Personal blog: matt-rickard.com
Current Projects
thiggle/api - Hosted categorization and classification API powered by LLMs. Give it a prompt and some categorizes, and it returns structured JSON with only the matching categories.
@react-llm/headless - Easy-to-use headless React Hooks to run LLMs in the browser with WebGPU. All inference happens clientside in the browser. See chat.matt-rickard.com for a live example.
LLaMaTab - A Chrome Extension that uses @react-llm/headless to run a LLM entirely in the browser. Load the model once and run on any site.
ReLLM - Exact structure out of any LLM by constraining pre-generation logits with regex. ParserLLM is an extension to ReLLM that constrains LLMs to only generating a specific context-free grammar (e.g., JSON).
openlm - a drop-in OpenAI-compatible Python library that can call LLMs from any other hosted inference API. OpenLM takes in the same parameters as the openai.Completion class and and outputs a similarly structured result.
llm.ts - A TypeScript equivalent of OpenLM that works in any JS environment (browser, node, deno)
virgo - Graph-based Declarative Configuration Language
mockerfile - Docker buildable alternative BuildKit frontend in YAML
ScapeNet and osrs-ocr - Fine-tuned object recognition and OCR models for the MMORPG Old School RuneScape
docker-merge - Merge Docker images like git branches
Past Projects
minikube - Run Kubernetes locally
skaffold - Define, develop, and run multi-deployment applications with Kubernetes
kubeflow - Machine Learning Toolkit for Kubernetes
distroless - Built a package manager for adding APT packages into distroless containers
minikube-kvm - Virtualization backend for minikube to run KVM machines on Linux