llama-cpp-delphi
- Active
- Library
- Delphi
- GitHub
- ★ 56

30,059 projects in the catalog.
Free Pascal, Lazarus and Delphi components, libraries and programs from GitHub, SourceForge, Codeberg, GitLab and more. Rate them, mark what looks interesting, and talk about them on their benches.
Free Pascal bindings for llama.cpp
Freepascal bindings for Llama.cpp
Run local LLM models in Delphi Object Pascal with llama.cpp.
Native gui to serveral AI services plus llama.cpp local AIs.
Delphi wrappers and compiled Windows DLLs for local LLM inference and embeddings via llama.cpp
Delphi 11+ bindings for llama.cpp (b11900+) with full GPU acceleration. Updated from the original Embarcadero fork: new memory API, vocab object, backend loader, CUDA 13, RTX 30xx/40xx/50xx support, Flash Attention, quantized KV cache, Jinja2 chat templates, and multimodal vision inference via the mtmd API.
Ashley is an all-in-one, single-click local AI assistant. It bundles an llama.cpp LLM inference engine, a Symfony/PHP web chatbot interface, a CEF-based web client (PHP Desktop), and a service manager (written in Free Pascal) into one package - no Internet connection or cloud API key required at runtime.
CartelNET: Dark Operator is a tactical cyber-warfare strategy game featuring a dynamic, LLM-powered AI adversary (Google Gemini / Llama.cpp)
VindexLLM is a pure Delphi, GPU-powered LLM inference engine that uses Vulkan compute shaders to run GGUF models entirely on the GPU. It performs full transformer inference without relying on Python, CUDA, or other external runtimes, requiring only vulkan-1.dll, which is typically included with modern GPU drivers.
The AI Operating System for Delphi. 100% native framework with RAG 2.0, autonomous agents, MCP protocol, and universal LLM connector. Supports OpenAI, Claude, Gemini, Ollama, and more. Delphi 10.4+ (limited), full support from Delphi 12 Athens.
PasLLM - LLM inference engine in Object Pascal (synced from my private work repository)
Ultra-lightweight native AI agent framework written entirely in Object Pascal for Delphi and Free Pascal, designed for performance, portability, and extensibility.
Demonstrates Voice Recognition, Text to Speech, Language Translation, OAuth2, Image Generation, Face Detection and Voice Chatbot.
MCP (Model Context Protocol) server library for Delphi. Built on DMVCFramework, it lets you expose tools, resources and prompts via attributes and RTTI. Supports both HTTP Streamable and stdio transports. MCP 2025-03-26 compliant.
LLM inference in Delphi
PaskalCPP is a systems language by Jarrod Davis: Pascal/Oberon-style syntax that transpiles to C++23 and builds with a bundled Zig/Clang toolchain. Mix PaskalCPP and C++ in one file, no bindings. Includes a Delphi-built compiler and language server, an Electron/Monaco editor, and diagnostics mapped to your source. Native Windows and Linux binaries.
Lazarus component for CHATGPT
mORMot2-based AI/LLM extension for Free Pascal and Delphi: MCP server, LLM clients, embeddings, vector stores, RAG
High performant CUDA powered LLM inference library
GPT Transformer developed in Delphi 13
Local AI interview copilot - Delphi VCL + Whisper + Qwen2.5 engine
An easy to use, high performant CUDA powered LLM inference library.
LlamaCPP library for Object Pascal Notebook
Local Generative AI
Short term long term AI agent memory system using fine-tuning, priors, and RAG.
Rust reimplementation of Graphify (Python)
Graphify fork that emits OKF-compatible Obsidian vaults
Bridge code graphs with knowledge-engine concepts and dependencies