New AI tools launch every single week — and most of them are noise. The MTD AI Tools Directory is our curated, regularly updated collection of the AI tools actually worth your attention: trending launches from Product Hunt and the open-source projects developers are building with on GitHub. Every roundup below is hand-reviewed by our team, with honest notes on pricing, strengths, and caveats.
Latest tool roundups
-
Adviserry Review: The AI Newsletter Summarizer That Turns Reading Into Action (2026)
Adviserry is an AI newsletter summarizer with a pitch that separates it from every digest tool on the market: it does not just summarise your newsletters. It reads everything your experts published this week, weighs it against the projects you are working on, and hands you a short list of specific moves to make —…
-
Scientific Agent Skills: An AI Agent for Science Research With 50,000+ Stars
If you have been waiting for a moment when coding assistants grow up into something a working lab could actually use, this is a good place to start. Scientific Agent Skills — an open-source library that turns AI coding agents into an AI agent for science research — has passed 51,000 GitHub stars (4,530 forks,…
-
PostNitro for Agents Review: The AI Social Media Post Generator That Designs Your Posts
An AI social media post generator usually means one of two things: a tool that writes your captions, or a template gallery you fill in by hand. PostNitro for Agents, which launched on Product Hunt this week, is a third thing entirely — it hands the whole design step to your AI agent. You ask…
-
Claude Code Plugins: A Developer’s Guide to Anthropic’s Official Directory
Claude Code plugins are the fastest way to stop treating your AI coding assistant like a clever autocomplete and start treating it like a team. The official Anthropic directory — anthropics/claude-plugins-official — is a curated marketplace of installable capability bundles: automated code reviewers, a guided feature-development workflow, security scanners, language servers for twelve programming languages,…
-
OpenClaw 2.0 Review: What a Self-Hosted AI Agent Really Costs to Run
Every few months an open-source project reminds the industry that the real moat around AI assistants is not the model — it is the plumbing. OpenClaw 2.0 is the latest example. This self-hosted AI agent does not sell you a chatbot subscription; it hands you an MIT-licensed gateway running on your own hardware that turns…
-
How to Reduce AI Coding Token Usage: Inside Caveman, the 100k-Star Open-Source Project
If you want to reduce AI coding token usage, the most interesting experiment of 2026 is not a cheaper model — it is a proxy that talks like a caveman. Caveman is an open-source project that sits between your coding agent and the model, compressing what the agent reads and says. Its headline claim: up…
-
Spira AI Review: The AI Social Media Agent That Runs Your Social End-to-End (2026)
If you run social media for a business in 2026, you already know the maths does not work: every platform wants daily native content, each with its own format, hook style and posting rhythm, and a human team that can keep up costs more than most SMEs can justify. An AI social media agent promises…
-
VoiceStudio: Open Source Voice Cloning That Runs 100% Locally
Open source voice cloning has a credibility problem: plenty of demos, almost nothing you can hand to a real team and run. VoiceStudio is the exception. It is a fully-local voice studio — cloning, voice design, video dubbing, dictation, transcription and audiobook creation — built as a desktop app that runs on your own hardware,…
-
REA: Reverse Engineer Anything with AI Agents (morluto/rea Guide)
See a feature in an app and wonder how it works? Until recently, answering that question meant weeks of expert work with tools like Ghidra or IDA Pro. REA (Reverse Engineer Anything) changes the equation: it connects your AI coding agent to professional reverse engineering tools through a single MCP server, letting you investigate any…
How we choose tools for this directory
- Verifiable traction — Product Hunt votes and badges, GitHub stars and commit activity, real user discussion. Hype alone does not qualify.
- Business relevance — every tool must solve a real problem for a real team, not just demo well.
- Honest economics — we note pricing, credit burn, and the hidden costs (setup time, infrastructure) that marketing pages skip.
- No paid placements — tools earn their spot here. If that ever changes, we will label it clearly.
We update this directory as new tools trend — bookmark it and check back. Want help evaluating which of these tools fit your business, or integrating AI into your existing systems? Talk to our team — 9+ years, 300+ projects, and a healthy skepticism toward launch-day hype.