I spotted the very underrated Bloom [1] in the screenshots and thought I should give it a shout in here. I've been using it, along with Witch [2] as an app switcher so that I can hide the Finder icon, for about 2 months and love it. [1] https://bloomapp.club [2] https://manytricks.com/witch/. - Source: Hacker News / 7 months ago

- check out Witch (https://manytricks.com/witch/). - Source: Hacker News / over 1 year ago

There's at least Witch and Contexts. https://manytricks.com/witch/ https://contexts.co/. - Source: Hacker News / about 2 years ago

There are multiple 3rd party window switchers, Witch is a popular one, afair: https://manytricks.com/witch/. - Source: Hacker News / about 2 years ago

I tried a lot, and https://manytricks.com/witch/ is what I stuck with for the ONLY decent alt tab experience I could find (it’s heavily customizable). I don’t understand this number thing, finding them like that takes the same reading action you could be doing while you press alt tab for each… and you’d be done, but instead I see so many apps offer that number route. It just seems like double work to me ;). Source: about 3 years ago

If you build on the JVM and want to use Qdrant, the official client is io.qdrant:client — and it's built for Java. Every call returns a ListenableFuture, requests are assembled with protobuf builders, and it drags a gRPC/Netty stack onto your classpath. From Kotlin, that means fighting the language:. - Source: dev.to / 20 days ago

The stack runs on Qdrant for vector storage, Ollama for local embeddings, and optional Neo4j for a knowledge graph that I added later. I also set it up to route different operations to the best LLM for each task. It provides eleven tools for your Claude Code instance to manage long-term memory operations, and your memories data never leaves your machine. - Source: dev.to / 6 months ago

Qdrant: Open-source vector database optimized for hybrid search and easy integration with ML workflows. - Source: dev.to / 9 months ago

Yes, Java SDKs are critical. But you don't need to rebuild entire orchestration engines just to write agents in Java. The ecosystem already has platforms solving the hard problems: memory (Zep, Mem0, LangMem), tools (specialized platforms), vectors (Pinecone, Weaviate, Qdrant), observability (LangSmith, Helicone, Langfuse). Integrate, don't rebuild. - Source: dev.to / 9 months ago

James Allsopp adds, "LangChain or LlamaIndex for managing LLM workflows, especially if you're adding vector search or documents." These tools handle multi-step processes, essential for complex apps. - Source: dev.to / 12 months ago