We're Hiring!
x

“Develop safe general artificial intelligence – as fast as possible – to help humanity and understand the universe.”

Long-Term Memory

We are developing Long-Term Memory (LTM) systems to expand LLM agents' context window, enabling continual learning from interactions and environmental dynamics. Our goal is to create agents capable of lifelong learning, using every new experience to enhance future performance.

Explore

Charlie Mnemonic

We are open-sourcing Charlie Mnemonic, the first personal assistant (LLM agent) equipped with Long-Term Memory (LTM). The distinctive feature is the implementation of LTM, enabling it to learn from every interaction.

Explore

LLM Agents

At GoodAI, we are dedicated to pushing the boundaries of artificial intelligence. Our current focus is on the development of Large Language Model (LLM)-based agents with personalities that go beyond simple conversations.

Explore

GoodAI Groundstation

In a small and agile team inside GoodAI, we have set out to solve the challenges in drone operations.

Explore

From our blog

Civilisational Resilience – How do we prepare for the future with AI?

We continue our efforts mentioned in the Manifesto for Resilient Civilization What Makes A Resilient Civilization?   For this occasion we organized our first public meeting, available for anyone to visit our office in Prague to discuss ideas about Civilisational.

Read more

AI People – The Sitting Pretty Update

October 24, 2024

The second content addition update named “The Sitting Pretty Update” comes to AI People server on October 24, 2024. This Update brings brand new interaction feature, a plethora of new characters to the game, and several other features and changes. .

Read more

Breaking the Chain: Simple Word Swaps Expose LLMs’ Reasoning Limits

October 16, 2024 AILLMLTMResearchWord Swap

Key Findings: Large Language Models (LLMs) exhibit significant limitations in handling sequentially dependent operations. Our simple word-swap experiment reveals that most models struggle to perform correctly beyond two consecutive word swap operations, highlighting a critical weakness in their sequential reasoning.

Read more

Join GoodAI

Are you keen on making a meaningful impact? Interested in joining the GoodAI team?

View open positions