- Warsaw, Poland
- https://mkozak.pl
- @mkozak
- in/mateuszkozak
Highlights
- Pro
Lists (2)
Sort Name ascending (A-Z)
Starred repositories
Open Source AI Platform - AI Chat with advanced features that works with every LLM
A high-throughput and memory-efficient inference and serving engine for LLMs
π OpenHands: Code Less, Make More
High-performance runtime for multi-agent systems. Build, run and manage secure multi-agent systems in your cloud.
π€ Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
Automate browser-based workflows with LLMs and Computer Vision
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
You like pytorch? You like micrograd? You love tinygrad! β€οΈ
π¦ PostHog provides open-source web & product analytics, session recording, feature flagging and A/B testing that you can self-host. Get started - free.
Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]
FastAPI framework, high performance, easy to learn, fast to code, ready for production
Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)
ModelScope: bring the notion of Model-as-a-Service to life.
Add object detection, tracking, and mobile notifications to any RTSP Camera or iPhone.
Hunt down social media accounts by username across social networks
Universal LLM Deployment Engine with ML Compilation
π Make websites accessible for AI agents. Automate tasks online with ease.
Collection of awesome LLM apps with AI Agents and RAG using OpenAI, Anthropic, Gemini and opensource models.
Fine-tuning & Reinforcement Learning for LLMs. π¦₯ Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
The official Python client for the Huggingface Hub.
LlamaIndex is the leading framework for building LLM-powered agents over your data.
ZenML π: MLOps for Reliable AI: from Classical AI to Agents. https://zenml.io.
Linux, Jenkins, AWS, SRE, Prometheus, Docker, Python, Ansible, Git, Kubernetes, Terraform, OpenStack, SQL, NoSQL, Azure, GCP, DNS, Elastic, Network, Virtualization. DevOps Interview Questions
Evaluation and Tracking for LLM Experiments and AI Agents
π Freely available programming books
An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries