Search

myApi

@mateuszrusyn

An interactive, runnable TypeScript val by mateuszrusyn

Script

export function myApi(name) {

return "hi " + name;

connect4_mcts_agent

@saolsen

Connect4 agent that uses Monte-Carlo tree search to simulate 10,000 random games from each possible action and pick the one with the highest win rate. Ported from a version I made in rust. https://github.com/saolsen/connect4 https://www.steveindusteves.com/p/connect4-mcts

HTTP

const SIMULATIONS = 10000;

function rand_action(state: connect4.State): connect4.Action {

const player = state.next_player;

return action;

function score_action(

current_state: connect4.State,

return score / SIMULATIONS;

function agent(state: connect4.State): connect4.Action {

// For each action we could take, simulate multiple random games from the resulting state.

val_9vc52PbAY5

@dhvanil

An interactive, runnable TypeScript val by dhvanil

HTTP

export async function val_9vc52PbAY5(req) {

try {

// Execute the code directly and capture its result

runPythonAsync

@joshuahhh

An interactive, runnable TypeScript val by joshuahhh

Script

const { loadPyodide } = await import("https://www.unpkg.com/pyodide/pyodide.mjs");

const pyodide = await loadPyodide();

export function runPythonAsync(s) {

return pyodide.runPythonAsync(s);

MuxAITranscript

@decepulis

Generate CuePoints and transcripts for your Mux video Adapted from the blog post, Build an AI-powered interactive video transcript with Mux Player CuePoints This Val exposes an HTTP endpoint that takes a Mux Asset ID and a list of speakers and Uses Mux's auto-generated captions to generate a CuePoints object for Mux Player Uses AssemblyAI for speaker labeling (diarization) Uses GPT-4o to format text Fork it and use it as a foundation for your own interactive video transcript project. Usage: Required environment variables: Mux Access token details ( MUX_TOKEN_ID , MUX_TOKEN_SECRET ) This endpoint requires an existing Mux asset that's ready with an audio-only static rendition associated with it. You can run this val to create a new one for testing. AssemblyAI API key ( ASSEMBLYAI_API_KEY ). Get it from their dashboard here OpenAI API key ( OPENAI_API_KEY ). Get it from their dashboard here Make a POST request to the Val's endpoint with the following body, replacing the values with your own asset ID and the list of speakers. Speakers are listed in order of appearance. { "asset_id": "00OZ8VnQ01wDNQDdI8Qw3kf01FkGTtkMq2CW901ltq64Jyc", "speakers": ["Matt", "Nick"] } Limitations This is just a demo, so it's obviously not battle hardened. The biggest issue is that it does this whole process synchronously, so if the any step takes longer than the Val's timeout, you're hosed.

HTTP

- OpenAI API key (`OPENAI_API_KEY`). Get it [from their dashboard here](https://platform.openai.com/api-keys)

import OpenAI from "npm:openai";

import { zodResponseFormat } from "npm:openai/helpers/zod";

const openai = new OpenAI({

async function getMuxAsset(assetId: string) {

function createSpeakersObject(speakersArray: string[]) {

async function getCuePointsFromMux(asset: Mux.Video.Assets.Asset): Promise<MuxCuePoint[]> {

async function getCuePointsFromAssemblyAI(

async function formatTextWithGPT4o(aaiCuePoints: AssemblyAICuePoint[]) {

const completion = await openai.chat.completions.create({

export default async function(req: Request): Promise<Response> {

myApi

@eagle251

An interactive, runnable TypeScript val by eagle251

Script

export function myApi(name) {

return "hi " + name;

myApi

@danielraffel

An interactive, runnable TypeScript val by danielraffel

Script

export function myApi(name) {

return "hi " + name;

valle_tmp_40006751975257874463561930335375

@janpaul123

// Define the main function that will be executed on each HTTP request

HTTP

// Define the main function that will be executed on each HTTP request

export default async function main(req: Request): Promise<Response> {

// Return a simple "Hello, World!" response

return new Response("Hello, World!", { headers: { "Content-Type": "text/plain" } });

myApi

@steveb1313

An interactive, runnable TypeScript val by steveb1313

Script

export function myApi(name) {

return "hi " + name;

mgsrBotEndpoint2

@stevekrouse

An interactive, runnable TypeScript val by stevekrouse

HTTP

import { example1 } from "https://esm.town/v/stevekrouse/example1?v=3";

import process from "node:process";

export async function mgsrBotEndpoint(request) {

const signatureTimestamp = request.headers.get("X-Signature-Timestamp");

const signatureEd25519 = request.headers.get("X-Signature-Ed25519");

status: status,

headers: { "Content-Type": "application/json" },

async function handleApplicationCommands(body) {

let response;

switch (body.data.name) {

GistGPT

@weaverwhale

GistGPT A helpful assistant who provides the gist of a gist How to use / and /gist - Default response is to explain this file. I believe this is effectively real-time recursion ? /gist?url={URL} - Provide a RAW file URL from Github, BitBucket, GitLab, Val Town, etc. and GistGPT will provide you the gist of the code. /about - "Tell me a little bit about yourself"

HTTP

import { Hono } from "npm:hono";

import { OpenAI } from "npm:openai";

const gistGPT = async (input: string, about?: boolean) => {

const chatInput = about ? input : await (await fetch(input)).text();

const openai = new OpenAI();

let chatCompletion = await openai.chat.completions.create({

messages: [

myApi

@genevra

An interactive, runnable TypeScript val by genevra

Script

export function myApi(name) {

return "hi " + name;

cerebras_coder

@stevekrouse

This is an AI code assistant powered by Cerebras , running llama3.3-70b. Inspired by Hassan's Llama Coder . Setup Sign up for Cerebras Get a Cerebras API Key Save it in a Val Town environment variable called CEREBRAS_API_KEY

503 14

HTTP

function Hero({

Turn your ideas into fully functional apps in{" "}

function App() {

function handleStarterPromptClick(promptItem: typeof prompts[number]) {

async function handleSubmit(e: React.FormEvent | string) {

function handleVersionChange(direction: "back" | "forward") {

function client() {

function extractCodeFromFence(text: string): string {

async function generateCode(prompt: string, currentCode: string) {

export default async function cerebras_coder(req: Request): Promise<Response> {