Alternatives
Products that do what RΞASON – Open-source TypeScript framework for LLM apps does
Hi HN! RΞASON is an OSS Typescript framework for developing LLM apps that uses Typescript's interfaces to get structured output from an LLM. While there are other TS LLM frameworks, I think RΞASON fills a unique space in the market: it's laser-focused on only three areas and, most importantly, actively stays away from pre-made prompting & retrieval. I've been in the LLM space since GPT-3 originally came out, and I've always had problems with other frameworks, such as LangChain. I dislike that they focus a ton on out-of-the-box prompting & pre-made agents — I, as the dev, should be the one in…
- 1NO
Hello 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…
2024 · github.com
- 2
- 3
- 4AT
2019 · blog.hediet.de
- 5OA
Thesys 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…
Mar 2026 · openui.com
- 6ET
We built a browser extension (Chrome + Firefox) that captures the runtime DOM and exports it as JSON. Not the pre-render source (HTML/CSS/JS, templates, bundles) and not a screenshot — but the live, post-render state the browser is actually displaying: - visibility/hidden, disabled/required - current input values and validation/validationMessage - dataset attributes - trimmed text - stable selector paths Why: LLMs often miss or guess UI state. Screenshots are too opaque, pre-render source is too noisy. A structured snapshot gives reproducible context for debugging…
2025
- 7OS
Hi HN, we’re Dylan and Matthew, building sublingual (https://github.com/sublingual-ai/sublingual), an open-source LLM observability tool you can use with zero code changes. As developers focused on iterating and building features as fast as possible, we felt observability would’ve been a helpful tool to have, but we found existing solutions had too much overhead to set up. So we gave ourselves the challenge of building an observability tool that you can integrate without changing a single line of code in your project. How it works Run your python application as usual with…
2025 · github.com
- 8MG
Anthropic released the Model Context Protocol a couple weeks ago - https://www.anthropic.com/news/model-context-protocol. They have official sdks for python and typescript but nothing for go, so I wrote one! The main goal is to provide a low boilerplate sdk to write MCP servers, you can spin up a server which can give an LLM access to weather forecasts like this: https://github.com/metoro-io/mcp-golang/blob/main/examples/g... . Using it here: https://youtu.be/xaMkMl_R-0A The library handles generating all the MCP…
2024 · github.com
- 9CL
I tried to port LLMLingua-2's official Python implementation into TypeScript. For best performance, open the URL with a WebGPU enabled web browser. Learn More: https://github.com/atjsh/llmlingua-2-js
2025 · atjsh.github.io
- 10CT
I've spent the past few months building a language that is 99% compatible with CoffeeScript and 99% compatible with TypeScript. Essentially a reimagined CoffeeScript for 2022 that finished ES6s partially completed features, adds TypeScript support, and keeps the niceties of CoffeeScript. Example features: - Const assignment shorthand user := getUser() --- const user = getUser() - Parens optional and braceless nesting if x > 0 return --- if (x > 0) { return } - &fn shorthand nums.map &+1 --- nums.map($=>$+1) And a heck-ton more: https://github.com/DanielXMoore/Civet A big…
2022
- 11AL
Hi HN, I build this a few months back, thinking about improving it but wanted to share as is first to see what feedback I can get. I built it to be modular and with a clean understandable codebase in mind so easily extendable. I want to add more components to it maybe... Thanks! Will add link to the repo in a comment now
2022
- 12LO
Hey HN, Ola and Karthik here. We are working on Langtrace(https://github.com/Scale3-Labs/langtrace), an open source, open telemetry based SDK and monitoring/evaluations client for LLM based applications. The SDK generates OTEL standard spans and traces for popular LLMs like OpenAI, Anthropic and Cohere, popular frameworks like Langchain and LlamaIndex and vectorDBs like ChromaDB and Pinecone. The LLM monitoring/evaluations space has seen a number of products off late, both open source and closed source ones. But, a couple of things we have observed are: lack of…
2024
- 13AA
We've rolled out a feature for openbase.com that we think is a DX game changer for Node devs. Since the emergence of ECMA Script modules, it's been a continuous guessing game as to what kind of exports a package has. That's never really been discoverable without using a site like unpkg, or installing the package and inspecting package.json. Openbase now displays the ES Module support level (e.g. type of exports) on all of their package pages. We added this feature because our devs are some of the folks continually caught off guard by installing an NPM dependency only to find out it's…
2022
- 14LM
This app is demonstrating how to support rich-text (markdown) in LLM responses (OpenAI in this case). It's a Nextjs app, with Vercel AI, and remark for handling the formatting.
2023 · llm-markdown.vercel.app
- 15EL
Hey HN! I built Experiment to solve a common frustration in LLM development: the lack of proper tools for prompt engineering experimentation. Here's what makes it different: Key Features: - Load and edit chat completion logs from CSV files - Fork and modify specific conversation entries - Run inference via Anthropic, Mistral, and OpenAI - Define custom tools using JSONSchema format - Visual tool usage analysis with collapsible, sorted key-value pairs - Full mobile support and available as installable PWA Technical Highlights: - Built with React using custom isomorphic architecture -…
2025 · github.com
- 16AL
Hi HN, This is Andrei from askmanu and I'm super happy to share a new framework I've been working on: acorn. It takes all the best parts of DSPy, langchaing, instructor, etc and wraps it in a beautiful and easy to use API. Very easy to define model I/O, branches, define callbacks for every step, etc See the getting started docs here: https://github.com/askmanu/acorn/blob/main/docs/getting-star... Try out the different demos here: https://huggingface.co/spaces/askmanu/acorn
Feb 2026 · github.com
- 17LO
Hey HN! I built Lumina – an open-source observability platform for AI/LLM applications. Self-host it in 5 minutes with Docker Compose, all features included. The Problem: I've been building LLM apps for the past year, and I kept running into the same issues: - LLM responses would randomly change after prompt tweaks, breaking things - Costs would spike unexpectedly (turns out a bug was hitting GPT-4 instead of 3.5) - No easy way to compare "before vs after" when testing prompt changes - Existing tools were either too expensive or missing features in free tiers What I Built: Lumina is…
Jan 2026 · github.com
- 18GA
GrainJS is a JavaScript / TypeScript library for building dynamic web applications. - It's in part inspired by React, but based on observables (like Knockout) instead of virtual dom. - It is lightweight, has no dependencies, and takes only ~30KB minified. - It needs no special tooling. It's nothing more than a library. - It supports convenient DOM-building in JS, event dispatching, DOM event subscriptions, 9disposable components, and in-code CSS styling. - It's fully typed for use with TypeScript. - It's proven its worth by powering Grist's rich frontend app. Source code:…
Dec 2025 · gristlabs.github.io
- 19IB
After fine-tuning GPT for a personal project, I realized how tedious it is to write plain text in a massive JSON file. That's why I built this app for my own use, and I want to see if others could benefit from a tool like this as well ;)
2024 · finetuna-ui.com
- 20ER
I built a MCP server using the Typescript SDK that wraps around the JSON RPC methods for EVM Blockchains. Without any extra documentation the LLM is able to interact with the EVM blockchain even through a complex series of requests. To get going, just add the following command to your MCP client of choice (e.g. Cursor) - npx -y ethereum-rpc-mpc [Optional: RPC_URL] It works out of the box with any EVM chain. Example usage with Claude: "What's the ETH balance of 0x742d35Cc6634C0532925a3b844Bc454e4438f44e?" "Is 0x6B175474E89094C44Da98b954EedeAC495271d0F a smart contract?" "Is…
2025 · github.com
- 21AF
Hi HN! My name is Salman Paracha. I aam the the Founder/CEO of Katanemo - the organization behind the open source Arch GW (an intelligent gateway for prompts - https://github.com/katanemo/arch). Today, we are making the (SOTA) LLMs engineered in Arch GW for function calling scenarios available under an OSS license that borrows from Llama's community license. What is function calling? Function calling helps developers personalize apps by calling application-specific operations via user prompts. This involves any predefined functions or APIs you want to expose to…
2024 · huggingface.co
- 22
Stop wasting money on JSON. Save 50%+ tokens on your LLMs
18d ago · zeon-eight.vercel.app
Ranked by how close each launch is in meaning, then by votes. Refine with a description →