Repository Showcase
A curated collection of interesting GitHub repositories
roboflow/maestro
Toolkit to fine-tune multimodal VLMs with a simple CLI and Python API, featuring ready-made recipes for Florence-2, PaliGemma 2, and Qwen2.5-VL
Related repos
- open large multimodal models for vision and language tasks
- multimodal AI model for real-time text, image, audio, and video chat
- open source toolkit for building real-time voice LLM apps and agents
- run vision and audio language models on your Mac with MLX
- multimodal agent with long-term memory for real-time visual and audio reasoning
- unified multimodal model for both understanding and generating images and text
- multimodal LLM inference engine in Rust and Python
- benchmark vLLM, SGLang, TensorRT-LLM on Modal
- Microsoft’s open-source foundation model for multimodal AI agents
- Command-line tool for running OpenAI Whisper speech recognition models using C/C++
