Explore AI Tools & Apps

Forsy

Forsy · Coding

Forsy is an AI agent data platform that records how agents behave while they run, not after the fact. It captures full agent workflows in real time across toolchains, then turns that activity into high-fidelity data teams can evaluate, license, or trade. Built by the team behind CPIBench-0, Forsy positions itself as the learning loop for AI agents operating in the living world.

WordPress – Website Builder

WordPress · Image · Coding

WordPress – Website Builder is the free, open-source publishing platform that powers more than 43% of sites on the web. Version 7.0, nicknamed "Armstrong," folds AI directly into the core: an AI Client talks to generative models, a central Connectors hub manages those links, and the block editor gains pattern editing, visual revisions, and responsive controls. You can run it on your own hosting or use WordPress.com, and there's a companion app for Android and iOS.

Shuffle Design CLI

Shuffle · Image · Coding

Shuffle Design CLI is a command line tool from Shuffle that generates and redesigns full landing pages from a single terminal command, drawing on top AI models like Claude Opus, GPT, Gemini Pro, and Kimi. It returns several design variants as clean, editable HTML with Tailwind CSS, so you can preview the output, refine it in Shuffle, and download the files for your own project. The tool targets anyone who wants repeatable design generation inside scripts, CI jobs, or internal dashboards rather than manual browser sessions. If that's you, it's a good fit.

DCP

DCP · Coding

DCP is a permission layer that sits between AI agents and the sensitive things they want to touch. It runs on your own computer, holds your wallet keys and stored details in a local vault, and hands agents only the result of an action, never the secret behind it. Think of it as practical AI agent security you can run yourself rather than rent. Connect an agent in one line, give it its own spending limits and access rules, and approve anything unusual from your phone. It works with Claude Desktop, ChatGPT, Cursor, VS Code, OpenClaw, and any MCP-compatible client.

General Compute

General Compute · Coding

General Compute is an AI inference cloud built for one job: serving large language models faster than GPU-only providers can. It runs OpenAI-compatible endpoints on purpose-built decode silicon from SambaNova, Cerebras, Positron, and d-Matrix, while prefill stays on NVIDIA B300 racks. New accounts get $100 in free credit, and teams that need reserved capacity or private weights can sign a dedicated contract instead. Pricing is transparent too. Inference API pricing runs per million tokens, with no monthly seat fee on the self-serve tier. No hidden platform charge.

WeWeb.io

WeWeb · Coding

WeWeb.io is an AI-powered no-code web app builder for turning a rough idea into a production-ready application without writing a single line of code. You describe what you want, the AI generates the structure, and a visual drag-and-drop editor lets you fine-tune every detail. It's fast. When it's done, you can launch on a global CDN or export the code as a standard Vue.js single-page app and host it yourself.

Trainer

Trainer Labs, Inc. · Coding

Trainer is an AI agent training tool that builds a working agent from a single screen recording. You hit record, do a task the way you normally would, and it captures your screen, clicks, keystrokes, and spoken narration on one timeline. The platform then breaks the video into steps, compiles those steps into a trace, and fine-tunes an agent that can repeat the job. No prompt writing. No labeled data. That combination makes it one of the few no-code AI agent builders aimed at people who can do the work but can't code the automation.

StoreClaw

StoreClaw · Coding · Business

StoreClaw is an AI ecommerce growth engine that connects to the platforms you sell on and runs the day-to-day work of growing a store from a single workspace. It monitors performance, spots problems like a falling conversion rate, and then executes SEO, listing, content, and operations tasks instead of just explaining them. Think of it as a teammate that watches your store around the clock and acts, with your approval, on what it finds.

ShioriCode

Shiori · Coding

ShioriCode is a desktop AI coding agent workspace from Shiori that lets you run several coding-agent tools in one place. Instead of bouncing between separate terminals for OpenAI Codex, Anthropic Claude Code, Google Gemini CLI, Cursor Agent, Kimi Code, and Shiori's own hosted provider, you open one project-aware window and work across all of them. Each thread keeps a live activity timeline, shows reviewable file changes, and snaps Git checkpoints around agent work so you can roll back a change you don't like.

Contextberg

Contextberg · Coding

Contextberg is a local-first memory app for AI coding agents. It watches your screens, browser activity, and agent transcripts in the background, then feeds that context back to tools like Claude Code, Cursor, Codex, and OpenClaw through a built-in MCP server. Your work history stays on your machine, and you pick which model handles the reasoning.

Polarity

Polarity · Coding

Polarity is a sandboxed evaluation and monitoring platform for AI agents. It runs your agent inside isolated Docker environments with real backing services, scores what the agent does against invariants and forbidden rules, and measures how much its behavior varies across repeated runs. That last part is the one most teams skip. Think of it as an agent eval tool that treats live behavior as the test. When a run fails, seed-based replay lets you rebuild the exact conditions and debug the failure instead of guessing.

Agentspan

Orkes · Coding

Agentspan is an MIT-licensed, self-hostable server and SDK that turns agent code into durable workflows. You write an agent, and the server keeps it alive across crashes, restarts, and long waits, resuming from the last completed step whenever a worker reconnects. It ships as a runtime rather than a hosted product, so you run it on your own infrastructure and pay only for the model calls you make. As of August 2026, the project has merged into Orkes Conductor, and the original repository is archived.