Zero-dependency, TypeScript SDK for building robust NLP applications
Hey HN! We just released a new library for building LLM-powered applications: @axflow/models. It is part of a larger suite of libraries we're developing for TypeScript developers working with generative AI. This library provides the simplest APIs for 1) invoking the most popular LLM and embedding models (openai, anthropic, cohere, huggingface, etc.) 2) streaming LLM responses to clients, including augmenting the streams with additional arbitrary data and 3) building client-side applications with React hooks. @axflow/models has zero dependencies and is built using only the…
Zero-dependency, TypeScript SDK for building robust NLP applications launched on September 19, 2023 with 16 votes, #1,418 of 4,228 launches that month and more than 75% of that year's launches. The site was still online in September 2026, 3 years on.
In plain words
Axflow/models is a TypeScript SDK for building applications with large language models and embeddings. It provides APIs for invoking models from OpenAI, Anthropic, Cohere, and Hugging Face, streaming responses to clients, and building React applications. Built with zero external dependencies using only JavaScript standard library, it runs in any environment including edge runtimes like Next.js. The library is designed for TypeScript developers working with generative AI applications.
written from the facts on this page · September 2026
From the sources
The TypeScript framework for AI development
Zero-dependency, modular SDK for building robust natural language applications. For models that support streaming, there is a convenience method for streaming only the string tokens. We've made building chat and completion UIs trivial. It doesn't get any easier than this 🚀 Sometimes you just want to create a proxy to the underlying LLM API. In this example, the server intercepts the request on the edge, adds the proper API key, and forwards the byte stream back to the client. Note this pattern works exactly the same with our other models that support streaming, like Cohere and Anthropic. On the client, we can use OpenAIChat.stream with a custom apiUrl in place of the apiKey that points to…from docs.axflow.dev
In the maker’s words, at launch
Hey HN! We just released a new library for building LLM-powered applications: @axflow/models. It is part of a larger suite of libraries we're developing for TypeScript developers working with generative AI. This library provides the simplest APIs for 1) invoking the most popular LLM and embedding models (openai…
Does a similar job
all alternatives →
Axilla – Open-source TypeScript framework for LLM apps2023 · github.com · ▲161Hi HN, we are Nick and Ben, creators of Axilla - an open source TypeScript framework to develop LLM applications. It’s in the early stages but you can use it today: we’ve already published 2 modules and have more coming soon. Ben and I met while working at Cruise on the ML platform for self-driving cars. We spent many years there and learned the hard way that shipping AI is not quite the same as shipping regular code. There are many parts of the ML lifecycle, e.g., mining, processing, and labeling data and training, evaluating, and deploying models. Although none of them are rocket science,…
Mastra 1.0Jan 2026 · github.com · ▲451Hi HN, we’re Sam, Shane, and Abhi, and we’re building Mastra (https://mastra.ai), an open-source JavaScript SDK for building agents on top of Vercel’s AI SDK. You can start a Mastra project with `npm create mastra` and create workflow graphs that can suspend/resume, build a RAG pipeline and write evals, give agents memory, create multi-agent workflows, and view it all in a local playground. Previously, we built Gatsby, the open-source React web framework. Later, we worked on an AI-powered CRM but it felt like we were having to roll all the AI bits (agentic workflows, evals,…
Building an LLM from Scratch in TypeScript8d ago · book.humanexperiences.io · ▲33The from-scratch guide to building large language models in NodeJS.
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…
Nous – Open-Source Agent Framework with Autonomous, SWE Agents, WebUI2024 · github.com · ▲155Hello HN! The day has finally come to stop adding features and start sharing what I've been building the last 5-6 months. It's a bit of CrewAI, OpenDevon, LangFuse/Cloud all in one, providing devs who prefer TypeScript an integrated framework thats provides a lot out of the box to start experimenting and building agents with. It started after peeking at the LangChain docs a few times and never liking the example code. I began experimenting with automating a simple Jira request from the engineering team to add an index to one of our Google Spanner databases (for context I'm the…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 29d ago · world.pixverse.video
Source: Show HN post ↗ · launch text quoted in part
