’re shipping an execution model that sits between LLM code generation and autonomous agents. The LLM generates only the glue logic between two deterministic interfaces: - a UI schema the frontend knows how to render - a constrained runtime interface exposed by the backend, from specific functions like list_comments…
Does a similar job
all alternatives →
OpenUIMar 2026 · openui.com · ▲322Thesys just open-sourced their generative UI rendering engine. Interesting timing given where Google a2ui and Vercel's json-render are headed. The difference worth noting: a2ui and json-render both treat JSONL as the contract between the LLM and the renderer. Thesys is betting that's the wrong primitive. Their engine uses a code-like syntax (OpenUI Lang) instead — LLM writes it, renderer executes it. The argument is that LLMs are fundamentally better at generating code than generating structured data, so you get cleaner output and ~67% fewer tokens. The broader vision seems to be a…
Why write code if the LLM can just do the thing? (web app experiment)Nov 2025 · github.com · ▲436I 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…
Agents.json – OpenAPI Specification for LLMs2025 · github.com · ▲212Hey HN, we’re building an open specification that lets agents discover and invoke APIs with natural language, built on the OpenAPI standard. agents.json clearly defines the contract between LLMs and API as a standard that's open, observable, and replicable. Here’s a walkthrough of how it works: https://youtu.be/kby2Wdt2Dtk?si=59xGCDy48Zzwr7ND. There’s 2 parts to this: 1. An agents.json file describes how to link API calls together into outcome-based tools for LLMs. This file sits alongside an OpenAPI file. 2. The agents.json SDK loads agents.json files as tools for an LLM that…
Code ModeNov 2025 · github.com · ▲144I’ve been testing a simple idea inspired by Apple/Cloudflare/Anthropic: LLMs are far better at writing a small program than coordinating multiple tool calls. So instead of giving the model 10+ tools, I exposed one: a TypeScript sandbox with access to the same interfaces. The model writes a script → it runs once → done. What changed - +68% reduction in token use - No multi-step drift or retries - Local models (Llama 3.1 8B / Phi-3) became much more reliable Repo: https://github.com/universal-tool-calling-protocol/code-mode Curious whether others have seen…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 21d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 30d ago · world.pixverse.video
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, February 2021
the whole month →- RS
Life & fun · 2021 · justine.lol
Contribute to DidierRLopes/GamestonkTerminal development by creating an account on GitHub.
Dev tools · 2021 · github.com
Contra▲798Connect with next-gen talent and tools to get work underway. Hire more independents. Start more projects. Get more creative.
Commerce · 2021 · contra.com
