Keryx
The Fullstack TypeScript Framework for MCP and APIs
What it does
Keryx is a TypeScript framework built on Bun where one action class is your HTTP endpoint, your WebSocket handler, your CLI command, your background task, and your MCP tool. Same logic, validation, middleware, and response type. MCP and OAuth 2.1 are built in.
Does a similar job
all alternatives →


- DCDeco.cx – realtime TypeScript web editor2024 · deco.cx · ▲98
Hi, HN. Gui, Lucis, and the deco.cx team here — we're a bunch of Brazilians building an open-source, all-in-one web editor for the modern TypeScript dev. Check out our GitHub at https://github.com/deco-cx/deco and discover more at our site https://deco.cx/. We built frontend tools at a hyper-growth e-commerce platform for 9 years. Deco.cx is the thing that we wish existed when we were managing hundreds of enterprise-grade React-based websites. The gist is: JSX, HTMX, TypeScript, Tailwind and Deno. All visually editable in a beautiful, collaborative,…
- CACrust – A CLI framework for TypeScript and BunMar 2026 · github.com · ▲95
We've been building Crust (https://crustjs.com/), a TypeScript-first, Bun-native CLI framework with zero dependencies. It's been powering our core product internally for a while, and we're now open-sourcing it. The problem we kept running into: existing CLI frameworks in the JS ecosystem are either minimal arg parsers where you wire everything yourself, or heavyweight frameworks with large dependency trees and Node-era assumptions. We wanted something in between. What Crust does differently: - Full type inference from definitions — args and flags are inferred automatically. No…
- IBI built an MCP server using Cloudflare's code mode patternSep 2025 · github.com · ▲87
Read this article by Cloudflare this morning https://blog.cloudflare.com/code-mode/ the main argument being that LLMs are much better at writing typescript code than tool calls because they've seen typescript code many more times. HN Discussion: https://news.ycombinator.com/item?id=45399204 https://news.ycombinator.com/item?id=45386248 Deno provides a great sandbox environment for Typescript code execution because of its permissions system which made it easy to spin up code that only has access to fetch and network calls. Stick an MCP proxy…
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 · 18d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 19d 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 · 27d ago · cactuscompute.com


Launched alongside, May 2026
the whole month →

Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai


- NW
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
- FM
Dev tools · May 2026 · github.com