AI tool comparison
Google AI Edge Gallery vs Travel Hacking Toolkit
Which one should you ship with? Here is the side-by-side panel verdict, pricing read, reviewer split, and community vote comparison.
Mobile AI
Google AI Edge Gallery
Run Gemma 4 and other open models fully on-device — no cloud, no data sent
75%
Panel ship
—
Community
Free
Entry
Google AI Edge Gallery is an Android and iOS app that lets users run open-source language models — including the newly released Gemma 4 family — entirely on-device with no internet required. It's essentially a showcase and sandbox for on-device ML, letting developers and power users benchmark models on their own hardware and explore capabilities without any data leaving the device. Version 1.0.11 shipped on April 2, 2026, adding support for Gemma 4 and on-device function calling. The app includes Prompt Lab for parameter testing, AI Chat with visible reasoning traces, image recognition, audio transcription, translation, and a small experimental offline game called Tiny Garden that uses natural language as input. The project has 16.6k stars and is fully open-source. With AICore integration landing in Android, Gemma 4 can run via the OS-level model runtime — meaning future apps can share a single on-device model instance rather than each bundling their own. This is the infrastructure play underneath the gallery.
Travel & Productivity
Travel Hacking Toolkit
MCP skills for finding award flights and hotel points deals with AI
75%
Panel ship
—
Community
Free
Entry
Travel Hacking Toolkit is an MCP-based skills layer that teaches AI assistants how to search award flights, compare loyalty program valuations, and surface hotel points deals in natural language. Built by Michael Borohovski and posted as a Show HN, it connects Claude Code and OpenCode to live travel APIs including Seats.aero, SerpAPI, Duffel, and AwardWallet through structured markdown "skills" files that teach the AI how to call each service. The toolkit includes MCP servers for Skiplagged, Kiwi.com, Trivago, Ferryhopper, and Airbnb, enabling queries like "find me a 60,000-mile business class flight to Tokyo and compare it to cash prices." Static data files encode airline alliance structures, hotel chain partner awards, historical sweet spots, and community-sourced valuations—giving the AI grounded knowledge rather than hallucinated redemption values. The project is deliberately low-abstraction: skills are readable markdown files you can edit to add new programs or APIs, and it requires no persistent backend. With 205 stars from a Show HN debut, it's a small but focused tool for the travel hacking community that finally gives the "ask your AI for deals" fantasy some real API teeth.
Reviewer scorecard
“The function calling demo on-device is the real headline here. If Gemma 4 can handle tool use locally, that's a viable path to offline agents on Android — which opens up use cases in low-connectivity environments that were impossible before. The AICore integration means you write to one API and the OS handles the model.”
“The MCP architecture is exactly right for this problem—travel APIs are diverse and constantly changing, and skills-as-markdown-files means any developer can add a new loyalty program or airline API in 30 minutes without touching a codebase. The Seats.aero integration alone makes this worth setting up.”
“On-device model performance is still heavily hardware-gated — Gemma 4 running well on a Pixel 9 Pro doesn't mean it runs acceptably on the median Android device. Google controls the showcase, so the benchmarks are cherry-picked for their best hardware. Until AICore reaches broad adoption, this is a preview for early adopters.”
“Most of these APIs require paid keys or have aggressive rate limits, and the 'sweet spots' data will go stale quickly as airlines devalue programs. This solves a real problem but requires significant manual maintenance to stay useful—you're essentially signing up to maintain your own travel hacking research infrastructure.”
“The combination of AICore (OS-level model runtime) and on-device function calling is the blueprint for AI that survives network failures, regulatory data-residency requirements, and cloud cost pressures. Google is betting that the edge is where AI matures — this gallery is the proof of concept.”
“This is an early template for domain-specific MCP skill sets—curated API knowledge plus structured data that turns a general AI assistant into a specialist. As MCP adoption grows, we'll see these skill bundles for every vertical from legal research to healthcare, and travel hacking is a natural first mover.”
“Audio transcription and translation that works offline and doesn't store your recordings anywhere is genuinely appealing for journalists, field researchers, and creators in low-connectivity areas. The privacy story alone makes this worth installing.”
“Finally something that makes the 'just ask your AI to book travel' promise real rather than theoretical. The alliance and partner award data files are the kind of curated, hard-to-find knowledge that normally lives in obscure blog posts—having it structured for AI consumption is genuinely useful.”
Weekly AI Tool Verdicts
Get the next comparison in your inbox
New AI tools ship daily. We compare them before you waste an afternoon.