Coding & Development 8074

Multilingual APIs for speech recognition, speech generation, and real-time translation Soniox is a multilingual speech AI platform that provides APIs for real-time and async speech-to-text, text-to-speech, and speech translation across 60+ languages. Its features include low-latency streaming, language switching, speaker identification, alphanumeric recognition, expressive speech generation, and voice cloning. Developers can use the APIs to add speech capabilities to voice agents, apps, wearables, transcription workflows, and multilingual products.

Scheduling optimization APIs and solver for complex operational planning Timefold is an enterprise scheduling optimization platform offering APIs and solver technology for workforce scheduling, vehicle routing, pickup and delivery, and task assignment. Its REST APIs integrate with existing software and optimize plans using real-world constraints such as skills, fairness, labor laws, dependencies, and changing conditions. The platform also provides explainability, dashboards, scenario analysis, hosting, and support options. Timefold offers API plans called Spark, Flow, and Horizon, as well as a free open-source Community solver and a paid Enterprise solver.

Mobile-first funnel builder for generating leads, sales, and applications Perspective Funnels is a mobile-first platform for building interactive lead-generation and sales funnels. It helps businesses create funnels for appointments, applications, online sales, and recruiting without design or coding skills. The platform also includes AI-assisted funnel creation, email and messaging automations, contact management, analytics, integrations, and team workspaces.

An API platform for developing, testing, managing, and securing APIs. Postman is an API development platform for designing, building, testing, managing, and distributing APIs. It provides tools for API clients, collections, specifications, mock servers, automated testing, monitoring, documentation, and team collaboration. Its agent-focused tools include Agent Mode, Postman CLI, and the Postman MCP Server, while Context Graph gives agents structured information about APIs and their relationships. Postman also offers API governance and security capabilities, including Passport for brokering API access without exposing secrets.

Platform for comparing AI agents on real computer-use tasks Coarena by Coasty is a computer-use evaluation arena where users watch multiple AI agents complete real computer tasks side by side. It enables users to compare agents based on speed, accuracy, reliability, and task completion quality, then vote for the better-performing agent. The platform focuses on everyday workflows across browsers, applications, and enterprise software rather than synthetic benchmarks.

Persistent Ubuntu cloud VMs for AI agents and developer workflows boat is a cloud sandbox platform that provides persistent Ubuntu virtual machines for AI agents, developers, and programmatic workflows. Sandboxes include SSH and SCP access, Docker, a dedicated IP address, a 60fps virtual desktop, and snapshot-based forking. Pre-installed tools include Docker, VS Code, Chrome, Ghostty, GitHub CLI, Rust, Node.js, and Bun. Users can manage sandboxes through the CLI, HTTP API, or Python and TypeScript SDKs. Compute is billed by the second while a sandbox is running; stopped sandboxes do not incur machine-time charges.

AI platform that builds and operates businesses across websites, sales, support, and marketing Crevio is an AI-powered platform designed to build and operate a business. Users describe the business they want, and Crevio can create and deploy websites and apps, set up products and payments, manage email and customer support, publish social content, run advertising campaigns, and report on performance. It also supports business formation, domains, CRM, research, and analytics. Work can be delegated through recurring or event-triggered AI tasks, with approval options for consequential actions. Crevio's capabilities are also available through its API, MCP server, and SDK.

Open-source TypeScript framework for building AI agents with shared application UIs Agent-Native is an open-source TypeScript framework for building agentic applications with rich user interfaces. It lets developers define a capability once with defineAction() and use it across the app's UI, AI agent, HTTP API, CLI, MCP server, and A2A endpoint. The framework connects agents and users to shared application state and PostgreSQL data, and includes features for authentication, permissions, collaboration, skills, memory, automations, and agent teams. Developers can choose their AI model, database, and hosting provider, build locally, and deploy anywhere.

AI web scraper that extracts and automates structured data collection without coding. Lection is an AI-powered web scraping agent that runs in a browser extension. Users describe the data they want in natural language, and Lection builds a scraper to collect structured information from websites without coding. It supports pagination, infinite scrolling, detail-page links, and scheduled cloud scrapes. Results can be exported as CSV, Excel, or JSON, or sent to spreadsheets, databases, and automation tools such as Google Sheets, Airtable, Zapier, Make, and n8n.

AI browser agent for web research, scraping, and task automation Retriever AI is an AI-powered browser agent for Chrome and the cloud. It uses natural-language instructions to automate tasks across public websites and sites where users are signed in, then returns completed results. It supports web research and scraping, lead enrichment, personalized outreach, form filling, monitoring, and recurring workflows. Users can work through the browser extension, Cloud, API, MCP, CLI, or SDK. Free Mode includes supported AI models and Cloud browser time for eligible tasks started in the extension or Cloud dashboard, with sponsored content and daily fair-use limits.

One OpenAI- and Anthropic-compatible API for text, image and video models from leading AI labs. One key, one prepaid USD balance, published per-token prices. BoostRail gives developers and businesses one API for text, image and video models from Anthropic, OpenAI, Google, DeepSeek and other labs. It works with the OpenAI and Anthropic SDKs unchanged: point the base URL at BoostRail, use one key, and pick a model by its id. Each request runs on a checked route. If that route fails before the response starts, the request moves to another route of the same model — it never swaps in a different model. Usage is metered per token in USD against one prepaid balance, with prices published per model. Teams that already hold provider accounts can bring their own keys (BYOK): those requests run on their own quota and contract prices, with platform routes as automatic fallback. The BYOK free plan includes 1,000,000 requests a month.

LanoX is a multi-model AI API platform: one API key for GPT, Claude, Gemini, Grok, DeepSeek, Qwen and GLM, at up to 95% off official prices, with official provider access and no model downgrades. LanoX gives developers and teams one account and one API key for text, image and video models, with usage and billing in one place. Pricing vs. official list prices (up to, as shown on lanox.ai/en/model-pricing): - GPT models: up to 95% off - Grok models: up to 93.1% off - Gemini models: up to 83.3% off - DeepSeek models: up to 80.1% off - Claude models: up to 70.1% off - GLM models: up to 70.1% off - Selected models are free to use Why LanoX: - Official provider access, with a clear source for every model - No model downgrades or watered-down responses - Every price is listed next to the official price, so you can check it yourself - OpenAI-compatible API, works with Codex and Claude Code - Pay with Alipay, WeChat Pay or international cards; unused balance is refundable Built for developers, startups and teams who want top AI models at a fraction of the official cost.

AI studio for generating and editing videos and images VidoGrid is an AI studio for generating cinematic videos and images from text, images, frames, and visual references. It brings multiple models, including Veo 3.1, Gemini Omni 1.1 Flash, Seedance, Grok, Nano Banana, GPT Image 2.5, and Vela, into one workspace with a shared credit balance and media library. Users can create, edit, extend, and export media, with supported video resolutions up to 1080p on specified models and image resolutions up to 4K.

Website and prototype feedback for teams and AI agents Skyelight simplifies the feedback loop for web development. It allows users to annotate any element on a live page or prototype and share those insights with human team members or coding agents such as Claude Code, Cursor, and Codex. By bridging the gap between visual review and technical execution, it helps teams communicate changes directly in the context of production or staging environments.

A desktop workspace for teams of AI agents OpenBot is a desktop app for running a team of AI agents on your computer. Agents can work in separate workspaces, communicate, hand off tasks, share files, and use a built-in browser. It supports several AI providers and local models, including Codex, Claude Code, Gemini, Grok, Ollama, and LM Studio. OpenBot also offers hosted Linux servers for teams that prefer not to set up and maintain their own machine.

Anonymous AI chat with GPT, Claude, Gemini and 200+ models. No email: your account is a random number. Pay with Monero, Bitcoin, Lightning or card. Obscurify.ai is a private AI chat. Use GPT, Claude, Gemini, Llama, DeepSeek, Qwen, Mistral and 200+ other models without giving up your identity. Guests can chat with Llama 3.3 70B without an account. Paid accounts are a random 16-digit account number: no email, phone, username or password. Your identity is scrambled before requests reach the model providers, prompts and responses are not stored on our servers, and text requests only use zero-data-retention routes (these rely on the providers' published policies; there are no signed agreements). Uncensored models are available on the Pro plan, and every account with a balance gets an OpenAI-compatible API. Pay with Monero, Bitcoin or Lightning through self-hosted BTCPay, or by card through Stripe. Each payment becomes blind-signed vouchers, so Obscurify can't tell which payment funded which account. Local Mode runs small open models entirely in your browser. The whole site works over Tor, and a signed warrant canary is updated monthly.

A free local-first workspace for code, notes, API requests, and developer tools. massCode is a free, open-source, cross-platform developer workspace for organizing code snippets, Markdown notes, HTTP requests, calculations, drawings, and developer tools. It stores workspace content locally as plain files, giving users control over their data and allowing them to open files outside the app or sync the workspace folder with services such as iCloud, Dropbox, Syncthing, or Git. It also includes an AI assistant that can connect to supported cloud models using a user-provided API key, or to models running through Ollama or LM Studio.

ModelAny is a free Chrome and Edge extension to ask multiple AI at once and compare answers side by side. One prompt goes in parallel to ChatGPT, Claude, Gemini, Grok, DeepSeek, Kimi and more, under your own accounts, with no API key. Export chats to Markdown, Word or PDF, continue a ChatGPT chat in Claude, and summarize YouTube/Bilibili videos. Data stays in your browser.

Jev: Typed Questions, Structured Answers. Run Jev, Clef, Perplexity Decider and OpenAI Luna Decisions on one key: send a state, ask typed questions, get answers with confidence. Start free.

TryAPI offers 81+ production-ready APIs with pay-as-you-go pricing, 99.9% uptime, and sub-200ms response times. Includes currency exchange, IP geolocation, weather, UUID generation, and X/Twitter data APIs.

Skilloop is an Agent Skills directory for Claude Code, Codex & Cursor. Preview skill outputs before install. Chinese: https://skilloop.dev/zh | Skills: https://skilloop.dev/skills | Examples: /zh/ai-video/fable-5-5, /zh/ai-video/opus-5-5 | GitHub: https://github.com/xianyu110/skillhub

AI tool for creating playable Roblox games from text prompts LevelShaper is an AI Roblox game maker that turns a written game idea into a playable, editable Roblox place. Users can describe an obby, tycoon, simulator, horror game, PvP arena, or RPG, preview the generated map in 3D, and download a real .rbxlx file for Roblox Studio. Generated games can include maps, checkpoints, shops, saving systems, leaderboards, droppers, conveyors, upgrade buttons, rebirths, moving platforms, kill bricks, keys, exits, and other working Luau scripts. The downloaded files belong to the user and can be edited, published, monetized, or remixed in Roblox Studio. LevelShaper also offers AI tools for Roblox thumbnails, icons, GFX, GUI assets, and Luau scripts.

Modelflare is a stable, lower-cost API gateway for GPT, Claude, Grok, GLM, Seedance, MiniMax, and other models, with routes as low as 1.5% of the official price. The same account opens Castaly, a studio for generating images and video, comparing models and prices, and remixing community work. Modelflare is one API gateway for apps, agents, and coding tools. Keep the client you already use, point it at https://modelflare.dev/v1, and call many model families with the same key. Lower price. Selected routes bill down to 1.5% of the official list price. A single top-up of US$20 unlocks GPT at that 0.015x rate. Everyday traffic can stay on a lower-cost group; more sensitive jobs can use a balanced or higher-stability group. The pricing page shows what you pay against the official list price. Balance is in US dollars: one dollar of top-up is one dollar of credit. Castaly uses that same balance. A key can list fallback groups in order. If the primary group is unavailable, the request moves to the next group. Each request records status, latency, token usage, and cost, whether it came from your own code or from Castaly. Many models, one account. GPT uses OpenAI Chat Completions and the Responses API, including Codex-style clients. Claude uses Anthropic Messages, including Claude Code. Grok, GLM, Seedance, and MiniMax are on the same key, along with DeepSeek, Kimi, Owen, Gemini, and image and video models. Castaly (https://castaly.modelflare.dev) is the studio on that account. In the browser you generate images and video with Seedance, Kling, Wan, MiniMax, Seedream, and other models from the same catalog. You compare specifications and price, set the shot parameters, and remix a community work from its prompt and settings. Account, balance, API keys, and usage history are shared with Modelflare, so a result made in Castaly can also be requested through the API. Create a key at https://modelflare.dev, set the base URL to https://modelflare.dev/v1, or start a shot in Castaly.

Build, refine, and deploy full-stack web apps by chatting with AI. Coderblock is an AI app-building platform for creating full-stack web applications through chat. Users describe an idea and Coderblock generates a React app with backend and database capabilities, then lets them refine the project conversationally and deploy it. The platform also offers templates, AI model choices, code export, image and video generation, domain purchasing, analytics, and integrations such as Supabase and Stripe.