ochafik

es6-lenses

ES6 functional lenses

jstyper

🦆 Adds Flow / TypeScript types to JavaScript files... because that hassle can be automated.

LibCL

Library of shared OpenCL code that can be reused between different binding libraries. Uses StringTemplate templates.

node-opencl

Experiments on auto-generated bindings for OpenCL in V8 / Node.js

openscad

OpenSCAD - The Programmers Solid 3D CAD Modeller

openscad-playground

OpenSCAD Web Playground

openscad-wasm

Webassembly port of OpenSCAD

optimized-loops-macros

Macro-powered loop optimizations (Range for comprehensions)

rpi-raspbian-bazel

Bazel Raspbian build script + off-the-shelf resin/rpi-raspbian Docker image derivative.

scalight

Trimmed-down Scala : get the language without the runtime !

ochafik/openscad-playground

OpenSCAD Web Playground

ochafik/openscad

OpenSCAD - The Programmers Solid 3D CAD Modeller

ochafik/llama-cpp-agent

The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). It provides a simple yet robust interface using llama-cpp-python, allowing users to chat with LLM models, execute structured function calls and get structured output.

ochafik/cline

Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.

ochafik/cofounder

ai-generated apps , full stack + generative UI

ochafik/cpp-httplib

A C++ header-only HTTP/HTTPS server and client library

ochafik/DiskANN

Graph-structured Indices for Scalable, Fast, Fresh and Filtered Approximate Nearest Neighbor Search

ochafik/duckdb-rs

Ergonomic bindings to duckdb for Rust

ochafik/entropix

Entropy Based Sampling and Parallel CoT Decoding

ochafik/g1

g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains

ochafik/langfun

OO for LLMs

ochafik/llama-models

Utilities intended for use with Llama models.

ochafik/llama-recipes

Scripts for fine-tuning Meta Llama with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama for WhatsApp & Messenger.

ochafik/llama-stack

Model components of the Llama Stack APIs

ochafik/llama-stack-apps

Agentic components of the Llama Stack APIs

ochafik/llama.cpp

Port of Facebook's LLaMA model in C/C++

ochafik/LLM-Research-Scripts

ochafik/MemGPT

Letta (fka MemGPT) is a framework for creating stateful LLM services.

ochafik/mistral-common

ochafik/mistral-inference

Official inference library for Mistral models

ochafik/observatory

A toolkit for describing model features and intervening on those features to steer behavior.

ochafik/openai-realtime-api-beta

Node.js + JavaScript reference client for the Realtime API (beta)

ochafik/piper

A fast, local neural text to speech system

ochafik/qrs

Stream data through multiple series of QR codes

ochafik/sqlite-lembed

A SQLite extension for generate text embeddings from GGUF models using llama.cpp

ochafik/sqlite-vec

A vector search SQLite extension that runs anywhere!

ochafik/vespa

AI + Data, online. https://vespa.ai

ochafik/wd2duckdb

Transform a Wikidata JSON dump into a DuckDB database

ochafik/web-llm

High-performance In-browser LLM Inference Engine

ochafik/whisper.cpp

Port of OpenAI's Whisper model in C/C++