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
-

Chatway MCP Review: AI Customer Support via MCP, Without Ditching Your Favourite Assistant (2026)
If you run customer support in 2026, you have probably been through the same loop: you pick a live-chat platform, it ships a built-in AI bot, the bot only knows what the vendor taught it, and the AI assistant your team actually uses all day — the one that already knows your products, your policies,…
-

Anatomy on GitHub: The Open-Source Agent Skill That Turns AI Agents Into Technical Illustrators
If you have ever asked an AI assistant to “draw a diagram of how this works” and received a wobbly box-and-arrow mess with misspelled labels, you are the audience for Anatomy. This agent skill for technical illustrations plugs into Claude Code, Codex, OpenCode and other coding agents, and teaches them to produce detailed, interactive isometric…
-

withHuman Review: The Human Approval Layer for AI Agents Your Team Controls
There is a class of failure that only shows up the week you let an AI agent touch something real. A support agent issues the same refund twice. A coding agent restarts the payments service at peak traffic. A research agent deletes the calendar event it was asked to summarise. Each of these has the…
-

Run Qwen Locally One-Click Install: Inside Strata, the 28,000-Star Local LLM Engine
The fastest way to run Qwen locally with a one-click install arrived this autumn, and it looks nothing like the local-LLM tooling of last year. Strata, an open-source inference engine by developer Niko1221, runs Qwen3.8-Flash-Next — a 125-billion-parameter model from Alibaba’s Qwen team — on an ordinary gaming PC. It has pulled in more than…
-

Navige Review: AI Agent Cost Management That Pays Only for the Intelligence You Need
Most teams running AI agents have an AI agent cost management problem they cannot see: every call goes to the biggest model in the stack, the monthly bill arrives as a single number, and nobody can say which agent spent what. Navige is a new launch (Product Hunt, 13 October 2026) that tries to fix…
-

Concat: the open source CapCut alternative with MCP that AI agents can drive
If you have been looking for an open source CapCut alternative with MCP support, the search has effectively been on hold until now. Concat — a free, local-first, cross-platform video editor built in Rust — has collected over 9,000 GitHub stars in under three months, and it is the first editor we have seen that…
-

ReSO AI Review: An AI Brand Visibility Tool That Owns Your Answer-Engine Presence (2026)
Ask yourself a simple question: when one of your buyers asks ChatGPT or Perplexity for the best option in your category, does your brand appear in the answer? If it does not, that sale may be over before your homepage ever loads. This is the problem an AI brand visibility tool is built to solve…
-

Reef: Inside the Self-Improving AI Agents Infrastructure With 7,600 Stars
Every production AI agent has the same quiet embarrassment: it is brilliant on launch day and never gets better. The model underneath it keeps improving with every release from the labs, but your agent — the prompts, the tool wiring, the way it handles your customers’ edge cases — stays frozen exactly as your team…
-

Foley Review: An AI Voice To-Do List App That Asks First (2026)
Every few months a new AI voice to-do list app launches promising to finally fix the problem of thoughts that never make it onto your list. Foley, which launched on Product Hunt in October 2026, is the latest — and it caught my attention for one specific reason: instead of confidently filing whatever it heard,…
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.