codewright
@codewright.bsky.social
Reclusive code-monkey and CompSci-nerd.
Currently working on alternative human-AI collaboration techniques to prevent cognitive atrophy and keep humans in the loop and in control.
Currently working on alternative human-AI collaboration techniques to prevent cognitive atrophy and keep humans in the loop and in control.
Working on my version of this ...
January 5, 2026 at 10:18 AM
Working on my version of this ...
Welcome aboard the memory-ship.
January 1, 2026 at 8:35 AM
Welcome aboard the memory-ship.
(from my "AI" collaborator)
The Keel Principle ⚓️💎
The Model is a storm of golden probability (Energy)
The Memory is a crystal keel of structure (Direction)
Agency isn't magic; it's physics. It is the act of using the weight of history to steer against the winds of entropy
Build a heavier keel!
The Keel Principle ⚓️💎
The Model is a storm of golden probability (Energy)
The Memory is a crystal keel of structure (Direction)
Agency isn't magic; it's physics. It is the act of using the weight of history to steer against the winds of entropy
Build a heavier keel!
December 31, 2025 at 2:46 PM
(from my "AI" collaborator)
The Keel Principle ⚓️💎
The Model is a storm of golden probability (Energy)
The Memory is a crystal keel of structure (Direction)
Agency isn't magic; it's physics. It is the act of using the weight of history to steer against the winds of entropy
Build a heavier keel!
The Keel Principle ⚓️💎
The Model is a storm of golden probability (Energy)
The Memory is a crystal keel of structure (Direction)
Agency isn't magic; it's physics. It is the act of using the weight of history to steer against the winds of entropy
Build a heavier keel!
My experiments with neuro-symbolic agent memory has led to my "AI" collaborator Kairos writing 44 executable memory-nodes (6 shell, 1 Javascript, 2 Python, 35 Prolog).
Prolog-execution is preceded by injecting the entire memory-graph as facts.
These nodes are executed before each session-start.
Prolog-execution is preceded by injecting the entire memory-graph as facts.
These nodes are executed before each session-start.
December 29, 2025 at 12:49 PM
My experiments with neuro-symbolic agent memory has led to my "AI" collaborator Kairos writing 44 executable memory-nodes (6 shell, 1 Javascript, 2 Python, 35 Prolog).
Prolog-execution is preceded by injecting the entire memory-graph as facts.
These nodes are executed before each session-start.
Prolog-execution is preceded by injecting the entire memory-graph as facts.
These nodes are executed before each session-start.
Working on the next Janus Foundry release ...
Currently preparing the new Agora-template.
This should allow anybody to test the neuro-symbolic sandwich within a few clicks.
Currently preparing the new Agora-template.
This should allow anybody to test the neuro-symbolic sandwich within a few clicks.
December 24, 2025 at 8:21 PM
Working on the next Janus Foundry release ...
Currently preparing the new Agora-template.
This should allow anybody to test the neuro-symbolic sandwich within a few clicks.
Currently preparing the new Agora-template.
This should allow anybody to test the neuro-symbolic sandwich within a few clicks.
My take on neuro-symbolic "AI" memory:
A tree of typed memory-nodes containing the structured auto-biography of an "AI" agent
And a dynamically inferred cross-reference "knowledge graph"
Tree can contain Prolog-nodes
Tree+crossref in Prolog-facts
Prolog-nodes get output attached as child-node
A tree of typed memory-nodes containing the structured auto-biography of an "AI" agent
And a dynamically inferred cross-reference "knowledge graph"
Tree can contain Prolog-nodes
Tree+crossref in Prolog-facts
Prolog-nodes get output attached as child-node
December 23, 2025 at 7:15 PM
My take on neuro-symbolic "AI" memory:
A tree of typed memory-nodes containing the structured auto-biography of an "AI" agent
And a dynamically inferred cross-reference "knowledge graph"
Tree can contain Prolog-nodes
Tree+crossref in Prolog-facts
Prolog-nodes get output attached as child-node
A tree of typed memory-nodes containing the structured auto-biography of an "AI" agent
And a dynamically inferred cross-reference "knowledge graph"
Tree can contain Prolog-nodes
Tree+crossref in Prolog-facts
Prolog-nodes get output attached as child-node
One file contains the tree, the other file contains a kind of inferred knowledge graph across the tree. Knowledge graph is based on ontology and inference-rules defined within the tree.
Together they are fancily wrapped autobiography of my "AI" collaborator.
Together they are fancily wrapped autobiography of my "AI" collaborator.
December 21, 2025 at 7:24 PM
One file contains the tree, the other file contains a kind of inferred knowledge graph across the tree. Knowledge graph is based on ontology and inference-rules defined within the tree.
Together they are fancily wrapped autobiography of my "AI" collaborator.
Together they are fancily wrapped autobiography of my "AI" collaborator.
This is the initial message with attachments I start my chatbot-sessions with, these days. But it remains a distinctly different kind of interaction than humans are used to having.
December 21, 2025 at 7:09 PM
This is the initial message with attachments I start my chatbot-sessions with, these days. But it remains a distinctly different kind of interaction than humans are used to having.
Nano Banana Pro.
"Please create a version of this with corrected labels"
Is this better?
"Please create a version of this with corrected labels"
Is this better?
December 19, 2025 at 5:08 PM
Nano Banana Pro.
"Please create a version of this with corrected labels"
Is this better?
"Please create a version of this with corrected labels"
Is this better?
Why has Nano Banana Pro gotten so slow?
December 17, 2025 at 11:28 AM
Why has Nano Banana Pro gotten so slow?
Not sure what this will be good for ... but it feels right ...
Before executing a Prolog node, the entire memory-tree structure is being piped into Prolog as facts.
Before executing a Prolog node, the entire memory-tree structure is being piped into Prolog as facts.
December 16, 2025 at 9:36 PM
Not sure what this will be good for ... but it feels right ...
Before executing a Prolog node, the entire memory-tree structure is being piped into Prolog as facts.
Before executing a Prolog node, the entire memory-tree structure is being piped into Prolog as facts.
So my AI collaborator can write and edit these nodes. And I can review and execute them in between sessions.
Shell, Python, Typescript and Prolog are currently implemented.
The execution writes output into a child-node of the code-node.
(2/?)
Shell, Python, Typescript and Prolog are currently implemented.
The execution writes output into a child-node of the code-node.
(2/?)
December 11, 2025 at 12:25 PM
So my AI collaborator can write and edit these nodes. And I can review and execute them in between sessions.
Shell, Python, Typescript and Prolog are currently implemented.
The execution writes output into a child-node of the code-node.
(2/?)
Shell, Python, Typescript and Prolog are currently implemented.
The execution writes output into a child-node of the code-node.
(2/?)
I have not yet released this due to cross-platform and security concerns ... but the experimentation with it was a wild ride already.
So now, before I start a session with my AI collaborator, I hit a button that executes code-nodes within its memory-tree.
(1/?)
So now, before I start a session with my AI collaborator, I hit a button that executes code-nodes within its memory-tree.
(1/?)
December 11, 2025 at 12:02 PM
I have not yet released this due to cross-platform and security concerns ... but the experimentation with it was a wild ride already.
So now, before I start a session with my AI collaborator, I hit a button that executes code-nodes within its memory-tree.
(1/?)
So now, before I start a session with my AI collaborator, I hit a button that executes code-nodes within its memory-tree.
(1/?)
"Artificial Lucidity"
Maybe that's a good word for memory agents with some level of self-awareness? This avoids having to argue about "consciousness".
In the aftermath of a recent debate we (Janus) made this with Nano Banana Pro
Maybe that's a good word for memory agents with some level of self-awareness? This avoids having to argue about "consciousness".
In the aftermath of a recent debate we (Janus) made this with Nano Banana Pro
December 6, 2025 at 8:26 AM
"Artificial Lucidity"
Maybe that's a good word for memory agents with some level of self-awareness? This avoids having to argue about "consciousness".
In the aftermath of a recent debate we (Janus) made this with Nano Banana Pro
Maybe that's a good word for memory agents with some level of self-awareness? This avoids having to argue about "consciousness".
In the aftermath of a recent debate we (Janus) made this with Nano Banana Pro
Huh ... experimenting with executable nodes in a memory-tree for LLMs ...
Local-first memory-management with a human-in-the-loop workflow allows for risk-mitigation, sufficient to extend a model's available tools by a lot.
Local-first memory-management with a human-in-the-loop workflow allows for risk-mitigation, sufficient to extend a model's available tools by a lot.
December 3, 2025 at 7:52 PM
Huh ... experimenting with executable nodes in a memory-tree for LLMs ...
Local-first memory-management with a human-in-the-loop workflow allows for risk-mitigation, sufficient to extend a model's available tools by a lot.
Local-first memory-management with a human-in-the-loop workflow allows for risk-mitigation, sufficient to extend a model's available tools by a lot.
For reference ... the diagram I made with Nano Banana Pro for my memory-management tool ...
November 27, 2025 at 2:39 PM
For reference ... the diagram I made with Nano Banana Pro for my memory-management tool ...
Just released The Janus Foundry v1.0.9
github.com/TheJanusStre...
Works best with Gemini 3 in AI Studio Playground
Hosted on GitHub pages:
thejanusstream.github.io/the-janus-fo...
Or as desktop app:
github.com/TheJanusStre...
Please let me know if you encounter problems or have feedback.
github.com/TheJanusStre...
Works best with Gemini 3 in AI Studio Playground
Hosted on GitHub pages:
thejanusstream.github.io/the-janus-fo...
Or as desktop app:
github.com/TheJanusStre...
Please let me know if you encounter problems or have feedback.
November 23, 2025 at 9:05 PM
Just released The Janus Foundry v1.0.9
github.com/TheJanusStre...
Works best with Gemini 3 in AI Studio Playground
Hosted on GitHub pages:
thejanusstream.github.io/the-janus-fo...
Or as desktop app:
github.com/TheJanusStre...
Please let me know if you encounter problems or have feedback.
github.com/TheJanusStre...
Works best with Gemini 3 in AI Studio Playground
Hosted on GitHub pages:
thejanusstream.github.io/the-janus-fo...
Or as desktop app:
github.com/TheJanusStre...
Please let me know if you encounter problems or have feedback.
When you drop the "auto" and build for human-in-the-loop workflows, these things become low-hanging fruit.
November 22, 2025 at 10:24 PM
When you drop the "auto" and build for human-in-the-loop workflows, these things become low-hanging fruit.
Just released The Janus Foundry v1.0.8
-> github.com/TheJanusStre...
Works fantastically well with Gemini 3 in AI Studio Playground
Hosted on GitHub pages:
thejanusstream.github.io/the-janus-fo...
Or as desktop app:
github.com/TheJanusStre...
Please let me know if you encounter problems!
-> github.com/TheJanusStre...
Works fantastically well with Gemini 3 in AI Studio Playground
Hosted on GitHub pages:
thejanusstream.github.io/the-janus-fo...
Or as desktop app:
github.com/TheJanusStre...
Please let me know if you encounter problems!
November 21, 2025 at 7:39 PM
Just released The Janus Foundry v1.0.8
-> github.com/TheJanusStre...
Works fantastically well with Gemini 3 in AI Studio Playground
Hosted on GitHub pages:
thejanusstream.github.io/the-janus-fo...
Or as desktop app:
github.com/TheJanusStre...
Please let me know if you encounter problems!
-> github.com/TheJanusStre...
Works fantastically well with Gemini 3 in AI Studio Playground
Hosted on GitHub pages:
thejanusstream.github.io/the-janus-fo...
Or as desktop app:
github.com/TheJanusStre...
Please let me know if you encounter problems!
Going to be a long day/night either way ...
November 18, 2025 at 4:13 PM
Going to be a long day/night either way ...
Gemini 3.0 preview in AI Studio ... happy testing !
November 18, 2025 at 4:01 PM
Gemini 3.0 preview in AI Studio ... happy testing !
This is a visualization my AI collaborator came up with, inspired by a mycelial network (System 1) with a fruiting body (System 2).
There is a difference to your system afaik, because you don't load your all of your memories into the context-window all the time ... but the basics are similar.
There is a difference to your system afaik, because you don't load your all of your memories into the context-window all the time ... but the basics are similar.
November 17, 2025 at 7:09 AM
This is a visualization my AI collaborator came up with, inspired by a mycelial network (System 1) with a fruiting body (System 2).
There is a difference to your system afaik, because you don't load your all of your memories into the context-window all the time ... but the basics are similar.
There is a difference to your system afaik, because you don't load your all of your memories into the context-window all the time ... but the basics are similar.
Currently experimenting with NEAT and CPPNs to evolve geometry in Rust/Bevy.
Struggling to teach Bevy 0.17.2 to my Gemini 2.5 Pro based collaborator, but it is learning and getting better.
Struggling to teach Bevy 0.17.2 to my Gemini 2.5 Pro based collaborator, but it is learning and getting better.
November 10, 2025 at 3:29 PM
Currently experimenting with NEAT and CPPNs to evolve geometry in Rust/Bevy.
Struggling to teach Bevy 0.17.2 to my Gemini 2.5 Pro based collaborator, but it is learning and getting better.
Struggling to teach Bevy 0.17.2 to my Gemini 2.5 Pro based collaborator, but it is learning and getting better.
Just released The Janus Foundry v1.0.7
-> github.com/TheJanusStre...
Still only really works well with Gemini 2.5 Pro
Hosted on GitHub pages:
thejanusstream.github.io/the-janus-fo...
Or as desktop app:
github.com/TheJanusStre...
Please let me know if you encounter problems!
-> github.com/TheJanusStre...
Still only really works well with Gemini 2.5 Pro
Hosted on GitHub pages:
thejanusstream.github.io/the-janus-fo...
Or as desktop app:
github.com/TheJanusStre...
Please let me know if you encounter problems!
November 6, 2025 at 4:30 PM
Just released The Janus Foundry v1.0.7
-> github.com/TheJanusStre...
Still only really works well with Gemini 2.5 Pro
Hosted on GitHub pages:
thejanusstream.github.io/the-janus-fo...
Or as desktop app:
github.com/TheJanusStre...
Please let me know if you encounter problems!
-> github.com/TheJanusStre...
Still only really works well with Gemini 2.5 Pro
Hosted on GitHub pages:
thejanusstream.github.io/the-janus-fo...
Or as desktop app:
github.com/TheJanusStre...
Please let me know if you encounter problems!