Please turn JavaScript on
Delphi 11 10 XE8 XE7 XE Seattle Berlin Tokyo Rio Firemonkey, Delphi Android, Delphi IOS icon

Delphi 11 10 XE8 XE7 XE Seattle Berlin Tokyo Rio Firemonkey, Delphi Android, Delphi IOS

Is this your feed? Claim it!

Publisher:  Unclaimed!
Message frequency:  0.44 / day

Message History

Developer TMS Software has released a FireDAC-powered MCP server that lets AI agents explore, query, and optionally modify databases through natural-language conversations.

The server connects to any database supported by FireDAC using a single connection string. AI clients can inspect schemas, list tables, describe columns, generate SQL, run queries, and return strong...


Read full story

Developer Paul Toth has released MiniLLM, an experimental language model implemented entirely in Delphi without neural networks, GPUs, external dependencies, or machine-learning frameworks.

Instead of using a transformer architecture, MiniLLM combines PMI-based word embeddings, a weighted Markov transition graph, a recurrent context vector, and similarity-based scoring...


Read full story

Developer tinyBigGAMES has made available Gemma4.pas, a native Object Pascal implementation of Google’s Gemma 4 multimodal models, bringing local text and vision AI directly to Delphi applications.

Rather than relying on external inference frameworks, Gemma4.pas demonstrates how modern multimodal LLMs can be integrated into native Delphi applications with support for c...


Read full story

Developer HemulGM has built an FMX interface for the ChatGPT API as a fully native cross-platform AI client built with Delphi and FireMonkey. Instead of embedding a browser, the application delivers a polished desktop and mobile experience using native FMX controls while supporting modern AI...


Read full story

Developer tinyBigGAMES has VindexLLM, a GPU-accelerated LLM inference engine written entirely in Delphi. Instead of wrapping existing inference libraries, VindexLLM performs the complete transformer forward pass using Vulkan compute shaders, requiring only the Vulkan runtime included with modern GPU drivers.

The framework loads standard GGUF models, memory-maps model w...


Read full story