Explore AI Tools & Apps

APX Terminal

Yoga Bagas · Coding

APX Terminal is an all-in-one AI development environment for macOS, Windows and Linux. It puts an SSH terminal, a database client, an API client, a project and task board, and an AI agent that can reach all of them into a single window. The agent reads and plans across your servers and code, but nothing changes on production until you approve it. You buy it once. Keep files on your own disk, and plug in your own AI key instead of paying the vendor for model access.

Doctective

Doctective · Coding

Doctective is an AI documentation tool that keeps your README and inline docs in sync with your code, and it treats automated documentation as something that runs on every commit rather than a project you schedule once a quarter. It connects to GitHub, reads every pull request, and works out which documentation your change just made wrong. Instead of nagging you with a warning, it opens a companion PR with AI-suggested fixes you can review and merge, which is the kind of pull request analysis most teams never get around to doing by hand. The pitch is simple: install once, and your documentation maintenance stops being a chore you forget about until a new hire complains.

Forums

BaseHub · Coding

Forums is an AI code Q&A tool that lets you ask GitHub repository questions and get a source-backed answer from a frontier LLM. Built by BaseHub, it reads the actual source code before replying, so the answer points back to real files instead of guessing. Developers use it to understand unfamiliar libraries, trace how a dependency works, and skip the hours spent cloning repos and grepping through folders. It's less a general code exploration tool than a focused research assistant for public source.

Preloop

Preloop · Coding

Preloop is an open-source AI agent control plane that sits between your agents and the outside world. It pairs an MCP firewall for tool access with a model gateway for cost and attribution, then adds policy-as-code rules, human-in-the-loop approvals, session observability, and audit trails. The platform is self-hostable under Apache-2.0, and its CLI can rewrite Claude Code, Codex CLI, Cursor, and other MCP runtimes to route through it without touching your agent code.

AgentEcho

Areshkew · Coding

AgentEcho is a visual feedback annotation Chrome extension that lets you drop numbered markers on any webpage element and turn them into a clean Markdown report. Instead of writing "the button near the top right," you click the actual button, type your note, and AgentEcho captures the element's selector, classes, text, and framework component name for you. It's built for developers who need to send precise UI feedback to teammates or AI coding assistants.

nlsh

Junaid Mahmood · Coding · Other

nlsh is an open source command line tool that translates plain English into working shell commands. Instead of memorizing flags and syntax, you describe the task and nlsh figures out the right command for your terminal. It runs on macOS and Linux, needs Python 3.8 or newer, and connects to the AI provider you pick, so you keep control of your own API key and history.

Git AutoReview

Git AutoReview Team · Coding

Git AutoReview is an AI code review tool that reviews pull requests on GitHub, GitLab, and Bitbucket by running Claude, Gemini, and GPT against the same diff. What sets this automated code review setup apart is the approval gate: the models draft comments in VS Code, you pick which ones to keep, and only approved suggestions get published to the PR. It's built for developers and small teams who want a faster PR review tool without handing final judgment to a model.

Pagesmith.ai

Pagesmith · Coding

Pagesmith.ai is an AI website builder for people who want a finished, editable site rather than a blank canvas. You describe a business in a prompt, paste the URL of a site you already own, or pick a template, and it drafts the pages with real content you can review before anything goes live. It publishes on Cloudflare, includes forms and analytics, and on paid plans lets you download the underlying Astro project, so the site stays yours if you ever walk away.

Coda by Conductor Quantum

Conductor Quantum · Coding

Coda by Conductor Quantum is a natural language quantum computing tool. Instead of hand-writing circuits in low-level frameworks, you type what you want a quantum computer to do, and Coda builds the circuit, checks the code, and runs it on real hardware or a simulator. Think of it as an AI quantum computing interface that targets students, researchers, and teams who want quantum results without spending weeks learning the tooling first.

Blink.new

Blink · Coding

Blink.new is an AI app builder that takes a plain description of what you want and produces a working website, a full-stack product, and always-on AI agents behind it. You type a prompt, and Blink designs the pages, wires up a real SQL database, adds authentication, and hosts the result on a custom domain. It suits founders, marketers, and small teams who need an app built from a prompt without hiring a developer or managing servers.

Mastra

Mastra AI · Coding

Mastra is an open-source TypeScript framework for building AI agents and AI-powered applications. It bundles agents, graph-based workflows, memory, and model routing across dozens of providers, plus observability, into one stack. Plug it into React, Next.js, or Node, or run it as a standalone server. If your team already writes TypeScript, Mastra is a short path to a working AI product.

Fimo

Fimo · Image · Coding

Fimo is an AI website builder for teams who want a website that maintains itself. You build the site with Claude Code, Codex, Cursor, or any coding agent you already use, then Fimo turns that output into an editable, autonomous-ready site with a visual editor and its own CMS. From there you add AI agents that handle SEO, translations, competitor analysis, and content refreshes on a schedule, with every run landing in a branch your team reviews before it ships.