andyk

ht

headless terminal - wrap any binary with a terminal interface for easy programmatic access.

recursive_llm

Implement recursion using English as the programming language and an LLM as the runtime.

headlong

A framework for collecting a large human-sourced chain-of-thoughts dataset

headlong-env

Headlong Env that provides actuation and sensory input for a Headlong agent. Operates by listening to the headlong var, executing actions, and updating the headlong var with observations.

lucida

Speech and Vision Based Intelligent Personal Assistant

agentos

AgentOS is an open source python API and a command line interface for building, running, and sharing learning agents.

andyk.github.io

Personal website

headlong-jsos

improved-funicular

Python implementation of the 2048 game

jsos

mlflow

Open source platform for the complete machine learning lifecycle

PuzzleDesigner

An API for designing puzzles, with a focus on escape rooms as a type of puzzle.

2048_java

Java implementation of 2048

clipper

A low-latency prediction-serving system

coding_the_matrix

Problem Sets from Coding The Matrix Textboko

crazyflie-clients-python

Host applications and library for Crazyflie written in Python.

crazyflie-lib-python

Python library to communicate with Crazyflie

design_docs

Design documents for AgentOS internals

dummy_agent

homework

Assignments for CS294-112.

jsos-py

la_deep_rl_meet_1

Repo for first meetup of LA Deep RL group

lineapy

Data engineering, simplified. LineaPy creates a frictionless path for taking your data science artifact from development to production.

mycroft-core

Mycroft Core, the Mycroft Artificial Intelligence platform.

nextjs

reading

Notes on readings related to reinforcement learning, neural nets, cognitive architectures, AI, and related topics.

reverb

Reverb is an efficient and easy-to-use data storage and transport system designed for machine learning research

spaun2.0

Spaun (nengo 2.0 version)

studious-winner

vanilla_policy_gradient

I coded up vanilla policy gradient in Google Colab from memory after carefully studying # The following is copied & pasted from Aurelien Geron's O'Reilly book example code notebook called 18_reinforcement_learning.ipyn